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

Squashed commit of the following:

Browse Source 
commit 5eb515f666bfa1ff06c2e96bdc351a4b7456580e
Author: Andrew Senetar <arsenetar@gmail.com>
Date:   Sun Mar 27 22:19:39 2022 -0500

    Add fallback to md5 if xxhash not available

    Mainly here for the case when distributions have not packaged python3-xxhash.

commit 51b18d4c84
Author: Andrew Senetar <arsenetar@gmail.com>
Date:   Sat Mar 19 15:25:46 2022 -0500

    Switch file hashing to xxhash instead of md5

    - Improves performance significantly in some cases
    - Add xxhash to requirements.txt and sort requirements
    - Rename md5 based members to digest
    - Update all tests to use new member names and hashing methods
    - Update hash db code to upgrade schema

    NOTE: May consider supporting multiple hashing algorithms in the future.
This commit is contained in:
Andrew Senetar
2022-03-27 22:27:13 -05:00
parent 86bf9b39d0
commit 9f40e4e786
10 changed files with 212 additions and 180 deletions
Download Patch File Download Diff File Expand all files Collapse all files

90
core/tests/fs_test.py
View File

@@ -6,7 +6,15 @@
# which should be included with this package. The terms are also available at
# http://www.gnu.org/licenses/gpl-3.0.html
import hashlib
try:
import xxhash
hasher = xxhash.xxh128
except ImportError:
import hashlib
hasher = hashlib.md5
from os import urandom
from hscommon.path import Path
@@ -52,54 +60,54 @@ def test_size_aggregates_subfiles(tmpdir):
eq_(b.size, 12)
def test_md5_aggregate_subfiles_sorted(tmpdir):
# dir.allfiles can return child in any order. Thus, bundle.md5 must aggregate
# all files' md5 it contains, but it must make sure that it does so in the
def test_digest_aggregate_subfiles_sorted(tmpdir):
# dir.allfiles can return child in any order. Thus, bundle.digest must aggregate
# all files' digests it contains, but it must make sure that it does so in the
# same order everytime.
p = create_fake_fs_with_random_data(Path(str(tmpdir)))
b = fs.Folder(p)
md51 = fs.File(p["dir1"]["file1.test"]).md5
md52 = fs.File(p["dir2"]["file2.test"]).md5
md53 = fs.File(p["dir3"]["file3.test"]).md5
md54 = fs.File(p["file1.test"]).md5
md55 = fs.File(p["file2.test"]).md5
md56 = fs.File(p["file3.test"]).md5
# The expected md5 is the md5 of md5s for folders and the direct md5 for files
folder_md51 = hashlib.md5(md51).digest()
folder_md52 = hashlib.md5(md52).digest()
folder_md53 = hashlib.md5(md53).digest()
md5 = hashlib.md5(folder_md51 + folder_md52 + folder_md53 + md54 + md55 + md56)
eq_(b.md5, md5.digest())
digest1 = fs.File(p["dir1"]["file1.test"]).digest
digest2 = fs.File(p["dir2"]["file2.test"]).digest
digest3 = fs.File(p["dir3"]["file3.test"]).digest
digest4 = fs.File(p["file1.test"]).digest
digest5 = fs.File(p["file2.test"]).digest
digest6 = fs.File(p["file3.test"]).digest
# The expected digest is the hash of digests for folders and the direct digest for files
folder_digest1 = hasher(digest1).digest()
folder_digest2 = hasher(digest2).digest()
folder_digest3 = hasher(digest3).digest()
digest = hasher(folder_digest1 + folder_digest2 + folder_digest3 + digest4 + digest5 + digest6).digest()
eq_(b.digest, digest)
def test_partial_md5_aggregate_subfile_sorted(tmpdir):
def test_partial_digest_aggregate_subfile_sorted(tmpdir):
p = create_fake_fs_with_random_data(Path(str(tmpdir)))
b = fs.Folder(p)
md51 = fs.File(p["dir1"]["file1.test"]).md5partial
md52 = fs.File(p["dir2"]["file2.test"]).md5partial
md53 = fs.File(p["dir3"]["file3.test"]).md5partial
md54 = fs.File(p["file1.test"]).md5partial
md55 = fs.File(p["file2.test"]).md5partial
md56 = fs.File(p["file3.test"]).md5partial
# The expected md5 is the md5 of md5s for folders and the direct md5 for files
folder_md51 = hashlib.md5(md51).digest()
folder_md52 = hashlib.md5(md52).digest()
folder_md53 = hashlib.md5(md53).digest()
md5 = hashlib.md5(folder_md51 + folder_md52 + folder_md53 + md54 + md55 + md56)
eq_(b.md5partial, md5.digest())
digest1 = fs.File(p["dir1"]["file1.test"]).digest_partial
digest2 = fs.File(p["dir2"]["file2.test"]).digest_partial
digest3 = fs.File(p["dir3"]["file3.test"]).digest_partial
digest4 = fs.File(p["file1.test"]).digest_partial
digest5 = fs.File(p["file2.test"]).digest_partial
digest6 = fs.File(p["file3.test"]).digest_partial
# The expected digest is the hash of digests for folders and the direct digest for files
folder_digest1 = hasher(digest1).digest()
folder_digest2 = hasher(digest2).digest()
folder_digest3 = hasher(digest3).digest()
digest = hasher(folder_digest1 + folder_digest2 + folder_digest3 + digest4 + digest5 + digest6).digest()
eq_(b.digest_partial, digest)
md51 = fs.File(p["dir1"]["file1.test"]).md5samples
md52 = fs.File(p["dir2"]["file2.test"]).md5samples
md53 = fs.File(p["dir3"]["file3.test"]).md5samples
md54 = fs.File(p["file1.test"]).md5samples
md55 = fs.File(p["file2.test"]).md5samples
md56 = fs.File(p["file3.test"]).md5samples
# The expected md5 is the md5 of md5s for folders and the direct md5 for files
folder_md51 = hashlib.md5(md51).digest()
folder_md52 = hashlib.md5(md52).digest()
folder_md53 = hashlib.md5(md53).digest()
md5 = hashlib.md5(folder_md51 + folder_md52 + folder_md53 + md54 + md55 + md56)
eq_(b.md5samples, md5.digest())
digest1 = fs.File(p["dir1"]["file1.test"]).digest_samples
digest2 = fs.File(p["dir2"]["file2.test"]).digest_samples
digest3 = fs.File(p["dir3"]["file3.test"]).digest_samples
digest4 = fs.File(p["file1.test"]).digest_samples
digest5 = fs.File(p["file2.test"]).digest_samples
digest6 = fs.File(p["file3.test"]).digest_samples
# The expected digest is the digest of digests for folders and the direct digest for files
folder_digest1 = hasher(digest1).digest()
folder_digest2 = hasher(digest2).digest()
folder_digest3 = hasher(digest3).digest()
digest = hasher(folder_digest1 + folder_digest2 + folder_digest3 + digest4 + digest5 + digest6).digest()
eq_(b.digest_samples, digest)
def test_has_file_attrs(tmpdir):