dapla-toolbelt-metadata 0.9.4__py3-none-any.whl → 0.9.5__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.


This version of dapla-toolbelt-metadata might be problematic. Click here for more details.

@@ -33,7 +33,10 @@ from dapla_metadata.datasets.utility.constants import (
33
33
  from dapla_metadata.datasets.utility.constants import METADATA_DOCUMENT_FILE_SUFFIX
34
34
  from dapla_metadata.datasets.utility.constants import NUM_OBLIGATORY_DATASET_FIELDS
35
35
  from dapla_metadata.datasets.utility.constants import NUM_OBLIGATORY_VARIABLES_FIELDS
36
+ from dapla_metadata.datasets.utility.urn import convert_definition_uris_to_urns
36
37
  from dapla_metadata.datasets.utility.utils import OptionalDatadocMetadataType
38
+ from dapla_metadata.datasets.utility.utils import VariableListType
39
+ from dapla_metadata.datasets.utility.utils import VariableType
37
40
  from dapla_metadata.datasets.utility.utils import calculate_percentage
38
41
  from dapla_metadata.datasets.utility.utils import derive_assessment_from_state
39
42
  from dapla_metadata.datasets.utility.utils import get_timestamp_now
@@ -108,8 +111,8 @@ class Datadoc:
108
111
  self.container: all_optional_model.MetadataContainer | None = None
109
112
  self.dataset_path: pathlib.Path | CloudPath | None = None
110
113
  self.dataset = all_optional_model.Dataset()
111
- self.variables: list = []
112
- self.variables_lookup: dict[str, all_optional_model.Variable] = {}
114
+ self.variables: VariableListType = []
115
+ self.variables_lookup: dict[str, VariableType] = {}
113
116
  self.explicitly_defined_metadata_document = False
114
117
  self.dataset_consistency_status: list[DatasetConsistencyStatus] = []
115
118
  if metadata_document_path:
@@ -204,22 +207,21 @@ class Datadoc:
204
207
  else:
205
208
  self._set_metadata(existing_metadata or extracted_metadata)
206
209
 
207
- set_default_values_variables(self.variables)
208
- set_default_values_dataset(cast("all_optional_model.Dataset", self.dataset))
209
- set_dataset_owner(self.dataset)
210
- self._create_variables_lookup()
211
-
212
210
  def _set_metadata(
213
211
  self,
214
- merged_metadata: OptionalDatadocMetadataType,
212
+ metadata: OptionalDatadocMetadataType,
215
213
  ) -> None:
216
- if not merged_metadata or not (
217
- merged_metadata.dataset and merged_metadata.variables
218
- ):
214
+ if not metadata or not (metadata.dataset and metadata.variables):
219
215
  msg = "Could not read metadata"
220
216
  raise ValueError(msg)
221
- self.dataset = cast("all_optional_model.Dataset", merged_metadata.dataset)
222
- self.variables = merged_metadata.variables
217
+ self.dataset = cast("all_optional_model.Dataset", metadata.dataset)
218
+ self.variables = metadata.variables
219
+
220
+ set_default_values_variables(self.variables)
221
+ set_default_values_dataset(cast("all_optional_model.Dataset", self.dataset))
222
+ set_dataset_owner(self.dataset)
223
+ convert_definition_uris_to_urns(self.variables)
224
+ self._create_variables_lookup()
223
225
 
224
226
  def _create_variables_lookup(self) -> None:
225
227
  self.variables_lookup = {
@@ -0,0 +1,129 @@
1
+ """Validate, parse and render URNs."""
2
+
3
+ import logging
4
+ import re
5
+ from dataclasses import dataclass
6
+ from enum import Enum
7
+ from enum import auto
8
+
9
+ from pydantic import AnyUrl
10
+
11
+ from dapla_metadata.datasets.utility.utils import VariableListType
12
+
13
+ logger = logging.getLogger(__name__)
14
+
15
+
16
+ VARDEF_URL_TEMPLATE = "https://{subdomain}.{domain}/variable-definitions"
17
+
18
+
19
+ class SsbNaisDomains(str, Enum):
20
+ """The available domains on SSBs Nais instance."""
21
+
22
+ TEST_EXTERNAL = "test.ssb.no"
23
+ TEST_INTERNAL = "intern.test.ssb.no"
24
+ PROD_EXTERNAL = "ssb.no"
25
+ PROD_INTERNAL = "intern.ssb.no"
26
+
27
+
28
+ class ReferenceUrlTypes(Enum):
29
+ """The general category of the URL.
30
+
31
+ This can be useful to refer to when constructing a URL from a URN for a
32
+ specific context.
33
+ """
34
+
35
+ API = auto()
36
+ FRONTEND = auto()
37
+
38
+
39
+ @dataclass
40
+ class UrnConverter:
41
+ """Converts URLs to URNs and vice versa.
42
+
43
+ Fields:
44
+ urn_base: The format for the URN, up to the identifier.
45
+ id_pattern: A capturing group pattern which matches identifiers for this resource.
46
+ url_bases: The list of all the different URL representations for a resource. There
47
+ will typically be a number of URL representations for a particular resource,
48
+ depending on which system or technology they are accessed through and other
49
+ technical factors. This list defines which concrete URLs can be considered
50
+ equivalent to a URN.
51
+ """
52
+
53
+ urn_base: str
54
+ id_pattern: str
55
+ url_bases: list[tuple[ReferenceUrlTypes, str]]
56
+
57
+ def _extract_id(self, url: str, pattern: re.Pattern[str]) -> str | None:
58
+ if match := pattern.match(url):
59
+ return match.group(1)
60
+ return None
61
+
62
+ def _build_pattern(self, url_base: str) -> re.Pattern[str]:
63
+ return re.compile(f"^{url_base}/{self.id_pattern}")
64
+
65
+ def build_urn(self, identifier: str) -> str:
66
+ """Build a URN for the given identifier."""
67
+ return f"{self.urn_base}:{identifier}"
68
+
69
+ def convert_to_urn(self, url: str | AnyUrl | None) -> str | None:
70
+ """Convert a URL to a generalized URN for that same resource.
71
+
72
+ Args:
73
+ url (str | None): The URL to convert.
74
+
75
+ Returns:
76
+ str | None: The URN or None if it can't be converted.
77
+ """
78
+ if not url:
79
+ return None
80
+
81
+ patterns = (self._build_pattern(url[-1]) for url in self.url_bases)
82
+ matches = (self._extract_id(str(url), p) for p in patterns)
83
+ identifier = next((m for m in matches if m), None)
84
+ if identifier:
85
+ return self.build_urn(identifier)
86
+
87
+ return None
88
+
89
+
90
+ vardef_urn_converter = UrnConverter(
91
+ urn_base="urn:ssb:variable-definition:vardef",
92
+ id_pattern=r"([a-z0-9]{8})",
93
+ url_bases=[
94
+ *[
95
+ (
96
+ ReferenceUrlTypes.API,
97
+ VARDEF_URL_TEMPLATE.format(
98
+ subdomain="metadata", domain=nais_domain.value
99
+ ),
100
+ )
101
+ for nais_domain in SsbNaisDomains
102
+ ],
103
+ *[
104
+ (
105
+ ReferenceUrlTypes.FRONTEND,
106
+ VARDEF_URL_TEMPLATE.format(
107
+ subdomain="catalog", domain=nais_domain.value
108
+ ),
109
+ )
110
+ for nais_domain in SsbNaisDomains
111
+ ],
112
+ ],
113
+ )
114
+
115
+
116
+ def convert_definition_uris_to_urns(variables: VariableListType) -> None:
117
+ """Where definition URIs are recognized URLs, convert them to URNs.
118
+
119
+ Where the value is not a known URL we preserve the value as it is and log an
120
+ ERROR level message.
121
+
122
+ Args:
123
+ variables (VariableListType): The list of variables.
124
+ """
125
+ for v in variables:
126
+ if urn := vardef_urn_converter.convert_to_urn(v.definition_uri):
127
+ v.definition_uri = urn # type: ignore [assignment]
128
+ else:
129
+ logger.error("Could not convert value to URN: %s", v.definition_uri)
@@ -121,7 +121,7 @@ def derive_assessment_from_state(state: DataSetState) -> Assessment:
121
121
  return Assessment.SENSITIVE
122
122
 
123
123
 
124
- def set_default_values_variables(variables: list) -> None:
124
+ def set_default_values_variables(variables: VariableListType) -> None:
125
125
  """Set default values on variables.
126
126
 
127
127
  Args:
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: dapla-toolbelt-metadata
3
- Version: 0.9.4
3
+ Version: 0.9.5
4
4
  Summary: Dapla Toolbelt Metadata
5
5
  Project-URL: homepage, https://github.com/statisticsnorway/dapla-toolbelt-metadata
6
6
  Project-URL: repository, https://github.com/statisticsnorway/dapla-toolbelt-metadata
@@ -8,7 +8,7 @@ dapla_metadata/dapla/user_info.py,sha256=bENez-ICt9ySR8orYebO68Q3_2LkIW9QTL58DTc
8
8
  dapla_metadata/datasets/__init__.py,sha256=an-REJgi7N8-S1SCz-MYO_8as6fMe03WvhjRP_hWWkg,293
9
9
  dapla_metadata/datasets/_merge.py,sha256=Tk5wQz6xZGr8veUAHZb42O8HARU8ObBJ_E4afvVWdlo,12993
10
10
  dapla_metadata/datasets/code_list.py,sha256=JtCE-5Q8grAKvkn0KKjzeGhO-96O7yGsastbuoakreg,9057
11
- dapla_metadata/datasets/core.py,sha256=p-2OJsAEWCUqBlzn0YIYkK-pAgtvMROdoxXvCyjfWYs,20434
11
+ dapla_metadata/datasets/core.py,sha256=GVDnzLZagTpaXin6eC1xB62U-LFinDuWVeZmyx-9pas,20633
12
12
  dapla_metadata/datasets/dapla_dataset_path_info.py,sha256=WPeV_mwKk2B9sXd14SaP-kTb1bOQ_8W2KtrqOG7sJIY,26867
13
13
  dapla_metadata/datasets/dataset_parser.py,sha256=3dtRXNy1C8SfG8zTYWdY26nV4l-dG25IC_0J5t2bYwI,8285
14
14
  dapla_metadata/datasets/model_validation.py,sha256=6qqq1ueTWRWBPTwEGJD49Pv7ksMEaq0iDtuOXelaw-s,7223
@@ -23,7 +23,8 @@ dapla_metadata/datasets/external_sources/external_sources.py,sha256=9eIcOIUbaodN
23
23
  dapla_metadata/datasets/utility/__init__.py,sha256=pp6tUcgUbo8iq9OPtFKQrTbLuI3uY7NHptwWSTpasOU,33
24
24
  dapla_metadata/datasets/utility/constants.py,sha256=YKsn6GfNIkwLoBp0yq209o0TbsEhsA_jGaZLVR984JU,2933
25
25
  dapla_metadata/datasets/utility/enums.py,sha256=i6dcxWya5k4LjLdGGIM_H37rRndizug3peaAgoE5UdM,652
26
- dapla_metadata/datasets/utility/utils.py,sha256=Enlmhj1BA7C9Im1ju3EwS6_kV1cpT53wb2cCtBGs_lI,20145
26
+ dapla_metadata/datasets/utility/urn.py,sha256=UfiQZf49zbrqRwBzD9yUgfwi6sXRl3KhS9seKhhYuUs,3896
27
+ dapla_metadata/datasets/utility/utils.py,sha256=q76UJI8W4j2aHSq1jz_AfYnJmLfygEflgUrQpqQEPnY,20157
27
28
  dapla_metadata/standards/__init__.py,sha256=n8jnMrudLuScSdfQ4UMJorc-Ptg3Y1-ilT8zAaQnM70,179
28
29
  dapla_metadata/standards/name_validator.py,sha256=6-DQE_EKVd6UjL--EXpFcZDQtusVbSFaWaUY-CfOV2c,9184
29
30
  dapla_metadata/standards/standard_validators.py,sha256=tcCiCI76wUVtMzXA2oCgdauZc0uGgUi11FKu-t7KGwQ,3767
@@ -90,7 +91,7 @@ dapla_metadata/variable_definitions/_utils/constants.py,sha256=zr5FNVCEz6TM9PVEr
90
91
  dapla_metadata/variable_definitions/_utils/files.py,sha256=JbPgPNQ7iA38juMqGEdcg5OjZZUwCb6NQtPL0AEspD0,10933
91
92
  dapla_metadata/variable_definitions/_utils/template_files.py,sha256=7fcc7yEHOl5JUZ698kqj4IiikXPHBi3SrAVOk4wqQtw,3308
92
93
  dapla_metadata/variable_definitions/_utils/variable_definition_files.py,sha256=sGhcSpckR9NtYGNh2oVkiCd5SI3bbJEBhc1PA2uShs0,4701
93
- dapla_toolbelt_metadata-0.9.4.dist-info/METADATA,sha256=xJyJK0IwI1cbzZyCNPNnBnGEAjHcwcwtjMPMt_MysrM,4723
94
- dapla_toolbelt_metadata-0.9.4.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
95
- dapla_toolbelt_metadata-0.9.4.dist-info/licenses/LICENSE,sha256=np3IfD5m0ZUofn_kVzDZqliozuiO6wrktw3LRPjyEiI,1073
96
- dapla_toolbelt_metadata-0.9.4.dist-info/RECORD,,
94
+ dapla_toolbelt_metadata-0.9.5.dist-info/METADATA,sha256=tS5t2BEedPZXNfVIp1fkBPF6hCEub3w2G8nv8UsDoY4,4723
95
+ dapla_toolbelt_metadata-0.9.5.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
96
+ dapla_toolbelt_metadata-0.9.5.dist-info/licenses/LICENSE,sha256=np3IfD5m0ZUofn_kVzDZqliozuiO6wrktw3LRPjyEiI,1073
97
+ dapla_toolbelt_metadata-0.9.5.dist-info/RECORD,,