diff --git a/.gitignore b/.gitignore
index 303d302636f5d8ff2d1d08c9764cc601676f2f0e..43b2d615d8483732cf4b72e4855b3201d62fd2e7 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,9 +1,13 @@
-*.pyc
-*.sw?
*~
+build
.coverage
+dist
+*.egg-info/
.eggs/
+.hypothesis
+*.pyc
__pycache__
-*.egg-info/
-dist
+.pytest_cache
+*.sw?
+.tox
version.txt
diff --git a/MANIFEST.in b/MANIFEST.in
index e7c46fcaa031efc7023aa243e3ff94ba7996ea65..99c8c1ac0f068c4ad84b7bac65a8316468c3d049 100644
--- a/MANIFEST.in
+++ b/MANIFEST.in
@@ -1,4 +1,6 @@
+include README.md
include Makefile
include requirements.txt
include requirements-swh.txt
include version.txt
+recursive-include swh/model/tests/data *.tgz
diff --git a/PKG-INFO b/PKG-INFO
index 653b8da334326f55a86ea9c15ce5b7d3508e2f22..b07e4b866fcb26f1f4f87d4f7060e879115afe6b 100644
--- a/PKG-INFO
+++ b/PKG-INFO
@@ -1,10 +1,38 @@
-Metadata-Version: 1.0
+Metadata-Version: 2.1
Name: swh.model
-Version: 0.0.27
+Version: 0.0.28
Summary: Software Heritage data model
Home-page: https://forge.softwareheritage.org/diffusion/DMOD/
Author: Software Heritage developers
Author-email: swh-devel@inria.fr
License: UNKNOWN
-Description: UNKNOWN
+Project-URL: Bug Reports, https://forge.softwareheritage.org/maniphest
+Project-URL: Funding, https://www.softwareheritage.org/donate
+Project-URL: Source, https://forge.softwareheritage.org/source/swh-model
+Description: swh-model
+ =========
+
+ Implementation of the Data model of the Software Heritage project, used to
+ archive source code artifacts.
+
+ This module defines the notion of Persistent Identifier (PID) and provides
+ tools to compute them:
+
+ ```sh
+ $ swh-identify fork.c kmod.c sched/deadline.c
+ swh:1:cnt:2e391c754ae730bd2d8520c2ab497c403220c6e3 fork.c
+ swh:1:cnt:0277d1216f80ae1adeed84a686ed34c9b2931fc2 kmod.c
+ swh:1:cnt:57b939c81bce5d06fa587df8915f05affbe22b82 sched/deadline.c
+
+ $ swh-identify --no-filename /usr/src/linux/kernel/
+ swh:1:dir:f9f858a48d663b3809c9e2f336412717496202ab
+ ```
+
Platform: UNKNOWN
+Classifier: Programming Language :: Python :: 3
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3)
+Classifier: Operating System :: OS Independent
+Classifier: Development Status :: 5 - Production/Stable
+Description-Content-Type: text/markdown
+Provides-Extra: testing
diff --git a/README.md b/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..f26f274ca14c90dc44905f5b27b8502e27d71f53
--- /dev/null
+++ b/README.md
@@ -0,0 +1,18 @@
+swh-model
+=========
+
+Implementation of the Data model of the Software Heritage project, used to
+archive source code artifacts.
+
+This module defines the notion of Persistent Identifier (PID) and provides
+tools to compute them:
+
+```sh
+ $ swh-identify fork.c kmod.c sched/deadline.c
+ swh:1:cnt:2e391c754ae730bd2d8520c2ab497c403220c6e3 fork.c
+ swh:1:cnt:0277d1216f80ae1adeed84a686ed34c9b2931fc2 kmod.c
+ swh:1:cnt:57b939c81bce5d06fa587df8915f05affbe22b82 sched/deadline.c
+
+ $ swh-identify --no-filename /usr/src/linux/kernel/
+ swh:1:dir:f9f858a48d663b3809c9e2f336412717496202ab
+```
diff --git a/bin/swh-hashtree b/bin/swh-hashtree
new file mode 100755
index 0000000000000000000000000000000000000000..faf258fddb4f8f6d21fc13eaee34c9cc077aa27d
--- /dev/null
+++ b/bin/swh-hashtree
@@ -0,0 +1,58 @@
+#!/usr/bin/env python3
+
+# Use sample:
+# swh-hashtree --path . --ignore '.svn' --ignore '.git-svn' \
+# --ignore-empty-folders
+# 38f8d2c3a951f6b94007896d0981077e48bbd702
+
+import click
+import os
+
+from swh.model import from_disk, hashutil
+
+
+def combine_filters(*filters):
+ """Combine several ignore filters"""
+ if len(filters) == 0:
+ return from_disk.accept_all_directories
+ elif len(filters) == 1:
+ return filters[0]
+
+ def combined_filter(*args, **kwargs):
+ return all(filter(*args, **kwargs) for filter in filters)
+
+ return combined_filter
+
+
+@click.command()
+@click.option('--path', default='.',
+ help='Optional path to hash.')
+@click.option('--ignore-empty-folder', is_flag=True, default=False,
+ help='Ignore empty folder.')
+@click.option('--ignore', multiple=True,
+ help='Ignore pattern.')
+def main(path, ignore_empty_folder=False, ignore=None):
+
+ filters = []
+ if ignore_empty_folder:
+ filters.append(from_disk.ignore_empty_directories)
+ if ignore:
+ filters.append(
+ from_disk.ignore_named_directories(
+ [os.fsencode(name) for name in ignore]
+ )
+ )
+
+ try:
+ d = from_disk.Directory.from_disk(path=os.fsencode(path),
+ dir_filter=combine_filters(*filters))
+ hash = d.hash
+ except Exception as e:
+ print(e)
+ return
+ else:
+ print(hashutil.hash_to_hex(hash))
+
+
+if __name__ == '__main__':
+ main()
diff --git a/docs/Makefile b/docs/Makefile
index c30c50ab01ec91da18f0718b7cfd052f046c2e44..b97c7532e5b946df72b8641f22f6e3e2ba84602c 100644
--- a/docs/Makefile
+++ b/docs/Makefile
@@ -1 +1,2 @@
include ../../swh-docs/Makefile.sphinx
+-include Makefile.local
diff --git a/docs/Makefile.local b/docs/Makefile.local
new file mode 100644
index 0000000000000000000000000000000000000000..352ffd352651af5bb929bc5b2c081e77cb42c401
--- /dev/null
+++ b/docs/Makefile.local
@@ -0,0 +1,14 @@
+sphinx/html: images
+sphinx/clean: clean-images
+
+images:
+ make -C images/
+clean-images:
+ make -C images/ clean
+
+.PHONY: images clean-images
+
+
+# Local Variables:
+# mode: makefile
+# End:
diff --git a/docs/images/Makefile b/docs/images/Makefile
index 2bc794e965ba7be048c00263d49e6a8c0769a5b5..ddc859daf3b0c1c6888808a395fe961751fefcd8 100644
--- a/docs/images/Makefile
+++ b/docs/images/Makefile
@@ -7,19 +7,11 @@ BUILD_TARGETS += $(MERKLE_DAG)
all: $(BUILD_TARGETS)
-# dia exporters
-
-%.eps: %.dia
- dia -t eps --export $@ $<
-
%.svg: %.dia
- dia -t svg --export $@ $<
-
-# generic converters
-
-%.pdf: %.eps
- epstopdf $<
+ inkscape -l $@ $<
+%.pdf: %.dia
+ inkscape -A $@ $<
clean:
-rm -f $(BUILD_TARGETS)
diff --git a/docs/index.rst b/docs/index.rst
index 74756e7522401bb4e7fa63d9231fc401524f1c6f..55ab5fd51185bd109cff0e0dc0532096726e6b02 100644
--- a/docs/index.rst
+++ b/docs/index.rst
@@ -1,7 +1,10 @@
.. _swh-model:
-Software Heritage - Development Documentation
-=============================================
+Software Heritage - Data model
+==============================
+
+Implementation of the :ref:`data-model` to archive source code artifacts.
+
.. toctree::
:maxdepth: 2
diff --git a/docs/persistent-identifiers.rst b/docs/persistent-identifiers.rst
index 29bf797e144d0a0ba19293caf3aca6f0497b55f9..89b0365d264e70700cbb8298aee0b8b9942b28cb 100644
--- a/docs/persistent-identifiers.rst
+++ b/docs/persistent-identifiers.rst
@@ -128,23 +128,6 @@ Examples
of the entire Darktable Git repository taken on 4 May 2017 from GitHub
-Resolution
-----------
-
-Persistent identifiers can be resolved using the Software Heritage Web
-application (see :py:mod:`swh.web`).
-
-In particular, the root endpoint ``/`` can be given a persistent identifier and
-will lead to the browsing page of the corresponding object, like this:
-``https://archive.softwareheritage.org/<identifier>``. For example:
-
-* `<https://archive.softwareheritage.org/swh:1:cnt:94a9ed024d3859793618152ea559a168bbcbb5e2>`_
-* `<https://archive.softwareheritage.org/swh:1:dir:d198bc9d7a6bcf6db04f476d29314f157507d505>`_
-* `<https://archive.softwareheritage.org/swh:1:rev:309cf2674ee7a0749978cf8265ab91a60aea0f7d>`_
-* `<https://archive.softwareheritage.org/swh:1:rel:22ece559cc7cc2364edc5e5593d63ae8bd229f9f>`_
-* `<https://archive.softwareheritage.org/swh:1:snp:c7c108084bc0bf3d81436bf980b46e98bd338453>`_
-
-
Contextual information
======================
@@ -191,3 +174,54 @@ The following piece of contextual information are supported:
* software origin: where a given object has been found or observed in the wild,
as the URI that was used by Software Heritage to ingest the object into the
archive
+
+
+Resolution
+==========
+
+
+Dedicated resolvers
+-------------------
+
+Persistent identifiers can be resolved using the Software Heritage Web
+application (see :py:mod:`swh.web`). In particular, the **root endpoint**
+``/`` can be given a persistent identifier and will lead to the browsing page
+of the corresponding object, like this:
+``https://archive.softwareheritage.org/<identifier>``.
+
+A **dedicated** ``/resolve`` **endpoint** of the HTTP API is also available to
+explicitly request persistent identifier resolution; see:
+:http:get:`/api/1/resolve/(swh_id)/`.
+
+Examples:
+
+* `<https://archive.softwareheritage.org/swh:1:cnt:94a9ed024d3859793618152ea559a168bbcbb5e2>`_
+* `<https://archive.softwareheritage.org/swh:1:dir:d198bc9d7a6bcf6db04f476d29314f157507d505>`_
+* `<https://archive.softwareheritage.org/api/1/resolve/swh:1:rev:309cf2674ee7a0749978cf8265ab91a60aea0f7d>`_
+* `<https://archive.softwareheritage.org/api/1/resolve/swh:1:rel:22ece559cc7cc2364edc5e5593d63ae8bd229f9f>`_
+* `<https://archive.softwareheritage.org/api/1/resolve/swh:1:snp:c7c108084bc0bf3d81436bf980b46e98bd338453>`_
+
+
+External resolvers
+------------------
+
+The following **independent resolvers** support resolution of Software
+Heritage persistent identifiers:
+
+* `Identifiers.org <https://identifiers.org>`_; see:
+ `<http://identifiers.org/swh/>`_ (registry identifier `MIR:00000655
+ <https://www.ebi.ac.uk/miriam/main/datatypes/MIR:00000655>`_).
+
+* `Name-to-Thing (N2T) <https://n2t.net/>`_
+
+Examples:
+
+* `<https://identifiers.org/swh:1:cnt:94a9ed024d3859793618152ea559a168bbcbb5e2>`_
+* `<https://identifiers.org/swh:1:dir:d198bc9d7a6bcf6db04f476d29314f157507d505>`_
+* `<https://identifiers.org/swh:1:rev:309cf2674ee7a0749978cf8265ab91a60aea0f7d>`_
+* `<https://n2t.net/swh:1:rel:22ece559cc7cc2364edc5e5593d63ae8bd229f9f>`_
+* `<https://n2t.net/swh:1:snp:c7c108084bc0bf3d81436bf980b46e98bd338453>`_
+
+Note that resolution via Identifiers.org does not support contextual
+information, due to `syntactic incompatibilities
+<http://identifiers.org/documentation#custom_requests>`_.
diff --git a/pytest.ini b/pytest.ini
new file mode 100644
index 0000000000000000000000000000000000000000..e86f7f4e0aa54f919816a112eec1963b5a780412
--- /dev/null
+++ b/pytest.ini
@@ -0,0 +1,3 @@
+[pytest]
+addopts = --doctest-modules
+norecursedirs = docs
diff --git a/requirements-test.txt b/requirements-test.txt
new file mode 100644
index 0000000000000000000000000000000000000000..e079f8a6038dd2dc8512967540f96ee0de172067
--- /dev/null
+++ b/requirements-test.txt
@@ -0,0 +1 @@
+pytest
diff --git a/setup.py b/setup.py
old mode 100644
new mode 100755
index 7e4a47ceb5549af703f343344c5e3161177d948b..c28e4bf0ad4ef5a6931ae5e986ab0b66b64569b0
--- a/setup.py
+++ b/setup.py
@@ -1,21 +1,42 @@
-import hashlib
+#!/usr/bin/env python3
+# Copyright (C) 2015-2018 The Software Heritage developers
+# See the AUTHORS file at the top-level directory of this distribution
+# License: GNU General Public License version 3, or any later version
+# See top-level LICENSE file for more information
from setuptools import setup, find_packages
+import hashlib
+
+from os import path
+from io import open
+
+here = path.abspath(path.dirname(__file__))
+# Get the long description from the README file
+with open(path.join(here, 'README.md'), encoding='utf-8') as f:
+ long_description = f.read()
+
+
+def parse_requirements(name=None):
+ if name:
+ reqf = 'requirements-%s.txt' % name
+ else:
+ reqf = 'requirements.txt'
-def parse_requirements():
requirements = []
- for reqf in ('requirements.txt', 'requirements-swh.txt'):
- with open(reqf) as f:
- for line in f.readlines():
- line = line.strip()
- if not line or line.startswith('#'):
- continue
- requirements.append(line)
+ if not path.exists(reqf):
+ return requirements
+
+ with open(reqf) as f:
+ for line in f.readlines():
+ line = line.strip()
+ if not line or line.startswith('#'):
+ continue
+ requirements.append(line)
return requirements
-extra_requirements = []
+blake2_requirements = []
pyblake2_hash_sets = [
# Built-in implementation in Python 3.6+
@@ -32,22 +53,37 @@ for pyblake2_hashes in pyblake2_hash_sets:
else:
# None of the possible sets of blake2 hashes are available.
# use pyblake2 instead
- extra_requirements.append('pyblake2')
+ blake2_requirements.append('pyblake2')
setup(
name='swh.model',
description='Software Heritage data model',
+ long_description=long_description,
+ long_description_content_type='text/markdown',
author='Software Heritage developers',
author_email='swh-devel@inria.fr',
url='https://forge.softwareheritage.org/diffusion/DMOD/',
- packages=find_packages(), # packages's modules
- scripts=[], # scripts to package
- install_requires=parse_requirements() + extra_requirements,
+ packages=find_packages(),
+ setup_requires=['vcversioner'],
+ install_requires=(parse_requirements() + parse_requirements('swh') +
+ blake2_requirements),
+ extras_require={'testing': parse_requirements('test')},
+ vcversioner={},
+ include_package_data=True,
entry_points='''
[console_scripts]
swh-identify=swh.model.cli:identify
''',
- setup_requires=['vcversioner'],
- vcversioner={},
- include_package_data=True,
+ classifiers=[
+ "Programming Language :: Python :: 3",
+ "Intended Audience :: Developers",
+ "License :: OSI Approved :: GNU General Public License v3 (GPLv3)",
+ "Operating System :: OS Independent",
+ "Development Status :: 5 - Production/Stable",
+ ],
+ project_urls={
+ 'Bug Reports': 'https://forge.softwareheritage.org/maniphest',
+ 'Funding': 'https://www.softwareheritage.org/donate',
+ 'Source': 'https://forge.softwareheritage.org/source/swh-model',
+ },
)
diff --git a/swh.model.egg-info/PKG-INFO b/swh.model.egg-info/PKG-INFO
index 653b8da334326f55a86ea9c15ce5b7d3508e2f22..b07e4b866fcb26f1f4f87d4f7060e879115afe6b 100644
--- a/swh.model.egg-info/PKG-INFO
+++ b/swh.model.egg-info/PKG-INFO
@@ -1,10 +1,38 @@
-Metadata-Version: 1.0
+Metadata-Version: 2.1
Name: swh.model
-Version: 0.0.27
+Version: 0.0.28
Summary: Software Heritage data model
Home-page: https://forge.softwareheritage.org/diffusion/DMOD/
Author: Software Heritage developers
Author-email: swh-devel@inria.fr
License: UNKNOWN
-Description: UNKNOWN
+Project-URL: Bug Reports, https://forge.softwareheritage.org/maniphest
+Project-URL: Funding, https://www.softwareheritage.org/donate
+Project-URL: Source, https://forge.softwareheritage.org/source/swh-model
+Description: swh-model
+ =========
+
+ Implementation of the Data model of the Software Heritage project, used to
+ archive source code artifacts.
+
+ This module defines the notion of Persistent Identifier (PID) and provides
+ tools to compute them:
+
+ ```sh
+ $ swh-identify fork.c kmod.c sched/deadline.c
+ swh:1:cnt:2e391c754ae730bd2d8520c2ab497c403220c6e3 fork.c
+ swh:1:cnt:0277d1216f80ae1adeed84a686ed34c9b2931fc2 kmod.c
+ swh:1:cnt:57b939c81bce5d06fa587df8915f05affbe22b82 sched/deadline.c
+
+ $ swh-identify --no-filename /usr/src/linux/kernel/
+ swh:1:dir:f9f858a48d663b3809c9e2f336412717496202ab
+ ```
+
Platform: UNKNOWN
+Classifier: Programming Language :: Python :: 3
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3)
+Classifier: Operating System :: OS Independent
+Classifier: Development Status :: 5 - Production/Stable
+Description-Content-Type: text/markdown
+Provides-Extra: testing
diff --git a/swh.model.egg-info/SOURCES.txt b/swh.model.egg-info/SOURCES.txt
index f6a2f94098b482c8b10045483d3c375f3165ad33..81e3d7dfcf82c118bb475c93c2fbef1a95c992d4 100644
--- a/swh.model.egg-info/SOURCES.txt
+++ b/swh.model.egg-info/SOURCES.txt
@@ -4,11 +4,16 @@ LICENSE
MANIFEST.in
Makefile
Makefile.local
+README.md
+pytest.ini
requirements-swh.txt
+requirements-test.txt
requirements.txt
setup.py
+tox.ini
version.txt
bin/git-revhash
+bin/swh-hashtree
bin/swh-revhash
debian/changelog
debian/compat
@@ -18,6 +23,7 @@ debian/rules
debian/source/format
docs/.gitignore
docs/Makefile
+docs/Makefile.local
docs/conf.py
docs/data-model.rst
docs/index.rst
@@ -56,6 +62,7 @@ swh/model/tests/test_identifiers.py
swh/model/tests/test_merkle.py
swh/model/tests/test_toposort.py
swh/model/tests/test_validators.py
+swh/model/tests/data/dir-folders/sample-folder.tgz
swh/model/tests/fields/__init__.py
swh/model/tests/fields/test_compound.py
swh/model/tests/fields/test_hashes.py
diff --git a/swh.model.egg-info/requires.txt b/swh.model.egg-info/requires.txt
index dbcd3082d3efe925da6522cc818c882fb36e74f8..091cefe89235e78d7ba4a9f88cb34a58f2abbf52 100644
--- a/swh.model.egg-info/requires.txt
+++ b/swh.model.egg-info/requires.txt
@@ -1,2 +1,5 @@
Click
vcversioner
+
+[testing]
+pytest
diff --git a/swh/model/from_disk.py b/swh/model/from_disk.py
index f9f37290cbf91aaf177b366496d84cda4ead46f0..bfd7c7cd026f271be37aecca9d2435b683304403 100644
--- a/swh/model/from_disk.py
+++ b/swh/model/from_disk.py
@@ -1,4 +1,4 @@
-# Copyright (C) 2017 The Software Heritage developers
+# Copyright (C) 2017-2018 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
@@ -7,7 +7,7 @@ import enum
import os
import stat
-from . import hashutil
+from .hashutil import MultiHash, HASH_BLOCK_SIZE
from .merkle import MerkleLeaf, MerkleNode
from .identifiers import (
directory_identifier,
@@ -77,7 +77,7 @@ class Content(MerkleLeaf):
mode (int): a file mode (passed to :func:`mode_to_perms`)
data (bytes): raw contents of the file
"""
- ret = hashutil.hash_data(data)
+ ret = MultiHash.from_data(data).digest()
ret['length'] = len(data)
ret['perms'] = mode_to_perms(mode)
ret['data'] = data
@@ -91,8 +91,8 @@ class Content(MerkleLeaf):
@classmethod
def from_file(cls, *, path, data=False, save_path=False):
- """Compute the Software Heritage content entry corresponding to an on-disk
- file.
+ """Compute the Software Heritage content entry corresponding to an
+ on-disk file.
The returned dictionary contains keys useful for both:
- loading the content in the archive (hashes, `length`)
@@ -103,6 +103,7 @@ class Content(MerkleLeaf):
content entry
data (bool): add the file data to the entry
save_path (bool): add the file path to the entry
+
"""
file_stat = os.lstat(path)
mode = file_stat.st_mode
@@ -117,17 +118,19 @@ class Content(MerkleLeaf):
length = file_stat.st_size
if not data:
- ret = hashutil.hash_path(path)
+ ret = MultiHash.from_path(path).digest()
else:
+ h = MultiHash(length=length)
chunks = []
-
- def append_chunk(x, chunks=chunks):
- chunks.append(x)
-
with open(path, 'rb') as fobj:
- ret = hashutil.hash_file(fobj, length=length,
- chunk_cb=append_chunk)
-
+ while True:
+ chunk = fobj.read(HASH_BLOCK_SIZE)
+ if not chunk:
+ break
+ h.update(chunk)
+ chunks.append(chunk)
+
+ ret = h.digest()
ret['data'] = b''.join(chunks)
if save_path:
diff --git a/swh/model/hashutil.py b/swh/model/hashutil.py
index d8249bc70b5d5b81286a7d945a3fb07d23ea969c..e58f6870fc121ddd674253a918c8849de822589f 100644
--- a/swh/model/hashutil.py
+++ b/swh/model/hashutil.py
@@ -30,25 +30,26 @@ Basic usage examples:
- To compute length, integrate the length to the set of algorithms to
compute, for example:
- h = MultiHash(hash_names=set({'length'}).union(DEFAULT_ALGORITHMS))
- with open(filepath, 'rb') as f:
- h.update(f.read(HASH_BLOCK_SIZE))
- hashes = h.digest() # returns a dict of {hash_algo_name: hash_in_bytes}
+ .. code-block:: python
- for chunk in
- # then use h as you would
+ h = MultiHash(hash_names=set({'length'}).union(DEFAULT_ALGORITHMS))
+ with open(filepath, 'rb') as f:
+ h.update(f.read(HASH_BLOCK_SIZE))
+ hashes = h.digest() # returns a dict of {hash_algo_name: hash_in_bytes}
- Write alongside computing hashing algorithms (from a stream), example:
- h = MultiHash(length=length)
- with open(filepath, 'wb') as f:
- for chunk in r.iter_content(): # r a stream of sort
- h.update(chunk)
- f.write(chunk)
- hashes = h.hexdigest() # returns a dict of {hash_algo_name: hash_in_hex}
+ .. code-block:: python
+
+ h = MultiHash(length=length)
+ with open(filepath, 'wb') as f:
+ for chunk in r.iter_content(): # r a stream of sort
+ h.update(chunk)
+ 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)
+ 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:
@@ -117,28 +118,25 @@ class MultiHash:
ret.track_length = track_length
@classmethod
- def from_file(cls, file, hash_names=DEFAULT_ALGORITHMS, length=None):
+ def from_file(cls, fobj, hash_names=DEFAULT_ALGORITHMS, length=None):
ret = cls(length=length, hash_names=hash_names)
- for chunk in file:
+ while True:
+ chunk = fobj.read(HASH_BLOCK_SIZE)
+ if not chunk:
+ break
ret.update(chunk)
return ret
@classmethod
- def from_path(cls, path, hash_names=DEFAULT_ALGORITHMS, length=None,
- track_length=True):
- if not length:
- length = os.path.getsize(path)
+ def from_path(cls, path, hash_names=DEFAULT_ALGORITHMS):
+ length = os.path.getsize(path)
with open(path, 'rb') as f:
ret = cls.from_file(f, hash_names=hash_names, length=length)
- # For compatibility reason with `hash_path`
- if track_length:
- ret.state['length'] = length
return ret
@classmethod
- def from_data(cls, data, hash_names=DEFAULT_ALGORITHMS, length=None):
- if not length:
- length = len(data)
+ def from_data(cls, data, hash_names=DEFAULT_ALGORITHMS):
+ length = len(data)
fobj = BytesIO(data)
return cls.from_file(fobj, hash_names=hash_names, length=length)
diff --git a/swh/model/identifiers.py b/swh/model/identifiers.py
index e7608e978af8a002ea2afc0d106a4c69da9c1189..083efd4504c7dbad38a26d4e9aaa50e7369ba650 100644
--- a/swh/model/identifiers.py
+++ b/swh/model/identifiers.py
@@ -11,8 +11,7 @@ from functools import lru_cache
from .exceptions import ValidationError
from .fields.hashes import validate_sha1
-from .hashutil import hash_data, hash_git_data, DEFAULT_ALGORITHMS
-from .hashutil import hash_to_hex
+from .hashutil import hash_git_data, hash_to_hex, MultiHash
SNAPSHOT = 'snapshot'
@@ -104,7 +103,7 @@ def content_identifier(content):
"""
- return hash_data(content['data'], DEFAULT_ALGORITHMS)
+ return MultiHash.from_data(content['data']).digest()
def _sort_key(entry):
diff --git a/swh/model/tests/data/dir-folders/sample-folder.tgz b/swh/model/tests/data/dir-folders/sample-folder.tgz
new file mode 100644
index 0000000000000000000000000000000000000000..cc848944a0d3e71d287027347e25467e61b07428
Binary files /dev/null and b/swh/model/tests/data/dir-folders/sample-folder.tgz differ
diff --git a/swh/model/tests/fields/test_compound.py b/swh/model/tests/fields/test_compound.py
index b6e13b6c33a7f975102d2faea9635e12f0e07ca8..dffbb043139221d7ed87197f368a4a2c5349f475 100644
--- a/swh/model/tests/fields/test_compound.py
+++ b/swh/model/tests/fields/test_compound.py
@@ -6,9 +6,7 @@
import datetime
import unittest
-from nose.tools import istest
-
-from swh.model.exceptions import ValidationError, NON_FIELD_ERRORS
+from swh.model.exceptions import NON_FIELD_ERRORS, ValidationError
from swh.model.fields import compound, simple
@@ -63,8 +61,7 @@ class ValidateCompound(unittest.TestCase):
self.present_keys = set(self.test_value)
self.missing_keys = {'missingkey1', 'missingkey2'}
- @istest
- def validate_any_key(self):
+ def test_validate_any_key(self):
self.assertTrue(
compound.validate_any_key(self.test_value, self.present_keys))
@@ -72,8 +69,7 @@ class ValidateCompound(unittest.TestCase):
compound.validate_any_key(self.test_value,
self.present_keys | self.missing_keys))
- @istest
- def validate_any_key_missing(self):
+ def test_validate_any_key_missing(self):
with self.assertRaises(ValidationError) as cm:
compound.validate_any_key(self.test_value, self.missing_keys)
@@ -83,13 +79,11 @@ class ValidateCompound(unittest.TestCase):
self.assertEqual(exc.params['missing_fields'],
', '.join(sorted(self.missing_keys)))
- @istest
- def validate_all_keys(self):
+ def test_validate_all_keys(self):
self.assertTrue(
compound.validate_all_keys(self.test_value, self.present_keys))
- @istest
- def validate_all_keys_missing(self):
+ def test_validate_all_keys_missing(self):
with self.assertRaises(ValidationError) as cm:
compound.validate_all_keys(self.test_value, self.missing_keys)
@@ -109,14 +103,12 @@ class ValidateCompound(unittest.TestCase):
self.assertEqual(exc.params['missing_fields'],
', '.join(sorted(self.missing_keys)))
- @istest
- def validate_against_schema(self):
+ def test_validate_against_schema(self):
self.assertTrue(
compound.validate_against_schema(self.test_model, self.test_schema,
self.test_value))
- @istest
- def validate_against_schema_wrong_type(self):
+ def test_validate_against_schema_wrong_type(self):
with self.assertRaises(ValidationError) as cm:
compound.validate_against_schema(self.test_model, self.test_schema,
self.test_value_wrong_type)
@@ -128,8 +120,7 @@ class ValidateCompound(unittest.TestCase):
self.assertEqual(exc.params['type'],
self.test_value_wrong_type.__class__.__name__)
- @istest
- def validate_against_schema_mandatory_keys(self):
+ def test_validate_against_schema_mandatory_keys(self):
with self.assertRaises(ValidationError) as cm:
compound.validate_against_schema(self.test_model, self.test_schema,
self.test_value_missing)
@@ -150,8 +141,7 @@ class ValidateCompound(unittest.TestCase):
self.assertEqual(nested.code, 'model-field-mandatory')
self.assertEqual(nested.params['field'], key)
- @istest
- def validate_against_schema_whole_schema_shortcut_previous_error(self):
+ def test_validate_whole_schema_shortcut_previous_error(self):
with self.assertRaises(ValidationError) as cm:
compound.validate_against_schema(
self.test_model,
@@ -163,8 +153,7 @@ class ValidateCompound(unittest.TestCase):
self.assertIsInstance(str(exc), str)
self.assertNotIn(NON_FIELD_ERRORS, exc.error_dict)
- @istest
- def validate_against_schema_whole_schema(self):
+ def test_validate_whole_schema(self):
with self.assertRaises(ValidationError) as cm:
compound.validate_against_schema(
self.test_model,
@@ -179,20 +168,19 @@ class ValidateCompound(unittest.TestCase):
exc = cm.exception
self.assertIsInstance(str(exc), str)
- self.assertEquals(set(exc.error_dict.keys()), {NON_FIELD_ERRORS})
+ self.assertEqual(set(exc.error_dict.keys()), {NON_FIELD_ERRORS})
non_field_errors = exc.error_dict[NON_FIELD_ERRORS]
self.assertIsInstance(non_field_errors, list)
- self.assertEquals(len(non_field_errors), 1)
+ self.assertEqual(len(non_field_errors), 1)
nested = non_field_errors[0]
self.assertIsInstance(nested, ValidationError)
- self.assertEquals(nested.code, 'model-validation-failed')
- self.assertEquals(nested.params['model'], self.test_model)
- self.assertEquals(nested.params['validator'], 'validate_never')
+ self.assertEqual(nested.code, 'model-validation-failed')
+ self.assertEqual(nested.params['model'], self.test_model)
+ self.assertEqual(nested.params['validator'], 'validate_never')
- @istest
- def validate_against_schema_field_error(self):
+ def test_validate_against_schema_field_error(self):
with self.assertRaises(ValidationError) as cm:
compound.validate_against_schema(self.test_model, self.test_schema,
self.test_value_str_error)
@@ -204,18 +192,17 @@ class ValidateCompound(unittest.TestCase):
exc = cm.exception
self.assertIsInstance(str(exc), str)
- self.assertEquals(set(exc.error_dict.keys()), {'str'})
+ self.assertEqual(set(exc.error_dict.keys()), {'str'})
str_errors = exc.error_dict['str']
self.assertIsInstance(str_errors, list)
- self.assertEquals(len(str_errors), 1)
+ self.assertEqual(len(str_errors), 1)
nested = str_errors[0]
self.assertIsInstance(nested, ValidationError)
- self.assertEquals(nested.code, 'unexpected-type')
+ self.assertEqual(nested.code, 'unexpected-type')
- @istest
- def validate_against_schema_field_failed(self):
+ def test_validate_against_schema_field_failed(self):
with self.assertRaises(ValidationError) as cm:
compound.validate_against_schema(self.test_model,
self.test_schema_field_failed,
@@ -228,14 +215,14 @@ class ValidateCompound(unittest.TestCase):
exc = cm.exception
self.assertIsInstance(str(exc), str)
- self.assertEquals(set(exc.error_dict.keys()), {'int'})
+ self.assertEqual(set(exc.error_dict.keys()), {'int'})
int_errors = exc.error_dict['int']
self.assertIsInstance(int_errors, list)
- self.assertEquals(len(int_errors), 1)
+ self.assertEqual(len(int_errors), 1)
nested = int_errors[0]
self.assertIsInstance(nested, ValidationError)
- self.assertEquals(nested.code, 'field-validation-failed')
- self.assertEquals(nested.params['validator'], 'validate_never')
- self.assertEquals(nested.params['field'], 'int')
+ self.assertEqual(nested.code, 'field-validation-failed')
+ self.assertEqual(nested.params['validator'], 'validate_never')
+ self.assertEqual(nested.params['field'], 'int')
diff --git a/swh/model/tests/fields/test_hashes.py b/swh/model/tests/fields/test_hashes.py
index 0ef303f034bceb0611c139a6b9191f4fd6dfb0d8..7ce0b78be04485a3f3cd11390eddcac2e112da5f 100644
--- a/swh/model/tests/fields/test_hashes.py
+++ b/swh/model/tests/fields/test_hashes.py
@@ -5,8 +5,6 @@
import unittest
-from nose.tools import istest
-
from swh.model.exceptions import ValidationError
from swh.model.fields import hashes
@@ -32,18 +30,15 @@ class ValidateHashes(unittest.TestCase):
self.bad_hash = object()
- @istest
- def valid_bytes_hash(self):
+ def test_valid_bytes_hash(self):
for hash_type, value in self.valid_byte_hashes.items():
self.assertTrue(hashes.validate_hash(value, hash_type))
- @istest
- def valid_str_hash(self):
+ def test_valid_str_hash(self):
for hash_type, value in self.valid_str_hashes.items():
self.assertTrue(hashes.validate_hash(value, hash_type))
- @istest
- def invalid_hash_type(self):
+ def test_invalid_hash_type(self):
hash_type = 'unknown_hash_type'
with self.assertRaises(ValidationError) as cm:
hashes.validate_hash(self.valid_str_hashes['sha1'], hash_type)
@@ -56,8 +51,7 @@ class ValidateHashes(unittest.TestCase):
self.assertIn('Unexpected hash type', str(exc))
self.assertIn(hash_type, str(exc))
- @istest
- def invalid_bytes_len(self):
+ def test_invalid_bytes_len(self):
for hash_type, value in self.valid_byte_hashes.items():
value = value + b'\x00\x01'
with self.assertRaises(ValidationError) as cm:
@@ -72,8 +66,7 @@ class ValidateHashes(unittest.TestCase):
self.assertIn('Unexpected length', str(exc))
self.assertIn(str(len(value)), str(exc))
- @istest
- def invalid_str_len(self):
+ def test_invalid_str_len(self):
for hash_type, value in self.valid_str_hashes.items():
value = value + '0001'
with self.assertRaises(ValidationError) as cm:
@@ -88,8 +81,7 @@ class ValidateHashes(unittest.TestCase):
self.assertIn('Unexpected length', str(exc))
self.assertIn(str(len(value)), str(exc))
- @istest
- def invalid_str_contents(self):
+ def test_invalid_str_contents(self):
for hash_type, value in self.valid_str_hashes.items():
value = '\xa2' + value[1:-1] + '\xc3'
with self.assertRaises(ValidationError) as cm:
@@ -105,8 +97,7 @@ class ValidateHashes(unittest.TestCase):
self.assertIn('\xc3', str(exc))
self.assertIn('\xa2', str(exc))
- @istest
- def invalid_value_type(self):
+ def test_invalid_value_type(self):
with self.assertRaises(ValidationError) as cm:
hashes.validate_hash(self.bad_hash, 'sha1')
@@ -118,8 +109,7 @@ class ValidateHashes(unittest.TestCase):
self.assertIn('Unexpected type', str(exc))
self.assertIn(self.bad_hash.__class__.__name__, str(exc))
- @istest
- def validate_sha1(self):
+ def test_validate_sha1(self):
self.assertTrue(hashes.validate_sha1(self.valid_byte_hashes['sha1']))
self.assertTrue(hashes.validate_sha1(self.valid_str_hashes['sha1']))
@@ -131,8 +121,7 @@ class ValidateHashes(unittest.TestCase):
self.assertEqual(exc.code, 'unexpected-hash-value-type')
self.assertEqual(exc.params['type'], self.bad_hash.__class__.__name__)
- @istest
- def validate_sha1_git(self):
+ def test_validate_sha1_git(self):
self.assertTrue(
hashes.validate_sha1_git(self.valid_byte_hashes['sha1_git']))
self.assertTrue(
@@ -146,8 +135,7 @@ class ValidateHashes(unittest.TestCase):
self.assertEqual(exc.code, 'unexpected-hash-value-type')
self.assertEqual(exc.params['type'], self.bad_hash.__class__.__name__)
- @istest
- def validate_sha256(self):
+ def test_validate_sha256(self):
self.assertTrue(
hashes.validate_sha256(self.valid_byte_hashes['sha256']))
self.assertTrue(
diff --git a/swh/model/tests/fields/test_simple.py b/swh/model/tests/fields/test_simple.py
index 6fa2918d8f76954b7b69efb1eadf734503e5befd..ab5e262eceba4eb08fe03f9df667534cc16379f2 100644
--- a/swh/model/tests/fields/test_simple.py
+++ b/swh/model/tests/fields/test_simple.py
@@ -6,8 +6,6 @@
import datetime
import unittest
-from nose.tools import istest
-
from swh.model.exceptions import ValidationError
from swh.model.fields import simple
@@ -29,12 +27,10 @@ class ValidateSimple(unittest.TestCase):
tzinfo=datetime.timezone.utc)
self.invalid_datetime_notz = datetime.datetime(1999, 1, 1, 12, 0, 0)
- @istest
- def validate_int(self):
+ def test_validate_int(self):
self.assertTrue(simple.validate_int(self.valid_int))
- @istest
- def validate_int_invalid_type(self):
+ def test_validate_int_invalid_type(self):
with self.assertRaises(ValidationError) as cm:
simple.validate_int(self.valid_str)
@@ -44,12 +40,10 @@ class ValidateSimple(unittest.TestCase):
self.assertEqual(exc.params['expected_type'], 'Integral')
self.assertEqual(exc.params['type'], 'str')
- @istest
- def validate_str(self):
+ def test_validate_str(self):
self.assertTrue(simple.validate_str(self.valid_str))
- @istest
- def validate_str_invalid_type(self):
+ def test_validate_str_invalid_type(self):
with self.assertRaises(ValidationError) as cm:
simple.validate_str(self.valid_int)
@@ -68,12 +62,10 @@ class ValidateSimple(unittest.TestCase):
self.assertEqual(exc.params['expected_type'], 'str')
self.assertEqual(exc.params['type'], 'bytes')
- @istest
- def validate_bytes(self):
+ def test_validate_bytes(self):
self.assertTrue(simple.validate_bytes(self.valid_bytes))
- @istest
- def validate_bytes_invalid_type(self):
+ def test_validate_bytes_invalid_type(self):
with self.assertRaises(ValidationError) as cm:
simple.validate_bytes(self.valid_int)
@@ -92,14 +84,12 @@ class ValidateSimple(unittest.TestCase):
self.assertEqual(exc.params['expected_type'], 'bytes')
self.assertEqual(exc.params['type'], 'str')
- @istest
- def validate_datetime(self):
+ def test_validate_datetime(self):
self.assertTrue(simple.validate_datetime(self.valid_datetime))
self.assertTrue(simple.validate_datetime(self.valid_int))
self.assertTrue(simple.validate_datetime(self.valid_real))
- @istest
- def validate_datetime_invalid_type(self):
+ def test_validate_datetime_invalid_type(self):
with self.assertRaises(ValidationError) as cm:
simple.validate_datetime(self.valid_str)
@@ -109,8 +99,7 @@ class ValidateSimple(unittest.TestCase):
self.assertEqual(exc.params['expected_type'], 'one of datetime, Real')
self.assertEqual(exc.params['type'], 'str')
- @istest
- def validate_datetime_invalide_tz(self):
+ def test_validate_datetime_invalide_tz(self):
with self.assertRaises(ValidationError) as cm:
simple.validate_datetime(self.invalid_datetime_notz)
@@ -118,13 +107,11 @@ class ValidateSimple(unittest.TestCase):
self.assertIsInstance(str(exc), str)
self.assertEqual(exc.code, 'datetime-without-tzinfo')
- @istest
- def validate_enum(self):
+ def test_validate_enum(self):
for value in self.enum_values:
self.assertTrue(simple.validate_enum(value, self.enum_values))
- @istest
- def validate_enum_invalid_value(self):
+ def test_validate_enum_invalid_value(self):
with self.assertRaises(ValidationError) as cm:
simple.validate_enum(self.invalid_enum_value, self.enum_values)
diff --git a/swh/model/tests/test_cli.py b/swh/model/tests/test_cli.py
index 9e31a4a397402521872eed8f0d0465160e5f6191..e4232fe2c4b4a70aeac2fb8991ab883e6b83b98a 100644
--- a/swh/model/tests/test_cli.py
+++ b/swh/model/tests/test_cli.py
@@ -8,21 +8,21 @@ import tempfile
import unittest
from click.testing import CliRunner
-from nose.plugins.attrib import attr
+import pytest
from swh.model import cli
-from swh.model.tests.test_from_disk import DataMixin
from swh.model.hashutil import hash_to_hex
+from swh.model.tests.test_from_disk import DataMixin
-@attr('fs')
+@pytest.mark.fs
class TestIdentify(DataMixin, unittest.TestCase):
def setUp(self):
super().setUp()
self.runner = CliRunner()
- def assertPidOK(self, result, pid):
+ def assertPidOK(self, result, pid): # noqa: N802
self.assertEqual(result.exit_code, 0)
self.assertEqual(result.output.split()[0], pid)
diff --git a/swh/model/tests/test_from_disk.py b/swh/model/tests/test_from_disk.py
index 8e568ec25d21985c00e8e5243992ea0bb753aa19..30f543d639f570be72c24bb55f7bb604cba5f2cd 100644
--- a/swh/model/tests/test_from_disk.py
+++ b/swh/model/tests/test_from_disk.py
@@ -8,12 +8,14 @@ import tarfile
import tempfile
import unittest
-from nose.plugins.attrib import attr
+import pytest
from swh.model import from_disk
-from swh.model.from_disk import Content, Directory, DentryPerms
+from swh.model.from_disk import Content, DentryPerms, Directory
from swh.model.hashutil import DEFAULT_ALGORITHMS, hash_to_bytes, hash_to_hex
+TEST_DATA = os.path.join(os.path.dirname(__file__), 'data')
+
class ModeToPerms(unittest.TestCase):
def setUp(self):
@@ -466,11 +468,7 @@ class DataMixin:
fn(path)
def make_from_tarball(self, directory):
- tarball = os.path.join(os.path.dirname(__file__),
- '../../../..',
- 'swh-storage-testdata',
- 'dir-folders',
- 'sample-folder.tgz')
+ tarball = os.path.join(TEST_DATA, 'dir-folders', 'sample-folder.tgz')
with tarfile.open(tarball, 'r:gz') as f:
f.extractall(os.fsdecode(directory))
@@ -687,7 +685,7 @@ class DirectoryToObjects(DataMixin, unittest.TestCase):
+ 1)
-@attr('fs')
+@pytest.mark.fs
class TarballTest(DataMixin, unittest.TestCase):
def setUp(self):
super().setUp()
diff --git a/swh/model/tests/test_hashutil.py b/swh/model/tests/test_hashutil.py
index 92b3684afe807774a9b8ed315bf1e39095b5e225..0e41068900686474db83d82ddfc7b9e54c60f36d 100644
--- a/swh/model/tests/test_hashutil.py
+++ b/swh/model/tests/test_hashutil.py
@@ -8,8 +8,6 @@ import io
import os
import tempfile
import unittest
-
-from nose.tools import istest
from unittest.mock import patch
from swh.model import hashutil
@@ -55,14 +53,12 @@ class BaseHashutil(unittest.TestCase):
class MultiHashTest(BaseHashutil):
- @istest
- def multi_hash_data(self):
+ def test_multi_hash_data(self):
checksums = MultiHash.from_data(self.data).digest()
self.assertEqual(checksums, self.checksums)
self.assertFalse('length' in checksums)
- @istest
- def multi_hash_data_with_length(self):
+ def test_multi_hash_data_with_length(self):
expected_checksums = self.checksums.copy()
expected_checksums['length'] = len(self.data)
@@ -72,64 +68,55 @@ class MultiHashTest(BaseHashutil):
self.assertEqual(checksums, expected_checksums)
self.assertTrue('length' in checksums)
- @istest
- def multi_hash_data_unknown_hash(self):
+ def test_multi_hash_data_unknown_hash(self):
with self.assertRaises(ValueError) as cm:
MultiHash.from_data(self.data, ['unknown-hash'])
self.assertIn('Unexpected hashing algorithm', cm.exception.args[0])
self.assertIn('unknown-hash', cm.exception.args[0])
- @istest
- def multi_hash_file(self):
+ def test_multi_hash_file(self):
fobj = io.BytesIO(self.data)
checksums = MultiHash.from_file(fobj, length=len(self.data)).digest()
self.assertEqual(checksums, self.checksums)
- @istest
- def multi_hash_file_hexdigest(self):
+ def test_multi_hash_file_hexdigest(self):
fobj = io.BytesIO(self.data)
length = len(self.data)
checksums = MultiHash.from_file(fobj, length=length).hexdigest()
self.assertEqual(checksums, self.hex_checksums)
- @istest
- def multi_hash_file_bytehexdigest(self):
+ def test_multi_hash_file_bytehexdigest(self):
fobj = io.BytesIO(self.data)
length = len(self.data)
checksums = MultiHash.from_file(fobj, length=length).bytehexdigest()
self.assertEqual(checksums, self.bytehex_checksums)
- @istest
- def multi_hash_file_missing_length(self):
+ def test_multi_hash_file_missing_length(self):
fobj = io.BytesIO(self.data)
with self.assertRaises(ValueError) as cm:
MultiHash.from_file(fobj, hash_names=['sha1_git'])
self.assertIn('Missing length', cm.exception.args[0])
- @istest
- def multi_hash_path(self):
+ def test_multi_hash_path(self):
with tempfile.NamedTemporaryFile(delete=False) as f:
f.write(self.data)
hashes = MultiHash.from_path(f.name).digest()
os.remove(f.name)
- self.checksums['length'] = len(self.data)
- self.assertEquals(self.checksums, hashes)
+ self.assertEqual(self.checksums, hashes)
class Hashutil(BaseHashutil):
- @istest
- def hash_data(self):
+ def test_hash_data(self):
checksums = hashutil.hash_data(self.data)
self.assertEqual(checksums, self.checksums)
self.assertFalse('length' in checksums)
- @istest
- def hash_data_with_length(self):
+ def test_hash_data_with_length(self):
expected_checksums = self.checksums.copy()
expected_checksums['length'] = len(self.data)
@@ -139,16 +126,14 @@ class Hashutil(BaseHashutil):
self.assertEqual(checksums, expected_checksums)
self.assertTrue('length' in checksums)
- @istest
- def hash_data_unknown_hash(self):
+ 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])
- @istest
- def hash_git_data(self):
+ def test_hash_git_data(self):
checksums = {
git_type: hashutil.hash_git_data(self.data, git_type)
for git_type in self.git_checksums
@@ -156,23 +141,20 @@ class Hashutil(BaseHashutil):
self.assertEqual(checksums, self.git_checksums)
- @istest
- def hash_git_data_unknown_git_type(self):
+ def test_hash_git_data_unknown_git_type(self):
with self.assertRaises(ValueError) as cm:
hashutil.hash_git_data(self.data, 'unknown-git-type')
self.assertIn('Unexpected git object type', cm.exception.args[0])
self.assertIn('unknown-git-type', cm.exception.args[0])
- @istest
- def hash_file(self):
+ def test_hash_file(self):
fobj = io.BytesIO(self.data)
checksums = hashutil.hash_file(fobj, length=len(self.data))
self.assertEqual(checksums, self.checksums)
- @istest
- def hash_file_missing_length(self):
+ def test_hash_file_missing_length(self):
fobj = io.BytesIO(self.data)
with self.assertRaises(ValueError) as cm:
@@ -180,8 +162,7 @@ class Hashutil(BaseHashutil):
self.assertIn('Missing length', cm.exception.args[0])
- @istest
- def hash_path(self):
+ def test_hash_path(self):
with tempfile.NamedTemporaryFile(delete=False) as f:
f.write(self.data)
@@ -189,50 +170,44 @@ class Hashutil(BaseHashutil):
os.remove(f.name)
self.checksums['length'] = len(self.data)
- self.assertEquals(self.checksums, hashes)
+ self.assertEqual(self.checksums, hashes)
- @istest
- def hash_to_hex(self):
+ def test_hash_to_hex(self):
for type in self.checksums:
hex = self.hex_checksums[type]
hash = self.checksums[type]
- self.assertEquals(hashutil.hash_to_hex(hex), hex)
- self.assertEquals(hashutil.hash_to_hex(hash), hex)
+ self.assertEqual(hashutil.hash_to_hex(hex), hex)
+ self.assertEqual(hashutil.hash_to_hex(hash), hex)
- @istest
- def hash_to_bytes(self):
+ def test_hash_to_bytes(self):
for type in self.checksums:
hex = self.hex_checksums[type]
hash = self.checksums[type]
- self.assertEquals(hashutil.hash_to_bytes(hex), hash)
- self.assertEquals(hashutil.hash_to_bytes(hash), hash)
+ self.assertEqual(hashutil.hash_to_bytes(hex), hash)
+ self.assertEqual(hashutil.hash_to_bytes(hash), hash)
- @istest
- def hash_to_bytehex(self):
+ def test_hash_to_bytehex(self):
for algo in self.checksums:
self.assertEqual(self.hex_checksums[algo].encode('ascii'),
hashutil.hash_to_bytehex(self.checksums[algo]))
- @istest
- def bytehex_to_hash(self):
+ def test_bytehex_to_hash(self):
for algo in self.checksums:
self.assertEqual(self.checksums[algo],
hashutil.bytehex_to_hash(
self.hex_checksums[algo].encode()))
- @istest
- def new_hash_unsupported_hashing_algorithm(self):
+ def test_new_hash_unsupported_hashing_algorithm(self):
try:
hashutil._new_hash('blake2:10')
except ValueError as e:
- self.assertEquals(str(e),
- 'Unexpected hashing algorithm blake2:10, '
- 'expected one of blake2b512, blake2s256, '
- 'sha1, sha1_git, sha256')
+ self.assertEqual(str(e),
+ 'Unexpected hashing algorithm blake2:10, '
+ 'expected one of blake2b512, blake2s256, '
+ 'sha1, sha1_git, sha256')
@patch('hashlib.new')
- @istest
- def new_hash_blake2b_blake2b512_builtin(self, mock_hashlib_new):
+ def test_new_hash_blake2b_blake2b512_builtin(self, mock_hashlib_new):
if 'blake2b512' not in hashlib.algorithms_available:
self.skipTest('blake2b512 not built-in')
mock_hashlib_new.return_value = sentinel = object()
@@ -243,8 +218,7 @@ class Hashutil(BaseHashutil):
mock_hashlib_new.assert_called_with('blake2b512')
@patch('hashlib.new')
- @istest
- def new_hash_blake2s_blake2s256_builtin(self, mock_hashlib_new):
+ def test_new_hash_blake2s_blake2s256_builtin(self, mock_hashlib_new):
if 'blake2s256' not in hashlib.algorithms_available:
self.skipTest('blake2s256 not built-in')
mock_hashlib_new.return_value = sentinel = object()
@@ -254,8 +228,7 @@ class Hashutil(BaseHashutil):
self.assertIs(h, sentinel)
mock_hashlib_new.assert_called_with('blake2s256')
- @istest
- def new_hash_blake2b_builtin(self):
+ def test_new_hash_blake2b_builtin(self):
removed_hash = False
try:
@@ -276,8 +249,7 @@ class Hashutil(BaseHashutil):
if removed_hash:
hashlib.algorithms_available.add('blake2b512')
- @istest
- def new_hash_blake2s_builtin(self):
+ def test_new_hash_blake2s_builtin(self):
removed_hash = False
try:
@@ -298,8 +270,7 @@ class Hashutil(BaseHashutil):
if removed_hash:
hashlib.algorithms_available.add('blake2s256')
- @istest
- def new_hash_blake2b_pyblake2(self):
+ def test_new_hash_blake2b_pyblake2(self):
if 'blake2b512' in hashlib.algorithms_available:
self.skipTest('blake2b512 built in')
if 'blake2b' in hashlib.algorithms_available:
@@ -313,8 +284,7 @@ class Hashutil(BaseHashutil):
self.assertIs(h, sentinel)
mock_blake2b.assert_called_with(digest_size=512//8)
- @istest
- def new_hash_blake2s_pyblake2(self):
+ def test_new_hash_blake2s_pyblake2(self):
if 'blake2s256' in hashlib.algorithms_available:
self.skipTest('blake2s256 built in')
if 'blake2s' in hashlib.algorithms_available:
@@ -369,15 +339,13 @@ blah
'e9e959f120'),
}
- @istest
- def unknown_header_type(self):
+ def test_unknown_header_type(self):
with self.assertRaises(ValueError) as cm:
hashutil.hash_git_data(b'any-data', 'some-unknown-type')
self.assertIn('Unexpected git object type', cm.exception.args[0])
- @istest
- def hashdata_content(self):
+ def test_hashdata_content(self):
# when
actual_hash = hashutil.hash_git_data(self.blob_data, git_type='blob')
@@ -385,8 +353,7 @@ blah
self.assertEqual(actual_hash,
self.checksums['blob_sha1_git'])
- @istest
- def hashdata_tree(self):
+ def test_hashdata_tree(self):
# when
actual_hash = hashutil.hash_git_data(self.tree_data, git_type='tree')
@@ -394,8 +361,7 @@ blah
self.assertEqual(actual_hash,
self.checksums['tree_sha1_git'])
- @istest
- def hashdata_revision(self):
+ def test_hashdata_revision(self):
# when
actual_hash = hashutil.hash_git_data(self.commit_data,
git_type='commit')
@@ -404,8 +370,7 @@ blah
self.assertEqual(actual_hash,
self.checksums['commit_sha1_git'])
- @istest
- def hashdata_tag(self):
+ def test_hashdata_tag(self):
# when
actual_hash = hashutil.hash_git_data(self.tag_data, git_type='tag')
diff --git a/swh/model/tests/test_identifiers.py b/swh/model/tests/test_identifiers.py
index 66586085535fcaaf3788b1ce5ffce99760eaf46d..de96865e3bb816a396ca50bd7edf9d3065f3d031 100644
--- a/swh/model/tests/test_identifiers.py
+++ b/swh/model/tests/test_identifiers.py
@@ -7,14 +7,11 @@ import binascii
import datetime
import unittest
-from nose.tools import istest
-
from swh.model import hashutil, identifiers
-
from swh.model.exceptions import ValidationError
-from swh.model.identifiers import SNAPSHOT, RELEASE, REVISION, DIRECTORY
-from swh.model.identifiers import CONTENT, PERSISTENT_IDENTIFIER_TYPES
-from swh.model.identifiers import PersistentId
+from swh.model.identifiers import (CONTENT, DIRECTORY,
+ PERSISTENT_IDENTIFIER_TYPES, RELEASE,
+ REVISION, SNAPSHOT, PersistentId)
class UtilityFunctionsIdentifier(unittest.TestCase):
@@ -23,8 +20,7 @@ class UtilityFunctionsIdentifier(unittest.TestCase):
self.bytes_id = binascii.unhexlify(self.str_id)
self.bad_type_id = object()
- @istest
- def identifier_to_bytes(self):
+ def test_identifier_to_bytes(self):
for id in [self.str_id, self.bytes_id]:
self.assertEqual(identifiers.identifier_to_bytes(id),
self.bytes_id)
@@ -40,8 +36,7 @@ class UtilityFunctionsIdentifier(unittest.TestCase):
self.assertIn('type', str(cm.exception))
- @istest
- def identifier_to_str(self):
+ def test_identifier_to_str(self):
for id in [self.str_id, self.bytes_id]:
self.assertEqual(identifiers.identifier_to_str(id),
self.str_id)
@@ -84,19 +79,16 @@ class UtilityFunctionsDateOffset(unittest.TestCase):
800: b'+1320',
}
- @istest
- def format_date(self):
+ def test_format_date(self):
for date_repr, date in self.dates.items():
self.assertEqual(identifiers.format_date(date), date_repr)
- @istest
- def format_date_fail(self):
+ def test_format_date_fail(self):
for date in self.broken_dates:
with self.assertRaises(ValueError):
identifiers.format_date(date)
- @istest
- def format_offset(self):
+ def test_format_offset(self):
for offset, res in self.offsets.items():
self.assertEqual(identifiers.format_offset(offset), res)
@@ -113,8 +105,7 @@ class ContentIdentifier(unittest.TestCase):
self.content_id = hashutil.hash_data(self.content['data'])
- @istest
- def content_identifier(self):
+ def test_content_identifier(self):
self.assertEqual(identifiers.content_identifier(self.content),
self.content_id)
@@ -216,14 +207,12 @@ class DirectoryIdentifier(unittest.TestCase):
'entries': [],
}
- @istest
- def dir_identifier(self):
+ def test_dir_identifier(self):
self.assertEqual(
identifiers.directory_identifier(self.directory),
self.directory['id'])
- @istest
- def dir_identifier_empty_directory(self):
+ def test_dir_identifier_empty_directory(self):
self.assertEqual(
identifiers.directory_identifier(self.empty_directory),
self.empty_directory['id'])
@@ -460,29 +449,25 @@ dg1KdHOa34shrKDaOVzW
}
}
- @istest
- def revision_identifier(self):
+ def test_revision_identifier(self):
self.assertEqual(
identifiers.revision_identifier(self.revision),
identifiers.identifier_to_str(self.revision['id']),
)
- @istest
- def revision_identifier_none_metadata(self):
+ def test_revision_identifier_none_metadata(self):
self.assertEqual(
identifiers.revision_identifier(self.revision_none_metadata),
identifiers.identifier_to_str(self.revision_none_metadata['id']),
)
- @istest
- def revision_identifier_synthetic(self):
+ def test_revision_identifier_synthetic(self):
self.assertEqual(
identifiers.revision_identifier(self.synthetic_revision),
identifiers.identifier_to_str(self.synthetic_revision['id']),
)
- @istest
- def revision_identifier_with_extra_headers(self):
+ def test_revision_identifier_with_extra_headers(self):
self.assertEqual(
identifiers.revision_identifier(
self.revision_with_extra_headers),
@@ -490,8 +475,7 @@ dg1KdHOa34shrKDaOVzW
self.revision_with_extra_headers['id']),
)
- @istest
- def revision_identifier_with_gpgsig(self):
+ def test_revision_identifier_with_gpgsig(self):
self.assertEqual(
identifiers.revision_identifier(
self.revision_with_gpgsig),
@@ -499,8 +483,7 @@ dg1KdHOa34shrKDaOVzW
self.revision_with_gpgsig['id']),
)
- @istest
- def revision_identifier_no_message(self):
+ def test_revision_identifier_no_message(self):
self.assertEqual(
identifiers.revision_identifier(
self.revision_no_message),
@@ -508,8 +491,7 @@ dg1KdHOa34shrKDaOVzW
self.revision_no_message['id']),
)
- @istest
- def revision_identifier_empty_message(self):
+ def test_revision_identifier_empty_message(self):
self.assertEqual(
identifiers.revision_identifier(
self.revision_empty_message),
@@ -517,8 +499,7 @@ dg1KdHOa34shrKDaOVzW
self.revision_empty_message['id']),
)
- @istest
- def revision_identifier_only_fullname(self):
+ def test_revision_identifier_only_fullname(self):
self.assertEqual(
identifiers.revision_identifier(
self.revision_only_fullname),
@@ -643,43 +624,37 @@ o6X/3T+vm8K3bf3driRr34c=
'target_type': 'revision',
}
- @istest
- def release_identifier(self):
+ def test_release_identifier(self):
self.assertEqual(
identifiers.release_identifier(self.release),
identifiers.identifier_to_str(self.release['id'])
)
- @istest
- def release_identifier_no_author(self):
+ def test_release_identifier_no_author(self):
self.assertEqual(
identifiers.release_identifier(self.release_no_author),
identifiers.identifier_to_str(self.release_no_author['id'])
)
- @istest
- def release_identifier_no_message(self):
+ def test_release_identifier_no_message(self):
self.assertEqual(
identifiers.release_identifier(self.release_no_message),
identifiers.identifier_to_str(self.release_no_message['id'])
)
- @istest
- def release_identifier_empty_message(self):
+ def test_release_identifier_empty_message(self):
self.assertEqual(
identifiers.release_identifier(self.release_empty_message),
identifiers.identifier_to_str(self.release_empty_message['id'])
)
- @istest
- def release_identifier_negative_utc(self):
+ def test_release_identifier_negative_utc(self):
self.assertEqual(
identifiers.release_identifier(self.release_negative_utc),
identifiers.identifier_to_str(self.release_negative_utc['id'])
)
- @istest
- def release_identifier_newline_in_author(self):
+ def test_release_identifier_newline_in_author(self):
self.assertEqual(
identifiers.release_identifier(self.release_newline_in_author),
identifiers.identifier_to_str(self.release_newline_in_author['id'])
@@ -829,7 +804,7 @@ class SnapshotIdentifier(unittest.TestCase):
actual_value = identifiers.persistent_identifier(
full_type, _hash, metadata=_meta)
- self.assertEquals(actual_value, expected_persistent_id)
+ self.assertEqual(actual_value, expected_persistent_id)
def test_persistent_identifier_wrong_input(self):
_snapshot_id = 'notahash4bc0bf3d81436bf980b46e98bd338453'
@@ -864,7 +839,7 @@ class SnapshotIdentifier(unittest.TestCase):
metadata={}
)
actual_result = identifiers.parse_persistent_identifier(pid)
- self.assertEquals(actual_result, expected_result)
+ self.assertEqual(actual_result, expected_result)
for pid, _type, _version, _hash, _metadata in [
('swh:1:cnt:9c95815d9e9d91b8dae8e05d8bbc696fe19f796b;lines=1-18;origin=https://github.com/python/cpython', # noqa
@@ -887,7 +862,7 @@ class SnapshotIdentifier(unittest.TestCase):
metadata=_metadata
)
actual_result = identifiers.parse_persistent_identifier(pid)
- self.assertEquals(actual_result, expected_result)
+ self.assertEqual(actual_result, expected_result)
def test_parse_persistent_identifier_parsing_error(self):
for pid, _error in [
diff --git a/swh/model/tests/test_merkle.py b/swh/model/tests/test_merkle.py
index 9f438928decb2018645e71b66a898980173e024f..8b1180a4094c19005b19ea52d8879fac9ac405fb 100644
--- a/swh/model/tests/test_merkle.py
+++ b/swh/model/tests/test_merkle.py
@@ -8,7 +8,7 @@ import unittest
from swh.model import merkle
-class TestedMerkleNode(merkle.MerkleNode):
+class MerkleTestNode(merkle.MerkleNode):
type = 'tested_merkle_node_type'
def __init__(self, data):
@@ -29,7 +29,7 @@ class TestedMerkleNode(merkle.MerkleNode):
)
-class TestedMerkleLeaf(merkle.MerkleLeaf):
+class MerkleTestLeaf(merkle.MerkleLeaf):
type = 'tested_merkle_leaf_type'
def __init__(self, data):
@@ -44,7 +44,7 @@ class TestedMerkleLeaf(merkle.MerkleLeaf):
class TestMerkleLeaf(unittest.TestCase):
def setUp(self):
self.data = {'value': b'value'}
- self.instance = TestedMerkleLeaf(self.data)
+ self.instance = MerkleTestLeaf(self.data)
def test_hash(self):
self.assertEqual(self.instance.compute_hash_called, 0)
@@ -90,25 +90,25 @@ class TestMerkleNode(unittest.TestCase):
maxDiff = None
def setUp(self):
- self.root = TestedMerkleNode({'value': b'root'})
+ self.root = MerkleTestNode({'value': b'root'})
self.nodes = {b'root': self.root}
for i in (b'a', b'b', b'c'):
value = b'root/' + i
- node = TestedMerkleNode({
+ node = MerkleTestNode({
'value': value,
})
self.root[i] = node
self.nodes[value] = node
for j in (b'a', b'b', b'c'):
value2 = value + b'/' + j
- node2 = TestedMerkleNode({
+ node2 = MerkleTestNode({
'value': value2,
})
node[j] = node2
self.nodes[value2] = node2
for k in (b'a', b'b', b'c'):
value3 = value2 + b'/' + j
- node3 = TestedMerkleNode({
+ node3 = MerkleTestNode({
'value': value3,
})
node2[j] = node3
@@ -188,8 +188,8 @@ class TestMerkleNode(unittest.TestCase):
hash_root = self.root.hash
hash_b = self.root[b'b'].hash
new_children = {
- b'c': TestedMerkleNode({'value': b'root/b/new_c'}),
- b'd': TestedMerkleNode({'value': b'root/b/d'}),
+ b'c': MerkleTestNode({'value': b'root/b/new_c'}),
+ b'd': MerkleTestNode({'value': b'root/b/d'}),
}
# collect all nodes
@@ -219,7 +219,7 @@ class TestMerkleNode(unittest.TestCase):
# Ensure we collected root, root/b, and both new children
collected_after_update = self.root.collect()
self.assertCountEqual(
- collected_after_update[TestedMerkleNode.type],
+ collected_after_update[MerkleTestNode.type],
[self.nodes[b'root'].hash, self.nodes[b'root/b'].hash,
new_children[b'c'].hash, new_children[b'd'].hash],
)
diff --git a/swh/model/tests/test_toposort.py b/swh/model/tests/test_toposort.py
index 66a8ee1c8ae9543b6dffdccf3a7fd389f8150630..174368f579d1fad763bb5ddb4b3720c6e01d579a 100644
--- a/swh/model/tests/test_toposort.py
+++ b/swh/model/tests/test_toposort.py
@@ -4,6 +4,7 @@
# See top-level LICENSE file for more information
import unittest
+
from swh.model.toposort import toposort
diff --git a/swh/model/tests/test_validators.py b/swh/model/tests/test_validators.py
index 60a1de42952167c54d94979eb18118a0ad32ee8a..8c8512e9cc6978e577d9e774be578244eacf21ac 100644
--- a/swh/model/tests/test_validators.py
+++ b/swh/model/tests/test_validators.py
@@ -6,9 +6,7 @@
import datetime
import unittest
-from nose.tools import istest
-
-from swh.model import validators, hashutil, exceptions
+from swh.model import exceptions, hashutil, validators
class TestValidators(unittest.TestCase):
@@ -38,16 +36,14 @@ class TestValidators(unittest.TestCase):
self.invalid_content_hash_mismatch.update(
hashutil.hash_data(b"this is not the data you're looking for"))
- @istest
- def validate_content(self):
+ def test_validate_content(self):
self.assertTrue(
validators.validate_content(self.valid_visible_content))
self.assertTrue(
validators.validate_content(self.valid_absent_content))
- @istest
- def validate_content_hash_mismatch(self):
+ def test_validate_content_hash_mismatch(self):
with self.assertRaises(exceptions.ValidationError) as cm:
validators.validate_content(self.invalid_content_hash_mismatch)
@@ -62,8 +58,8 @@ class TestValidators(unittest.TestCase):
exc = cm.exception
self.assertIsInstance(str(exc), str)
- self.assertEquals(set(exc.error_dict.keys()),
- {exceptions.NON_FIELD_ERRORS})
+ self.assertEqual(set(exc.error_dict.keys()),
+ {exceptions.NON_FIELD_ERRORS})
hash_mismatches = exc.error_dict[exceptions.NON_FIELD_ERRORS]
self.assertIsInstance(hash_mismatches, list)
diff --git a/swh/model/validators.py b/swh/model/validators.py
index ea64b40f800c2c384b67019306549adc262c216f..6d2c37035b04a0185750aae7c0b1c0f02cad5584 100644
--- a/swh/model/validators.py
+++ b/swh/model/validators.py
@@ -1,10 +1,11 @@
-# Copyright (C) 2015 The Software Heritage developers
+# Copyright (C) 2015-2018 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
from .exceptions import ValidationError, NON_FIELD_ERRORS
-from . import fields, hashutil
+from . import fields
+from .hashutil import MultiHash, hash_to_bytes
def validate_content(content):
@@ -44,11 +45,11 @@ def validate_content(content):
def validate_hashes(content):
errors = []
if 'data' in content:
- hashes = hashutil.hash_data(content['data'])
+ hashes = MultiHash.from_data(content['data']).digest()
for hash_type, computed_hash in hashes.items():
if hash_type not in content:
continue
- content_hash = hashutil.hash_to_bytes(content[hash_type])
+ content_hash = hash_to_bytes(content[hash_type])
if content_hash != computed_hash:
errors.append(ValidationError(
'hash mismatch in content for hash %(hash)s',
diff --git a/tox.ini b/tox.ini
new file mode 100644
index 0000000000000000000000000000000000000000..0fb07c66bbbafd910825e5048dde06f445d8fd4e
--- /dev/null
+++ b/tox.ini
@@ -0,0 +1,16 @@
+[tox]
+envlist=flake8,py3
+
+[testenv:py3]
+deps =
+ .[testing]
+ pytest-cov
+commands =
+ pytest --cov=swh --cov-branch {posargs}
+
+[testenv:flake8]
+skip_install = true
+deps =
+ flake8
+commands =
+ {envpython} -m flake8
diff --git a/version.txt b/version.txt
index 04ecf50935976fe64ce5bc3a8fd124094e1dd418..b5af97970e87e33ff6a989b707c5e85141bd4e58 100644
--- a/version.txt
+++ b/version.txt
@@ -1 +1 @@
-v0.0.27-0-geb338cd
\ No newline at end of file
+v0.0.28-0-g4e6bce9
\ No newline at end of file