Skip to content

input4mips_validation.cvs#

Sub-package Description
activity_id Activity ID CV handling
author Definition of an author of a dataset.
cvs Data model of the controlled vocabularies (CVs)
drs Data reference syntax data model
exceptions Exceptions related to CVs
institution_id Institution ID CV handling
license License CV handling
loading Loading of CVs from a given source
loading_raw Tools for loading the raw CVs
source_id Source ID CV handling

input4mips_validation.cvs #

Controlled vocabularies (CVs) handling

Input4MIPsCVs #

Data model of input4MIPs' CVs

Source code in src/input4mips_validation/cvs/cvs.py 
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 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
169
@define
class Input4MIPsCVs:
    """
    Data model of input4MIPs' CVs
    """

    raw_loader: RawCVLoader
    """Object used to load the raw CVs"""

    DRS: DataReferenceSyntax
    """Data reference syntax used with these CVs"""
    # TODO: validation - check that all bits of the DRS
    #       are known in the metadata universe
    #        e.g. are required fields of files or something
    #        (may have to maintain list of 'known stuff' by hand).

    activity_id_entries: ActivityIDEntries
    """Activity ID entries"""

    # dataset_categories: tuple[str, ...]
    # """Recognised dataset categories"""
    # Would make sense for this to actually be entries,
    # and to specify the variables in each category here
    # No other validation applied

    institution_ids: tuple[str, ...]
    """Recognised institution IDs"""
    # TODO: check these against the global CVs when validating

    license_entries: LicenseEntries
    """License entries"""

    # mip_eras: tuple[str, ...]
    # """Recognised MIP eras"""
    # These should be linked back to the global CVs somehow
    # (probably as part of validation)

    # products: ProductEntries
    # """Recognised product types"""
    # These should be linked back to the global CVs somehow I assume (?)
    # (probably as part of validation)

    # publication_statuses: PublicationStatusEntries
    # """Recognised publication statuses"""
    # These should be linked back to the global CVs somehow I assume (?)
    # (probably as part of validation)

    # required_global_attribute: tuple[str, ...]
    # """Global attributes required in input4MIPs files"""
    # Would be nice if these were entries and hence we could get descriptions
    # of the meanins of the fields/link back to global CVs.
    # Might be easy with JSON-LD.

    source_id_entries: SourceIDEntries
    """Source ID entries"""

    # target_mip_entries: TargetMIPEntries
    # """Target MIP entries"""
    # These should be linked back to the global CVs somehow I assume (?)
    # (probably as part of validation)

    # tracking_id_regexp: str | regexp
    # """Regular expression which files' tracking IDs must match"""
    def validate_activity_id(self, value: str) -> None:
        """
        Validate that a value of activity ID is valid

        Parameters
        ----------
        value
            Value to validate

        Raises
        ------
        ValueNotAllowedByCVsError
            The provided value is not allowed by the CVs
        """
        if value not in self.activity_id_entries.activity_ids:
            raise ValueNotAllowedByCVsError(
                value=value,
                cv_component="activity_id",
                cv_allowed_values=self.activity_id_entries.activity_ids,
                cv_entries=self.activity_id_entries.entries,
            )

    def validate_contact(self, value: str, source_id: str) -> None:
        """
        Validate that a value of contact is valid

        Parameters
        ----------
        value
            Value to validate

        source_id
            Source ID value

            This is required because the source ID defines
            what the expected value of contact is.

        Raises
        ------
        ValueInconsistentWithCVsError
            The provided value is not the correct value according to the CVs
            and the value of `source_id`.
        """
        cv_source_id_entry = self.source_id_entries[source_id]
        expected_value = cv_source_id_entry.values.contact

        if value != expected_value:
            raise ValueInconsistentWithCVsError(
                value=value,
                expected_value=expected_value,
                cv_component="contact",
                cv_component_dependent_on="source_id",
                cv_entry_dependenty_component=cv_source_id_entry,
            )

    def validate_source_version(self, value: str, source_id: str) -> None:
        """
        Validate that a value of source version is valid

        Parameters
        ----------
        value
            Value to validate

        source_id
            Source ID value

            This is required because the source ID defines
            what the expected value of source_version is.

        Raises
        ------
        ValueInconsistentWithCVsError
            The provided value is not the correct value according to the CVs
            and the value of `source_id`.
        """
        cv_source_id_entry = self.source_id_entries[source_id]
        expected_value = cv_source_id_entry.values.source_version

        if value != expected_value:
            raise ValueInconsistentWithCVsError(
                value=value,
                expected_value=expected_value,
                cv_component="source_version",
                cv_component_dependent_on="source_id",
                cv_entry_dependenty_component=cv_source_id_entry,
            )

DRS: DataReferenceSyntax instance-attribute #

Data reference syntax used with these CVs

activity_id_entries: ActivityIDEntries instance-attribute #

Activity ID entries

institution_ids: tuple[str, ...] instance-attribute #

Recognised institution IDs

license_entries: LicenseEntries instance-attribute #

License entries

raw_loader: RawCVLoader instance-attribute #

Object used to load the raw CVs

source_id_entries: SourceIDEntries instance-attribute #

Source ID entries

validate_activity_id(value) #

Validate that a value of activity ID is valid

Parameters:

Name Type Description Default
value str

Value to validate

 required

Raises:

Type Description
ValueNotAllowedByCVsError

The provided value is not allowed by the CVs
Source code in src/input4mips_validation/cvs/cvs.py 
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
def validate_activity_id(self, value: str) -> None:
    """
    Validate that a value of activity ID is valid

    Parameters
    ----------
    value
        Value to validate

    Raises
    ------
    ValueNotAllowedByCVsError
        The provided value is not allowed by the CVs
    """
    if value not in self.activity_id_entries.activity_ids:
        raise ValueNotAllowedByCVsError(
            value=value,
            cv_component="activity_id",
            cv_allowed_values=self.activity_id_entries.activity_ids,
            cv_entries=self.activity_id_entries.entries,
        )

validate_contact(value, source_id) #

Validate that a value of contact is valid

Parameters:

Name Type Description Default
value str

Value to validate

 required
source_id str

Source ID value

This is required because the source ID defines what the expected value of contact is.

 required

Raises:

Type Description
ValueInconsistentWithCVsError

The provided value is not the correct value according to the CVs and the value of source_id.
Source code in src/input4mips_validation/cvs/cvs.py 
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
def validate_contact(self, value: str, source_id: str) -> None:
    """
    Validate that a value of contact is valid

    Parameters
    ----------
    value
        Value to validate

    source_id
        Source ID value

        This is required because the source ID defines
        what the expected value of contact is.

    Raises
    ------
    ValueInconsistentWithCVsError
        The provided value is not the correct value according to the CVs
        and the value of `source_id`.
    """
    cv_source_id_entry = self.source_id_entries[source_id]
    expected_value = cv_source_id_entry.values.contact

    if value != expected_value:
        raise ValueInconsistentWithCVsError(
            value=value,
            expected_value=expected_value,
            cv_component="contact",
            cv_component_dependent_on="source_id",
            cv_entry_dependenty_component=cv_source_id_entry,
        )

validate_source_version(value, source_id) #

Validate that a value of source version is valid

Parameters:

Name Type Description Default
value str

Value to validate

 required
source_id str

Source ID value

This is required because the source ID defines what the expected value of source_version is.

 required

Raises:

Type Description
ValueInconsistentWithCVsError

The provided value is not the correct value according to the CVs and the value of source_id.
Source code in src/input4mips_validation/cvs/cvs.py 
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
169
def validate_source_version(self, value: str, source_id: str) -> None:
    """
    Validate that a value of source version is valid

    Parameters
    ----------
    value
        Value to validate

    source_id
        Source ID value

        This is required because the source ID defines
        what the expected value of source_version is.

    Raises
    ------
    ValueInconsistentWithCVsError
        The provided value is not the correct value according to the CVs
        and the value of `source_id`.
    """
    cv_source_id_entry = self.source_id_entries[source_id]
    expected_value = cv_source_id_entry.values.source_version

    if value != expected_value:
        raise ValueInconsistentWithCVsError(
            value=value,
            expected_value=expected_value,
            cv_component="source_version",
            cv_component_dependent_on="source_id",
            cv_entry_dependenty_component=cv_source_id_entry,
        )

load_cvs(cv_source=None, **kwargs) #

Load CVs

Parameters:

Name Type Description Default
cv_source None | str | Path

String identifying the source of the CVs.

For full details of possible options, see get_raw_cvs_loader.

 None
kwargs Any

Passed through to get_raw_cvs_loader.

 {}

Returns:

Type Description
Input4MIPsCVs

Loaded CVs
Source code in src/input4mips_validation/cvs/loading.py 
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
def load_cvs(
    cv_source: None | str | Path = None,
    **kwargs: Any,
) -> Input4MIPsCVs:
    """
    Load CVs

    Parameters
    ----------
    cv_source
        String identifying the source of the CVs.

        For full details of possible options, see
        [`get_raw_cvs_loader`][input4mips_validation.cvs.loading_raw.get_raw_cvs_loader].

    kwargs
        Passed through to
        [`get_raw_cvs_loader`][input4mips_validation.cvs.loading_raw.get_raw_cvs_loader].

    Returns
    -------
    :
        Loaded CVs
    """
    raw_cvs_loader = get_raw_cvs_loader(cv_source=cv_source)
    logger.debug(f"{raw_cvs_loader=}")

    return load_cvs_known_loader(raw_cvs_loader=raw_cvs_loader)