Skip to content

data_catalog#

PIDType#

Bases: TextChoices

All PID types.

Source code in src/apps/core/models/data_catalog.py 
20
21
22
23
24
25
class PIDType(models.TextChoices):
    """All PID types."""

    URN = "URN", "URN"
    DOI = "DOI", "DOI"
    EXTERNAL = "external", "External"

GeneratedPIDType#

Bases: TextChoices

PID types that are generated by Metax.

Source code in src/apps/core/models/data_catalog.py 
28
29
30
31
32
class GeneratedPIDType(models.TextChoices):
    """PID types that are generated by Metax."""

    URN = "URN", "URN"
    DOI = "DOI", "DOI"

default_allowed_pid_types#

Source code in src/apps/core/models/data_catalog.py 
35
36
def default_allowed_pid_types() -> List[PIDType]:
    return [PIDType.EXTERNAL]

default_publishing_channels#

Source code in src/apps/core/models/data_catalog.py 
39
40
def default_publishing_channels() -> List["DataCatalog.PublishingChannel"]:
    return [DataCatalog.PublishingChannel.ETSIN, DataCatalog.PublishingChannel.TTV]

DataCatalog#

Bases: AbstractBaseModel

A curated collection of metadata about resources.

RDF Class: dcat:Catalog

Source: DCAT Version 3, Draft 11, https://www.w3.org/TR/vocab-dcat-3/#Class:Catalog

Attributes:

Name Type Description
title HStoreField

catalog title
dataset_versioning_enabled BooleanField

does the catalog have versioning enabled
harvested BooleanField

are the catalog resources harvested from some other sources
language ManyToManyField

default language of the catalog
publisher ForeignKey

publisher of the cataloged resources
access_rights ForeignKey

default access rights for the cataloged resources
Source code in src/apps/core/models/data_catalog.py 
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
class DataCatalog(AbstractBaseModel):
    """A curated collection of metadata about resources.

    RDF Class: dcat:Catalog

    Source: DCAT Version 3, Draft 11,
    https://www.w3.org/TR/vocab-dcat-3/#Class:Catalog

    Attributes:
        title (HStoreField): catalog title
        dataset_versioning_enabled (models.BooleanField): does the catalog have versioning enabled
        harvested (models.BooleanField):
            are the catalog resources harvested from some other sources
        language (models.ManyToManyField): default language of the catalog
        publisher (models.ForeignKey): publisher of the cataloged resources
        access_rights (models.ForeignKey): default access rights for the cataloged resources
    """

    # https://www.w3.org/TR/vocab-dcat-3/#Property:resource_identifier
    id = models.CharField(
        max_length=255,
        primary_key=True,
        help_text="A unique id of the resource being described or cataloged.",
    )
    title = HStoreField(help_text='example: {"en":"title", "fi":"otsikko"}')
    dataset_versioning_enabled = models.BooleanField(default=False)
    harvested = models.BooleanField(default=False)
    language = models.ManyToManyField(Language, related_name="catalogs")
    publisher = models.ForeignKey(
        "DatasetPublisher",
        on_delete=models.SET_NULL,
        related_name="catalogs",
        null=True,
        blank=True,
    )
    description = HStoreField(
        help_text='example: {"en":"description", "fi":"kuvaus"}', blank=True, null=True
    )
    logo = models.CharField(
        max_length=100,
        blank=True,
        null=True,
    )
    dataset_groups_create = models.ManyToManyField(
        Group,
        help_text="User groups that are allowed to create datasets in catalog.",
        related_name="catalogs_create_datasets",
        blank=True,
    )
    dataset_groups_admin = models.ManyToManyField(
        Group,
        help_text="User groups that are allowed to update all datasets in catalog.",
        related_name="catalogs_admin_datasets",
        blank=True,
    )
    allow_remote_resources = models.BooleanField(
        default=True, help_text="True when datasets in catalog can have remote resources."
    )
    storage_services = ArrayField(
        models.CharField(max_length=64, choices=STORAGE_SERVICE_CHOICES),
        default=list,
        blank=True,
        help_text="File storage services supported for datasets in catalog.",
    )

    class PublishingChannel(models.TextChoices):
        ETSIN = "etsin", _("etsin")
        TTV = "ttv", _("ttv")

    publishing_channels = ArrayField(
        models.CharField(max_length=64, choices=PublishingChannel.choices),
        default=default_publishing_channels,
        blank=True,
        help_text="Channels in which datasets in this catalog will be published.",
    )
    allowed_pid_types = ArrayField(
        models.CharField(max_length=16, choices=PIDType.choices),
        default=default_allowed_pid_types,
        blank=True,
        help_text=(
            "Persistent identifier types supported for datasets in catalog. "
            "External PIDs are not managed by Metax."
        ),
    )
    history = HistoricalRecords(m2m_fields=(language,))

    def __str__(self):
        return self.id

    def __init__(self, *args, **kwargs):
        super().__init__(*args, **kwargs)
        self._admin_user_cache = {}  # Map of user.id -> can admin datasets

    @property
    def managed_pid_types(self) -> list:
        """PID types that are allowed to be generated and managed by Metax."""
        return [v for v in self.allowed_pid_types if v != PIDType.EXTERNAL]

    @property
    def allow_external_pid(self) -> bool:
        return PIDType.EXTERNAL in self.allowed_pid_types

    @property
    def allow_generated_pid(self) -> bool:
        return any(self.managed_pid_types)

    def _can_admin_datasets(self, user: MetaxUser) -> bool:
        return DataCatalogAccessPolicy().query_object_permission(
            user=user, object=self, action="<op:admin_dataset>"
        )

    def can_admin_datasets(self, user: MetaxUser) -> bool:
        """Determine if user has permission to update all datasets in catalog.

        This is potentially called for every dataset in a list, so
        we memoize the value for the lifetime of the instance."""
        perms_cache = self._admin_user_cache
        if user.id not in perms_cache:
            perms_cache[user.id] = self._can_admin_datasets(user)
        return perms_cache[user.id]

    def can_create_datasets(self, user: MetaxUser) -> bool:
        """Determine if user has permission to create datasets in catalog."""
        return DataCatalogAccessPolicy().query_object_permission(
            user=user, object=self, action="<op:create_dataset>"
        )

managed_pid_types: list property #

PID types that are allowed to be generated and managed by Metax.

can_admin_datasets(user) #

Determine if user has permission to update all datasets in catalog.

This is potentially called for every dataset in a list, so we memoize the value for the lifetime of the instance.

Source code in src/apps/core/models/data_catalog.py 
154
155
156
157
158
159
160
161
162
def can_admin_datasets(self, user: MetaxUser) -> bool:
    """Determine if user has permission to update all datasets in catalog.

    This is potentially called for every dataset in a list, so
    we memoize the value for the lifetime of the instance."""
    perms_cache = self._admin_user_cache
    if user.id not in perms_cache:
        perms_cache[user.id] = self._can_admin_datasets(user)
    return perms_cache[user.id]

can_create_datasets(user) #

Determine if user has permission to create datasets in catalog.

Source code in src/apps/core/models/data_catalog.py 
164
165
166
167
168
def can_create_datasets(self, user: MetaxUser) -> bool:
    """Determine if user has permission to create datasets in catalog."""
    return DataCatalogAccessPolicy().query_object_permission(
        user=user, object=self, action="<op:create_dataset>"
    )

CatalogHomePage#

Bases: AbstractDatasetProperty

A homepage of the catalog (a public Web document usually available in HTML).

RDF Property: foaf:homepage

Source: DCAT Version 3, Draft 11, https://www.w3.org/TR/vocab-dcat-3/#Property:catalog_homepage

Note

foaf:homepage is an inverse functional property (IFP) which means that it MUST be unique and precisely identify the Web-page for the resource. This property indicates the canonical Web-page, which might be helpful in cases where there is more than one Web-page about the resource.

Source code in src/apps/core/models/data_catalog.py 
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
class CatalogHomePage(AbstractDatasetProperty):
    """A homepage of the catalog (a public Web document usually available in HTML).

    RDF Property: foaf:homepage

    Source: DCAT Version 3, Draft 11,
    https://www.w3.org/TR/vocab-dcat-3/#Property:catalog_homepage

    Note:
        foaf:homepage is an inverse functional property (IFP) which means that it MUST be unique and precisely
        identify the Web-page for the resource. This property indicates the canonical Web-page, which might be helpful
        in cases where there is more than one Web-page about the resource.

    """

    history = HistoricalRecords()

DatasetPublisher#

Bases: AbstractBaseModel

The entity responsible for making the item available.

Note

Resources of type foaf:Agent are recommended as values for this property.

RDF Property: dcterms:publisher

Source: DCAT Version 3, Draft 11, https://www.w3.org/TR/vocab-dcat-3/#Property:resource_publisher

Attributes:

Name Type Description
name HStoreField

the name of the publisher organization
homepage ManyToManyField

webpage of the publisher
Source code in src/apps/core/models/data_catalog.py 
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
class DatasetPublisher(AbstractBaseModel):
    """The entity responsible for making the item available.

    Note:
        Resources of type foaf:Agent are recommended as values for this property.

    RDF Property: dcterms:publisher

    Source: DCAT Version 3, Draft 11,
    https://www.w3.org/TR/vocab-dcat-3/#Property:resource_publisher

    Attributes:
        name (HStoreField): the name of the publisher organization
        homepage (models.ManyToManyField): webpage of the publisher
    """

    id = models.UUIDField(primary_key=True, default=uuid.uuid4, editable=False)
    name = HStoreField(help_text='example: {"en": "name", "fi":"nimi"}')
    homepage = models.ManyToManyField(CatalogHomePage, related_name="publishers")
    history = HistoricalRecords(m2m_fields=(homepage,))

    def __str__(self):
        name = self.name
        if isinstance(name, str):
            name = json.loads(name)
        return str(next(iter(name.items())))