diff --git a/PKG-INFO b/PKG-INFO
index b07e4b866fcb26f1f4f87d4f7060e879115afe6b..3a4aa502b5df44a95859cac637ecbcecec8ce45b 100644
--- a/PKG-INFO
+++ b/PKG-INFO
@@ -1,6 +1,6 @@
Metadata-Version: 2.1
Name: swh.model
-Version: 0.0.28
+Version: 0.0.29
Summary: Software Heritage data model
Home-page: https://forge.softwareheritage.org/diffusion/DMOD/
Author: Software Heritage developers
diff --git a/docs/persistent-identifiers.rst b/docs/persistent-identifiers.rst
index 89b0365d264e70700cbb8298aee0b8b9942b28cb..a588e9debf6363c4278f99fad71e48cd198a2562 100644
--- a/docs/persistent-identifiers.rst
+++ b/docs/persistent-identifiers.rst
@@ -225,3 +225,15 @@ Examples:
Note that resolution via Identifiers.org does not support contextual
information, due to `syntactic incompatibilities
<http://identifiers.org/documentation#custom_requests>`_.
+
+
+References
+==========
+
+* Roberto Di Cosmo, Morane Gruenpeter, Stefano Zacchiroli. `Identifiers for
+ Digital Objects: the Case of Software Source Code Preservation
+ <https://hal.archives-ouvertes.fr/hal-01865790v4>`_. In Proceedings of `iPRES
+ 2018 <https://ipres2018.org/>`_: 15th International Conference on Digital
+ Preservation, Boston, MA, USA, September 2018, 9 pages.
+
+
diff --git a/swh.model.egg-info/PKG-INFO b/swh.model.egg-info/PKG-INFO
index b07e4b866fcb26f1f4f87d4f7060e879115afe6b..3a4aa502b5df44a95859cac637ecbcecec8ce45b 100644
--- a/swh.model.egg-info/PKG-INFO
+++ b/swh.model.egg-info/PKG-INFO
@@ -1,6 +1,6 @@
Metadata-Version: 2.1
Name: swh.model
-Version: 0.0.28
+Version: 0.0.29
Summary: Software Heritage data model
Home-page: https://forge.softwareheritage.org/diffusion/DMOD/
Author: Software Heritage developers
diff --git a/swh.model.egg-info/SOURCES.txt b/swh.model.egg-info/SOURCES.txt
index 81e3d7dfcf82c118bb475c93c2fbef1a95c992d4..8fa4241d3cf11fc0f760e280dee51bf158b4d001 100644
--- a/swh.model.egg-info/SOURCES.txt
+++ b/swh.model.egg-info/SOURCES.txt
@@ -15,12 +15,6 @@ version.txt
bin/git-revhash
bin/swh-hashtree
bin/swh-revhash
-debian/changelog
-debian/compat
-debian/control
-debian/copyright
-debian/rules
-debian/source/format
docs/.gitignore
docs/Makefile
docs/Makefile.local
diff --git a/swh/model/hashutil.py b/swh/model/hashutil.py
index e58f6870fc121ddd674253a918c8849de822589f..de85857e1294bb82a1e851966878d6887a4b9c7b 100644
--- a/swh/model/hashutil.py
+++ b/swh/model/hashutil.py
@@ -48,21 +48,6 @@ Basic usage examples:
f.write(chunk)
hashes = h.hexdigest() # returns a dict of {hash_algo_name: hash_in_hex}
- Note: Prior to this, we would have to use chunk_cb (cf. hash_file,
- hash_path)
-
-
-This module also defines the following (deprecated) hashing functions:
-
-- hash_file: Hash the contents of the given file object with the given
- algorithms (defaulting to DEFAULT_ALGORITHMS if none provided).
-
-- hash_data: Hash the given binary blob with the given algorithms
- (defaulting to DEFAULT_ALGORITHMS if none provided).
-
-- hash_path: Hash the contents of the file at the given path with the
- given algorithms (defaulting to DEFAULT_ALGORITHMS if none
- provided).
"""
@@ -290,84 +275,6 @@ def _new_hash(algo, length=None):
return _new_hashlib_hash(algo)
-def hash_file(fobj, length=None, algorithms=DEFAULT_ALGORITHMS,
- chunk_cb=None):
- """(Deprecated) cf. MultiHash.from_file
-
- Hash the contents of the given file object with the given algorithms.
-
- Args:
- fobj: a file-like object
- length (int): the length of the contents of the file-like
- object (for the git-specific algorithms)
- algorithms (set): the hashing algorithms to be used, as an
- iterable over strings
- chunk_cb (fun): a callback function taking a chunk of data as
- parameter
-
- Returns:
- a dict mapping each algorithm to a digest (bytes by default).
-
- Raises:
- ValueError if algorithms contains an unknown hash algorithm.
-
- """
- h = MultiHash(algorithms, length)
- while True:
- chunk = fobj.read(HASH_BLOCK_SIZE)
- if not chunk:
- break
- h.update(chunk)
- if chunk_cb:
- chunk_cb(chunk)
-
- return h.digest()
-
-
-def hash_path(path, algorithms=DEFAULT_ALGORITHMS, chunk_cb=None):
- """(deprecated) cf. MultiHash.from_path
-
- Hash the contents of the file at the given path with the given
- algorithms.
-
- Args:
- path (str): the path of the file to hash
- algorithms (set): the hashing algorithms used
- chunk_cb (fun): a callback function taking a chunk of data as parameter
-
- Returns: a dict mapping each algorithm to a bytes digest.
-
- Raises:
- ValueError if algorithms contains an unknown hash algorithm.
- OSError on file access error
-
- """
- length = os.path.getsize(path)
- with open(path, 'rb') as fobj:
- hashes = hash_file(fobj, length, algorithms, chunk_cb=chunk_cb)
- hashes['length'] = length
- return hashes
-
-
-def hash_data(data, algorithms=DEFAULT_ALGORITHMS):
- """(deprecated) cf. MultiHash.from_data
-
- Hash the given binary blob with the given algorithms.
-
- Args:
- data (bytes): raw content to hash
- algorithms (set): the hashing algorithms used
-
- Returns: a dict mapping each algorithm to a bytes digest
-
- Raises:
- TypeError if data does not support the buffer interface.
- ValueError if algorithms contains an unknown hash algorithm.
-
- """
- return MultiHash.from_data(data, hash_names=algorithms).digest()
-
-
def hash_git_data(data, git_type, base_algo='sha1'):
"""Hash the given data as a git object of type git_type.
diff --git a/swh/model/tests/test_hashutil.py b/swh/model/tests/test_hashutil.py
index 0e41068900686474db83d82ddfc7b9e54c60f36d..abdff979f5d01b80615f79da6cf986001dc11cb0 100644
--- a/swh/model/tests/test_hashutil.py
+++ b/swh/model/tests/test_hashutil.py
@@ -111,27 +111,6 @@ class MultiHashTest(BaseHashutil):
class Hashutil(BaseHashutil):
- def test_hash_data(self):
- checksums = hashutil.hash_data(self.data)
- self.assertEqual(checksums, self.checksums)
- self.assertFalse('length' in checksums)
-
- def test_hash_data_with_length(self):
- expected_checksums = self.checksums.copy()
- expected_checksums['length'] = len(self.data)
-
- algos = set(['length']).union(hashutil.DEFAULT_ALGORITHMS)
- checksums = hashutil.hash_data(self.data, algorithms=algos)
-
- self.assertEqual(checksums, expected_checksums)
- self.assertTrue('length' in checksums)
-
- def test_hash_data_unknown_hash(self):
- with self.assertRaises(ValueError) as cm:
- hashutil.hash_data(self.data, ['unknown-hash'])
-
- self.assertIn('Unexpected hashing algorithm', cm.exception.args[0])
- self.assertIn('unknown-hash', cm.exception.args[0])
def test_hash_git_data(self):
checksums = {
@@ -148,30 +127,6 @@ class Hashutil(BaseHashutil):
self.assertIn('Unexpected git object type', cm.exception.args[0])
self.assertIn('unknown-git-type', cm.exception.args[0])
- def test_hash_file(self):
- fobj = io.BytesIO(self.data)
-
- checksums = hashutil.hash_file(fobj, length=len(self.data))
- self.assertEqual(checksums, self.checksums)
-
- def test_hash_file_missing_length(self):
- fobj = io.BytesIO(self.data)
-
- with self.assertRaises(ValueError) as cm:
- hashutil.hash_file(fobj, algorithms=['sha1_git'])
-
- self.assertIn('Missing length', cm.exception.args[0])
-
- def test_hash_path(self):
- with tempfile.NamedTemporaryFile(delete=False) as f:
- f.write(self.data)
-
- hashes = hashutil.hash_path(f.name)
- os.remove(f.name)
-
- self.checksums['length'] = len(self.data)
- self.assertEqual(self.checksums, hashes)
-
def test_hash_to_hex(self):
for type in self.checksums:
hex = self.hex_checksums[type]
diff --git a/swh/model/tests/test_identifiers.py b/swh/model/tests/test_identifiers.py
index de96865e3bb816a396ca50bd7edf9d3065f3d031..1492b87ed0c23b505df2988c7913caec32912f88 100644
--- a/swh/model/tests/test_identifiers.py
+++ b/swh/model/tests/test_identifiers.py
@@ -103,7 +103,8 @@ class ContentIdentifier(unittest.TestCase):
tzinfo=datetime.timezone.utc),
}
- self.content_id = hashutil.hash_data(self.content['data'])
+ self.content_id = hashutil.MultiHash.from_data(
+ self.content['data']).digest()
def test_content_identifier(self):
self.assertEqual(identifiers.content_identifier(self.content),
diff --git a/swh/model/tests/test_validators.py b/swh/model/tests/test_validators.py
index 8c8512e9cc6978e577d9e774be578244eacf21ac..691c579e4704e96733ecebba027411b1453f7eda 100644
--- a/swh/model/tests/test_validators.py
+++ b/swh/model/tests/test_validators.py
@@ -9,6 +9,10 @@ import unittest
from swh.model import exceptions, hashutil, validators
+def hash_data(raw_content):
+ return hashutil.MultiHash.from_data(raw_content).digest()
+
+
class TestValidators(unittest.TestCase):
def setUp(self):
self.valid_visible_content = {
@@ -20,7 +24,7 @@ class TestValidators(unittest.TestCase):
}
self.valid_visible_content.update(
- hashutil.hash_data(self.valid_visible_content['data']))
+ hash_data(self.valid_visible_content['data']))
self.valid_absent_content = {
'status': 'absent',
@@ -34,7 +38,7 @@ class TestValidators(unittest.TestCase):
self.invalid_content_hash_mismatch = self.valid_visible_content.copy()
self.invalid_content_hash_mismatch.update(
- hashutil.hash_data(b"this is not the data you're looking for"))
+ hash_data(b"this is not the data you're looking for"))
def test_validate_content(self):
self.assertTrue(
diff --git a/version.txt b/version.txt
index b5af97970e87e33ff6a989b707c5e85141bd4e58..8eba90c0f40bfe79683d690c0c710ce0a28a889d 100644
--- a/version.txt
+++ b/version.txt
@@ -1 +1 @@
-v0.0.28-0-g4e6bce9
\ No newline at end of file
+v0.0.29-0-gfa140b2
\ No newline at end of file