Merge tag 'debian/6.5.1-1_swh1' into debian/buster-swh

PKG-INFO

 Metadata-Version: 2.1
 Name: swh.model
-Version: 6.5.0
+Version: 6.5.1
 Summary: Software Heritage data model
 Home-page: https://forge.softwareheritage.org/diffusion/DMOD/
 Author: Software Heritage developers

debian/changelog

-swh-model (6.5.0-1~swh1~bpo10+1) buster-swh; urgency=medium
+swh-model (6.5.1-1~swh1) unstable-swh; urgency=medium
 
-  * Rebuild for buster-swh
+  * New upstream release 6.5.1     - (tagged by Antoine Lambert
+    <anlambert@softwareheritage.org> on 2022-09-30 15:23:14 +0200)
+  * Upstream changes:     - version 6.5.1
 
- -- Software Heritage autobuilder (on jenkins-debian1) <jenkins@jenkins-debian1.internal.softwareheritage.org>  Mon, 26 Sep 2022 16:17:36 +0000
+ -- Software Heritage autobuilder (on jenkins-debian1) <jenkins@jenkins-debian1.internal.softwareheritage.org>  Fri, 30 Sep 2022 13:27:54 +0000
 
 swh-model (6.5.0-1~swh1) unstable-swh; urgency=medium
 

swh.model.egg-info/PKG-INFO

 Metadata-Version: 2.1
 Name: swh.model
-Version: 6.5.0
+Version: 6.5.1
 Summary: Software Heritage data model
 Home-page: https://forge.softwareheritage.org/diffusion/DMOD/
 Author: Software Heritage developers

swh/model/from_disk.py

@@ -300,16 +300,20 @@ def extract_regex_objs(
 
     Args:
       root_path (bytes): path to the root directory
-      patterns (list of byte): patterns to match
+      patterns (list of byte): shell patterns to match
 
      Yields:
         an SRE_Pattern object
     """
     absolute_root_path = os.path.abspath(root_path)
     for pattern in patterns:
-        for path in glob.glob(pattern):
-            absolute_path = os.path.abspath(path)
-            if not absolute_path.startswith(absolute_root_path):
+        if os.path.isabs(pattern):
+            pattern = os.path.relpath(pattern, root_path)
+        # python 3.10 has a `root_dir` argument for glob, but not the previous
+        # version. So we adjust the pattern
+        test_pattern = os.path.join(absolute_root_path, pattern)
+        for path in glob.glob(test_pattern):
+            if os.path.isabs(path) and not path.startswith(absolute_root_path):
                 error_msg = (
                     b'The path "' + path + b'" is not a subdirectory or relative '
                     b'to the root directory path: "' + root_path + b'"'
@@ -326,7 +330,7 @@ def ignore_directories_patterns(root_path: bytes, patterns: Iterable[bytes]):
 
     Args:
       root_path (bytes): path of the root directory
-      patterns (list of byte): patterns to ignore
+      patterns (list of bytes): patterns to ignore
 
     Returns:
       a directory filter for :func:`directory_to_objects`

swh/model/hashutil.py

@@ -58,7 +58,9 @@ from io import BytesIO
 import os
 from typing import Callable, Dict, Optional, Union
 
-ALGORITHMS = set(["sha1", "sha256", "sha1_git", "blake2s256", "blake2b512", "md5"])
+ALGORITHMS = set(
+    ["sha1", "sha256", "sha1_git", "blake2s256", "blake2b512", "md5", "sha512"]
+)
 """Hashing algorithms supported by this module"""
 
 DEFAULT_ALGORITHMS = set(["sha1", "sha256", "sha1_git", "blake2s256"])

swh/model/tests/test_hashutil.py

@@ -112,34 +112,44 @@ def test_multi_hash_file_bytehexdigest(hash_test_data):
     assert checksums == hash_test_data.bytehex_checksums
 
 
-def test_multi_hash_file_with_md5(hash_test_data):
+EXTRA_HASH_ALGOS = ["md5", "sha512"]
+
+
+@pytest.mark.parametrize("hash_algo", EXTRA_HASH_ALGOS)
+def test_multi_hash_file_with_extra_hash_algo(hash_test_data, hash_algo):
     fobj = io.BytesIO(hash_test_data.data)
 
     checksums = MultiHash.from_file(
-        fobj, hash_names=DEFAULT_ALGORITHMS | {"md5"}, length=len(hash_test_data.data)
+        fobj,
+        hash_names=DEFAULT_ALGORITHMS | {hash_algo},
+        length=len(hash_test_data.data),
     ).digest()
-    md5sum = {"md5": hashlib.md5(hash_test_data.data).digest()}
-    assert checksums == {**hash_test_data.checksums, **md5sum}
+    checksum = {hash_algo: hashlib.new(hash_algo, hash_test_data.data).digest()}
+    assert checksums == {**hash_test_data.checksums, **checksum}
 
 
-def test_multi_hash_file_hexdigest_with_md5(hash_test_data):
+@pytest.mark.parametrize("hash_algo", EXTRA_HASH_ALGOS)
+def test_multi_hash_file_hexdigest_with_extra_hash_algo(hash_test_data, hash_algo):
     fobj = io.BytesIO(hash_test_data.data)
     length = len(hash_test_data.data)
     checksums = MultiHash.from_file(
-        fobj, hash_names=DEFAULT_ALGORITHMS | {"md5"}, length=length
+        fobj, hash_names=DEFAULT_ALGORITHMS | {hash_algo}, length=length
     ).hexdigest()
-    md5sum = {"md5": hashlib.md5(hash_test_data.data).hexdigest()}
-    assert checksums == {**hash_test_data.hex_checksums, **md5sum}
+    checksum = {hash_algo: hashlib.new(hash_algo, hash_test_data.data).hexdigest()}
+    assert checksums == {**hash_test_data.hex_checksums, **checksum}
 
 
-def test_multi_hash_file_bytehexdigest_with_md5(hash_test_data):
+@pytest.mark.parametrize("hash_algo", EXTRA_HASH_ALGOS)
+def test_multi_hash_file_bytehexdigest_with_extra_algo(hash_test_data, hash_algo):
     fobj = io.BytesIO(hash_test_data.data)
     length = len(hash_test_data.data)
     checksums = MultiHash.from_file(
-        fobj, hash_names=DEFAULT_ALGORITHMS | {"md5"}, length=length
+        fobj, hash_names=DEFAULT_ALGORITHMS | {hash_algo}, length=length
     ).bytehexdigest()
-    md5sum = {"md5": hash_to_bytehex(hashlib.md5(hash_test_data.data).digest())}
-    assert checksums == {**hash_test_data.bytehex_checksums, **md5sum}
+    checksum = {
+        hash_algo: hash_to_bytehex(hashlib.new(hash_algo, hash_test_data.data).digest())
+    }
+    assert checksums == {**hash_test_data.bytehex_checksums, **checksum}
 
 
 def test_multi_hash_file_missing_length(hash_test_data):