diff --git a/PKG-INFO b/PKG-INFO
index f1120edf560986917c20ffbade9e6640ca056336..bba27476db25720b2956fe2b08858b12a4dd091e 100644
--- a/PKG-INFO
+++ b/PKG-INFO
@@ -1,6 +1,6 @@
Metadata-Version: 2.1
Name: swh.model
-Version: 0.1.1
+Version: 0.2.0
Summary: Software Heritage data model
Home-page: https://forge.softwareheritage.org/diffusion/DMOD/
Author: Software Heritage developers
diff --git a/swh.model.egg-info/PKG-INFO b/swh.model.egg-info/PKG-INFO
index f1120edf560986917c20ffbade9e6640ca056336..bba27476db25720b2956fe2b08858b12a4dd091e 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: 0.1.1
+Version: 0.2.0
Summary: Software Heritage data model
Home-page: https://forge.softwareheritage.org/diffusion/DMOD/
Author: Software Heritage developers
diff --git a/swh/model/hypothesis_strategies.py b/swh/model/hypothesis_strategies.py
index 448487a8ea2e1e2bc79a51529c64402f17cccdd6..bc9d58c46c2ce73fd153efbd65db2b389a8da84a 100644
--- a/swh/model/hypothesis_strategies.py
+++ b/swh/model/hypothesis_strategies.py
@@ -93,10 +93,13 @@ def urls(draw):
return "%s://%s" % (protocol, domain)
-def persons_d():
- return builds(
- dict, fullname=binary(), email=optional(binary()), name=optional(binary()),
- )
+@composite
+def persons_d(draw):
+ fullname = draw(binary())
+ email = draw(optional(binary()))
+ name = draw(optional(binary()))
+ assume(not (len(fullname) == 32 and email is None and name is None))
+ return dict(fullname=fullname, name=name, email=email)
def persons():
diff --git a/swh/model/model.py b/swh/model/model.py
index 74702cf435d3dfb60b2d39b247531389c2d349c9..7db255cc5600c46f7a35dcc1b5857b0c9fc10775 100644
--- a/swh/model/model.py
+++ b/swh/model/model.py
@@ -7,7 +7,8 @@ import datetime
from abc import ABCMeta, abstractmethod
from enum import Enum
-from typing import Dict, List, Optional, Union
+from hashlib import sha256
+from typing import Dict, List, Optional, TypeVar, Union
import attr
from attrs_strict import type_validator
@@ -51,6 +52,9 @@ def dictify(value):
return value
+ModelType = TypeVar("ModelType", bound="BaseModel")
+
+
class BaseModel:
"""Base class for SWH model classes.
@@ -68,6 +72,13 @@ class BaseModel:
recursively builds the corresponding objects."""
return cls(**d)
+ def anonymize(self: ModelType) -> Optional[ModelType]:
+ """Returns an anonymized version of the object, if needed.
+
+ If the object model does not need/support anonymization, returns None.
+ """
+ return None
+
class HashableObject(metaclass=ABCMeta):
"""Mixin to automatically compute object identifier hash when
@@ -129,6 +140,14 @@ class Person(BaseModel):
return Person(name=name or None, email=email or None, fullname=fullname,)
+ def anonymize(self) -> "Person":
+ """Returns an anonymized version of the Person object.
+
+ Anonymization is simply a Person which fullname is the hashed, with unset name
+ or email.
+ """
+ return Person(fullname=sha256(self.fullname).digest(), name=None, email=None,)
+
@attr.s(frozen=True)
class Timestamp(BaseModel):
@@ -369,6 +388,14 @@ class Release(BaseModel, HashableObject):
d["date"] = TimestampWithTimezone.from_dict(d["date"])
return cls(target_type=ObjectType(d.pop("target_type")), **d)
+ def anonymize(self) -> "Release":
+ """Returns an anonymized version of the Release object.
+
+ Anonymization consists in replacing the author with an anonymized Person object.
+ """
+ author = self.author and self.author.anonymize()
+ return attr.evolve(self, author=author)
+
class RevisionType(Enum):
GIT = "git"
@@ -422,6 +449,16 @@ class Revision(BaseModel, HashableObject):
**d,
)
+ def anonymize(self) -> "Revision":
+ """Returns an anonymized version of the Revision object.
+
+ Anonymization consists in replacing the author and committer with an anonymized
+ Person object.
+ """
+ return attr.evolve(
+ self, author=self.author.anonymize(), committer=self.committer.anonymize()
+ )
+
@attr.s(frozen=True)
class DirectoryEntry(BaseModel):
diff --git a/swh/model/tests/test_hypothesis_strategies.py b/swh/model/tests/test_hypothesis_strategies.py
index 1622b3c71ba47542f4cec845d3a2094f3f152dfd..2be35a0575a04bf2f787ce4f33a406dc190a377f 100644
--- a/swh/model/tests/test_hypothesis_strategies.py
+++ b/swh/model/tests/test_hypothesis_strategies.py
@@ -18,6 +18,7 @@ from swh.model.hypothesis_strategies import (
skipped_contents,
snapshots,
origin_visits,
+ persons,
)
from swh.model.model import TargetType
@@ -196,3 +197,10 @@ def test_snapshots_strategy_fixed_size(snapshot):
@given(origin_visits())
def test_origin_visit_aware_datetime(visit):
assert visit.date.tzinfo is not None
+
+
+@given(persons())
+def test_person_do_not_look_like_anonimized(person):
+ assert not (
+ len(person.fullname) == 32 and person.name is None and person.email is None
+ )
diff --git a/swh/model/tests/test_model.py b/swh/model/tests/test_model.py
index 6027cc2735bc12bd8cb6dc16852dd16a1a4e3535..e126ca571e8d631486242b231df6dd3f88c09e8a 100644
--- a/swh/model/tests/test_model.py
+++ b/swh/model/tests/test_model.py
@@ -61,6 +61,37 @@ def test_todict_inverse_fromdict(objtype_and_obj):
assert obj_as_dict == type(obj).from_dict(obj_as_dict).to_dict()
+# Anonymization
+
+
+@given(strategies.objects())
+def test_anonymization(objtype_and_obj):
+ (obj_type, obj) = objtype_and_obj
+
+ def check_person(p):
+ if p is not None:
+ assert p.name is None
+ assert p.email is None
+ assert len(p.fullname) == 32
+
+ anon_obj = obj.anonymize()
+ if obj_type == "person":
+ assert anon_obj is not None
+ check_person(anon_obj)
+ elif obj_type == "release":
+ assert anon_obj is not None
+ check_person(anon_obj.author)
+ elif obj_type == "revision":
+ assert anon_obj is not None
+ check_person(anon_obj.author)
+ check_person(anon_obj.committer)
+ else:
+ assert anon_obj is None
+
+
+# Origin, OriginVisit
+
+
@given(strategies.origins())
def test_todict_origins(origin):
obj = origin.to_dict()
diff --git a/version.txt b/version.txt
index 8019930dbc7fb6e043f89728e2f895f10b09ad3b..461646da2e67bbb6ae7b2b6799e5334afaaee225 100644
--- a/version.txt
+++ b/version.txt
@@ -1 +1 @@
-v0.1.1-0-g091498e
\ No newline at end of file
+v0.2.0-0-g29312df
\ No newline at end of file