udata 9.1.4__py2.py3-none-any.whl → 9.1.4.dev30973__py2.py3-none-any.whl

udata/core/user/api.py

@@ -1,15 +1,15 @@
-from typing import Optional
-
 from flask_security import current_user, logout_user
 from slugify import slugify
 
 from udata.api import API, api
 from udata.api.parsers import ModelApiParser
 from udata.auth import admin_permission
+from udata.core import storages
 from udata.core.dataset.api_fields import community_resource_fields, dataset_fields
 from udata.core.discussions.actions import discussions_for
 from udata.core.discussions.api import discussion_fields
 from udata.core.followers.api import FollowAPI
+from udata.core.reuse.api_fields import reuse_fields
 from udata.core.storages.api import (
     image_parser,
     parse_uploaded_image,
@@ -103,7 +103,7 @@ class AvatarAPI(API):
 class MyReusesAPI(API):
     @api.secure
     @api.doc("my_reuses")
-    @api.marshal_list_with(Reuse.__read_fields__)
+    @api.marshal_list_with(reuse_fields)
     def get(self):
         """List all my reuses (including private ones)"""
         return list(Reuse.objects.owned_by(current_user.id))
@@ -166,7 +166,7 @@ class MyOrgReusesAPI(API):
     @api.secure
     @api.doc("my_org_reuses")
     @api.expect(filter_parser)
-    @api.marshal_list_with(Reuse.__read_fields__)
+    @api.marshal_list_with(reuse_fields)
     def get(self):
         """List all reuses related to me and my organizations."""
         q = filter_parser.parse_args().get("q")
@@ -321,10 +321,9 @@ class UserAPI(API):
         return "", 204
 
 
-# These imports are not at the top of the file to avoid circular imports
-from udata.core.contact_point.api import ContactPointApiParser  # noqa
-from udata.core.contact_point.api_fields import contact_point_page_fields  # noqa
-from udata.models import ContactPoint  # noqa
+from udata.core.contact_point.api import ContactPointApiParser
+from udata.core.contact_point.api_fields import contact_point_page_fields
+from udata.models import ContactPoint
 
 contact_point_parser = ContactPointApiParser()
 
@@ -361,27 +360,8 @@ suggest_parser = api.parser()
 suggest_parser.add_argument(
     "q", help="The string to autocomplete/suggest", location="args", required=True
 )
-
-
-def suggest_size(value: str) -> Optional[int]:
-    """Parse an integer that must be between 1 and 20."""
-    help_message = "The size must be an integer between 1 and 20."
-    try:
-        parsed = int(value)
-    except ValueError:
-        raise ValueError(help_message)
-
-    if parsed < 1 or parsed > 20:
-        raise ValueError(help_message)
-    return parsed
-
-
 suggest_parser.add_argument(
-    "size",
-    type=suggest_size,
-    help="The amount of suggestion to fetch (between 1 and 20)",
-    location="args",
-    default=10,
+    "size", type=int, help="The amount of suggestion to fetch", location="args", default=10
 )
 
 

udata/core/user/metrics.py

@@ -1,6 +1,6 @@
 from udata.core.followers.signals import on_follow, on_unfollow
 from udata.core.owned import Owned
-from udata.models import Dataset, Reuse, User
+from udata.models import Dataset, Reuse, User, db
 
 
 @Dataset.on_create.connect

udata/cors.py

@@ -15,10 +15,10 @@ def add_vary(headers: Headers, header: str):
 
 def add_actual_request_headers(headers: Headers) -> Headers:
     origin = request.headers.get("Origin", None)
-    add_vary(headers, "Origin")
-
     if origin:
         headers.set("Access-Control-Allow-Origin", origin)
+        add_vary(headers, "Origin")
+
         headers.set("Access-Control-Allow-Credentials", "true")
 
     return headers
@@ -41,10 +41,10 @@ def is_allowed_cors_route():
 
 def add_preflight_request_headers(headers: Headers) -> Headers:
     origin = request.headers.get("Origin", None)
-    add_vary(headers, "Origin")
-
     if origin:
         headers.set("Access-Control-Allow-Origin", origin)
+        add_vary(headers, "Origin")
+
         headers.set("Access-Control-Allow-Credentials", "true")
 
         # The API allows all methods, so just copy the browser requested methods from the request headers.

udata/features/transfer/api.py

@@ -3,6 +3,7 @@ from flask import request
 from udata.api import API, api, base_reference, fields
 from udata.core.dataset.api_fields import dataset_ref_fields
 from udata.core.organization.api_fields import org_ref_fields
+from udata.core.reuse.api_fields import reuse_ref_fields
 from udata.core.user.api_fields import user_ref_fields
 from udata.models import Dataset, Organization, Reuse, User, db
 from udata.utils import id_or_404
@@ -46,7 +47,7 @@ person_mapping = {
 
 subject_mapping = {
     Dataset: dataset_ref_fields,
-    Reuse: Reuse.__ref_fields__,
+    Reuse: reuse_ref_fields,
 }
 
 transfer_fields = api.model(

udata/harvest/actions.py

@@ -177,7 +177,7 @@ def purge_jobs():
         bucket = current_app.config.get("HARVEST_GRAPHS_S3_BUCKET")
         if bucket is None:
             log.error(
-                "Bucket isn't configured anymore, but jobs still exist with external filenames. Could not delete them."
+                f"Bucket isn't configured anymore, but jobs still exist with external filenames. Could not delete them."
             )
             break
 

udata/harvest/backends/__init__.py

@@ -14,4 +14,4 @@ def get_all(app):
     return get_enabled("udata.harvesters", app)
 
 
-from .base import BaseBackend, HarvestFeature, HarvestFilter  # noqa
+from .base import BaseBackend, HarvestFeature, HarvestFilter  # flake8: noqa

udata/harvest/tasks.py

@@ -1,3 +1,4 @@
+from celery import chord
 from flask import current_app
 
 from udata.tasks import get_logger, job, task

udata/harvest/tests/factories.py

@@ -3,6 +3,8 @@ import pytest
 from factory.fuzzy import FuzzyChoice
 from flask.signals import Namespace
 
+from udata.core.dataset.factories import DatasetFactory
+from udata.core.dataset.models import Dataset
 from udata.factories import ModelFactory
 
 from .. import backends

udata/harvest/tests/test_base_backend.py

@@ -2,6 +2,7 @@ from datetime import datetime, timedelta
 from urllib.parse import urlparse
 
 import pytest
+from dateutil.parser import parse
 from voluptuous import Schema
 
 from udata.core.dataset import tasks

udata/harvest/tests/test_dcat_backend.py

@@ -4,6 +4,7 @@ import re
 import xml.etree.ElementTree as ET
 from datetime import date
 
+import boto3
 import pytest
 from flask import current_app
 
@@ -244,7 +245,7 @@ class DcatBackendTest:
 
         datasets = {d.harvest.dct_identifier: d for d in Dataset.objects}
 
-        assert datasets["1"].schema is None
+        assert datasets["1"].schema == None
         resources_by_title = {resource["title"]: resource for resource in datasets["1"].resources}
 
         # Schema with wrong version are considered as external. Maybe we could change this in the future
@@ -252,8 +253,8 @@ class DcatBackendTest:
             resources_by_title["Resource 1-2"].schema.url
             == "https://schema.data.gouv.fr/schemas/etalab/schema-irve-statique/1337.42.0/schema-statique.json"
         )
-        assert resources_by_title["Resource 1-2"].schema.name is None
-        assert resources_by_title["Resource 1-2"].schema.version is None
+        assert resources_by_title["Resource 1-2"].schema.name == None
+        assert resources_by_title["Resource 1-2"].schema.version == None
 
         assert datasets["2"].schema.name == "RGF93 / Lambert-93 (EPSG:2154)"
         assert (
@@ -265,17 +266,17 @@ class DcatBackendTest:
         # Unknown schema are kept as they were provided
         assert resources_by_title["Resource 2-1"].schema.name == "Example Schema"
         assert resources_by_title["Resource 2-1"].schema.url == "https://example.org/schema.json"
-        assert resources_by_title["Resource 2-1"].schema.version is None
+        assert resources_by_title["Resource 2-1"].schema.version == None
 
-        assert resources_by_title["Resource 2-2"].schema is None
+        assert resources_by_title["Resource 2-2"].schema == None
 
-        assert datasets["3"].schema is None
+        assert datasets["3"].schema == None
         resources_by_title = {resource["title"]: resource for resource in datasets["3"].resources}
 
         # If there is just the URL, and it matches a known schema inside the catalog, only set the name and the version
         # (discard the URL)
         assert resources_by_title["Resource 3-1"].schema.name == "etalab/schema-irve-statique"
-        assert resources_by_title["Resource 3-1"].schema.url is None
+        assert resources_by_title["Resource 3-1"].schema.url == None
         assert resources_by_title["Resource 3-1"].schema.version == "2.2.0"
 
         job = HarvestJob.objects.order_by("-id").first()
@@ -320,7 +321,7 @@ class DcatBackendTest:
 
         datasets = {d.harvest.dct_identifier: d for d in Dataset.objects}
 
-        assert datasets["1"].spatial is None
+        assert datasets["1"].spatial == None
         assert datasets["2"].spatial.geom == {
             "type": "MultiPolygon",
             "coordinates": [
@@ -329,7 +330,7 @@ class DcatBackendTest:
                 [[[159, -25.0], [159, -11], [212, -11], [212, -25.0], [159, -25.0]]],
             ],
         }
-        assert datasets["3"].spatial is None
+        assert datasets["3"].spatial == None
 
     @pytest.mark.options(SCHEMA_CATALOG_URL="https://example.com/schemas")
     def test_harvest_schemas(self, rmock):
@@ -344,7 +345,7 @@ class DcatBackendTest:
 
         datasets = {d.harvest.dct_identifier: d for d in Dataset.objects}
 
-        assert datasets["1"].schema is None
+        assert datasets["1"].schema == None
         resources_by_title = {resource["title"]: resource for resource in datasets["1"].resources}
 
         # Schema with wrong version are considered as external. Maybe we could change this in the future
@@ -352,8 +353,8 @@ class DcatBackendTest:
             resources_by_title["Resource 1-2"].schema.url
             == "https://schema.data.gouv.fr/schemas/etalab/schema-irve-statique/1337.42.0/schema-statique.json"
         )
-        assert resources_by_title["Resource 1-2"].schema.name is None
-        assert resources_by_title["Resource 1-2"].schema.version is None
+        assert resources_by_title["Resource 1-2"].schema.name == None
+        assert resources_by_title["Resource 1-2"].schema.version == None
 
         assert datasets["2"].schema.name == "RGF93 / Lambert-93 (EPSG:2154)"
         assert (
@@ -365,17 +366,17 @@ class DcatBackendTest:
         # Unknown schema are kept as they were provided
         assert resources_by_title["Resource 2-1"].schema.name == "Example Schema"
         assert resources_by_title["Resource 2-1"].schema.url == "https://example.org/schema.json"
-        assert resources_by_title["Resource 2-1"].schema.version is None
+        assert resources_by_title["Resource 2-1"].schema.version == None
 
-        assert resources_by_title["Resource 2-2"].schema is None
+        assert resources_by_title["Resource 2-2"].schema == None
 
-        assert datasets["3"].schema is None
+        assert datasets["3"].schema == None
         resources_by_title = {resource["title"]: resource for resource in datasets["3"].resources}
 
         # If there is just the URL, and it matches a known schema inside the catalog, only set the name and the version
         # (discard the URL)
         assert resources_by_title["Resource 3-1"].schema.name == "etalab/schema-irve-statique"
-        assert resources_by_title["Resource 3-1"].schema.url is None
+        assert resources_by_title["Resource 3-1"].schema.url == None
         assert resources_by_title["Resource 3-1"].schema.version == "2.2.0"
 
     def test_simple_nested_attributes(self, rmock):

udata/migrations/2020-07-24-remove-s-from-scope-oauth.py

@@ -18,7 +18,7 @@ def migrate(db):
     oauth_clients = db.oauth2_client
     oauth_clients.update_many({}, {"$rename": {"scopes": "scope"}})
     for client in oauth_clients.find():
-        if type(client["scope"]) is list:
+        if type(client["scope"]) == list:
             scope_str = " ".join(client["scope"])
             client["scope"] = scope_str
             oauth_clients.save(client)

udata/migrations/2021-07-05-remove-unused-badges.py

@@ -4,6 +4,7 @@ The purpose here is to update every resource's metadata 'schema' name.
 
 import logging
 
+from udata.core.reuse.models import Reuse
 from udata.models import Dataset, Reuse
 
 log = logging.getLogger(__name__)

udata/migrations/2023-02-08-rename-internal-dates.py

@@ -6,6 +6,8 @@ import logging
 
 from mongoengine.connection import get_db
 
+from udata.models import Dataset
+
 log = logging.getLogger(__name__)
 
 

udata/migrations/2024-06-11-fix-reuse-datasets-references.py

@@ -4,6 +4,7 @@ Add a default topic to all reuses in db
 
 import logging
 
+import mongoengine
 from bson import DBRef
 
 from udata.models import Reuse

udata/mongo/datetime_fields.py

@@ -6,7 +6,6 @@ from mongoengine import EmbeddedDocument
 from mongoengine.fields import BaseField, DateTimeField
 from mongoengine.signals import pre_save
 
-from udata.api_fields import field
 from udata.i18n import lazy_gettext as _
 
 log = logging.getLogger(__name__)
@@ -56,17 +55,11 @@ class DateRange(EmbeddedDocument):
 
 
 class Datetimed(object):
-    created_at = field(
-        DateTimeField(verbose_name=_("Creation date"), default=datetime.utcnow, required=True),
-        sortable="created",
-        readonly=True,
+    created_at = DateTimeField(
+        verbose_name=_("Creation date"), default=datetime.utcnow, required=True
     )
-    last_modified = field(
-        DateTimeField(
-            verbose_name=_("Last modification date"), default=datetime.utcnow, required=True
-        ),
-        sortable=True,
-        readonly=True,
+    last_modified = DateTimeField(
+        verbose_name=_("Last modification date"), default=datetime.utcnow, required=True
     )
 
 

udata/mongo/document.py

@@ -11,8 +11,6 @@ log = logging.getLogger(__name__)
 def serialize(value):
     if hasattr(value, "to_dict"):
         return value.to_dict()
-    elif isinstance(value, dict):
-        return {key: serialize(val) for key, val in value.items()}
     elif isinstance(value, Iterable) and not isinstance(value, str):
         return [serialize(val) for val in value]
     else:

udata/mongo/taglist_field.py

@@ -1,24 +1,12 @@
 from mongoengine.fields import ListField, StringField
 from slugify import slugify
 
-from udata import tags
-from udata.i18n import lazy_gettext as _
-
 
 class TagListField(ListField):
     def __init__(self, **kwargs):
         self.tags = []
         super(TagListField, self).__init__(StringField(), **kwargs)
 
-    @staticmethod
-    def from_input(input):
-        if isinstance(input, list):
-            return [tags.slug(value) for value in input]
-        elif isinstance(input, str):
-            return tags.tags_list(input)
-        else:
-            return []
-
     def clean(self, value):
         return sorted(list(set([slugify(v, to_lower=True) for v in value])))
 
@@ -27,17 +15,3 @@ class TagListField(ListField):
 
     def to_mongo(self, value):
         return super(TagListField, self).to_mongo(self.clean(value))
-
-    def validate(self, values):
-        super(TagListField, self).validate(values)
-
-        for tag in values:
-            if not tags.MIN_TAG_LENGTH <= len(tag) <= tags.MAX_TAG_LENGTH:
-                self.error(
-                    _(
-                        'Tag "%(tag)s" must be between %(min)d ' "and %(max)d characters long.",
-                        min=tags.MIN_TAG_LENGTH,
-                        max=tags.MAX_TAG_LENGTH,
-                        tag=tag,
-                    )
-                )

udata/search/commands.py

@@ -93,7 +93,7 @@ def finalize_reindex(models, start):
         r = requests.post(url, json=payload)
         r.raise_for_status()
     except Exception:
-        log.exception("Unable to set alias for index")
+        log.exception(f"Unable to set alias for index")
 
     modified_since_reindex = 0
     for adapter in iter_adapters():

udata/search/query.py

@@ -3,7 +3,7 @@ import logging
 import urllib.parse
 
 import requests
-from flask import current_app, request
+from flask import current_app, request, url_for
 
 from udata.search.result import SearchResult
 

udata/settings.py

@@ -522,7 +522,6 @@ class Defaults(object):
     FIXTURE_DATASET_SLUGS = []
     PUBLISH_ON_RESOURCE_EVENTS = False
     RESOURCES_ANALYSER_URI = "http://localhost:8000"
-    RESOURCES_ANALYSER_API_KEY = None
 
     # Datasets quality settings
     ###########################################################################