Resolve merge conflict

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "ssb-datadoc"
-version = "0.8.3"
+version = "0.9.0"
 description = "Document dataset metadata. For use in Statistics Norway's metadata system."
 authors = ["Statistics Norway <[email protected]>"]
 license = "MIT"

src/datadoc/assets/workspace_style.css

@@ -81,3 +81,7 @@
 .form-check{
     padding-left: 0;
 }
+
+label.form-check-label{
+    padding-left: 0.5rem;
+}

src/datadoc/backend/dapla_dataset_path_info.py

@@ -292,26 +292,21 @@ def __init__(self, dataset_path: str | os.PathLike[str]) -> None:
         self._period_strings = self._extract_period_strings(self.dataset_name_sections)
 
     @staticmethod
-    def _extract_period_strings(dataset_name_sections: list[str]) -> list[str]:
-        """Extract period strings from dataset name sections.
-
-        Iterates over the dataset name sections and returns a list of strings
-        that match the year regex, stripping the first character. This extracts
-        the year periods from the dataset name.
+    def _get_period_string_indices(dataset_name_sections: list[str]) -> list[int]:
+        """Get all the indices at which period strings are found.
 
         Examples:
-        >>> DaplaDatasetPathInfo._extract_period_strings(['p2022', 'kommune', 'v1'])
-        ['2022']
+        >>> DaplaDatasetPathInfo._get_period_string_indices(['kommune', 'p2022', 'v1'])
+        [1]
 
-        >>> DaplaDatasetPathInfo._extract_period_strings(['p2022-01', 'p2023-06', 'kommune', 'v1'])
-        ['2022-01', '2023-06']
+        >>> DaplaDatasetPathInfo._get_period_string_indices(['kommune', 'p2022-01', 'p2023-06', 'v1'])
+        [1, 2]
 
-        >>> DaplaDatasetPathInfo._extract_period_strings(['p1990Q1', 'kommune', 'v1'])
-        ['1990Q1']
+        >>> DaplaDatasetPathInfo._get_period_string_indices(['kommune', 'p1990Q1', 'v1'])
+        [1]
 
-        >>> DaplaDatasetPathInfo._extract_period_strings(['varehandel','v1']) # No date will return empty string
+        >>> DaplaDatasetPathInfo._get_period_string_indices(['varehandel','v1'])
         []
-
         """
 
         def insert_p(regex: str) -> str:
@@ -324,14 +319,43 @@ def insert_p(regex: str) -> str:
             return regex[:1] + "p" + regex[1:]
 
         return [
-            x[1:]
-            for x in dataset_name_sections
+            i
+            for i, x in enumerate(dataset_name_sections)
             if any(
                 re.match(insert_p(date_format.regex_pattern), x)
                 for date_format in SUPPORTED_DATE_FORMATS
             )
         ]
 
+    @staticmethod
+    def _extract_period_strings(dataset_name_sections: list[str]) -> list[str]:
+        """Extract period strings from dataset name sections.
+
+        Iterates over the dataset name sections and returns a list of strings
+        that match the year regex, stripping the first character. This extracts
+        the year periods from the dataset name.
+
+        Examples:
+        >>> DaplaDatasetPathInfo._extract_period_strings(['p2022', 'kommune', 'v1'])
+        ['2022']
+
+        >>> DaplaDatasetPathInfo._extract_period_strings(['p2022-01', 'p2023-06', 'kommune', 'v1'])
+        ['2022-01', '2023-06']
+
+        >>> DaplaDatasetPathInfo._extract_period_strings(['p1990Q1', 'kommune', 'v1'])
+        ['1990Q1']
+
+        >>> DaplaDatasetPathInfo._extract_period_strings(['varehandel','v1'])
+        []
+
+        """
+        return [
+            dataset_name_sections[i][1:]
+            for i in DaplaDatasetPathInfo._get_period_string_indices(
+                dataset_name_sections,
+            )
+        ]
+
     def _extract_period_string_from_index(self, index: int) -> str | None:
         try:
             return self._period_strings[index]
@@ -347,6 +371,38 @@ def _extract_norwegian_dataset_state_path_part(
         ).lower()
         return {norwegian_dataset_state_path_part.replace(" ", x) for x in ["-", "_"]}
 
+    @property
+    def dataset_short_name(
+        self,
+    ) -> str | None:
+        """Extract the dataset short name from the filepath.
+
+        The dataset short name is defined as the first section of the stem, up to the period information,
+        or the version information if no period information is present.
+
+        Examples:
+        >>> DaplaDatasetPathInfo('prosjekt/befolkning/klargjorte_data/person_data_v1.parquet').dataset_short_name
+        person_data
+        >>> DaplaDatasetPathInfo('befolkning/inndata/sykepenger_p2022Q1_p2022Q2_v23.parquet').dataset_short_name
+        sykepenger
+        >>> DaplaDatasetPathInfo('my_data/simple_dataset_name.parquet').dataset_short_name
+        simple_dataset_name
+        """
+        if self.contains_data_from or self.contains_data_until:
+            short_name_sections = self.dataset_name_sections[
+                : min(
+                    DaplaDatasetPathInfo._get_period_string_indices(
+                        self.dataset_name_sections,
+                    ),
+                )
+            ]
+        elif self.dataset_version:
+            short_name_sections = self.dataset_name_sections[:-1]
+        else:
+            short_name_sections = self.dataset_name_sections
+
+        return "_".join(short_name_sections)
+
     @property
     def contains_data_from(self) -> datetime.date | None:
         """The earliest date from which data in the dataset is relevant for."""

src/datadoc/backend/datadoc_metadata.py

@@ -53,7 +53,6 @@ def __init__(
         self.metadata_document: pathlib.Path | CloudPath | None = None
         self.container: model.MetadataContainer | None = None
         self.dataset_path: pathlib.Path | CloudPath | None = None
-        self.short_name: str | None = None
         self.dataset = model.Dataset()
         self.variables: list = []
         self.variables_lookup: dict[str, model.Variable] = {}
@@ -176,7 +175,7 @@ def extract_metadata_from_dataset(
         )
 
         self.dataset = model.Dataset(
-            short_name=self.dataset_path.stem if self.dataset_path else None,
+            short_name=dapla_dataset_path_info.dataset_short_name,
             dataset_state=dapla_dataset_path_info.dataset_state,
             dataset_status=DataSetStatus.DRAFT,
             assessment=self.get_assessment_by_state(
@@ -185,7 +184,7 @@ def extract_metadata_from_dataset(
             version=dapla_dataset_path_info.dataset_version,
             contains_data_from=str(dapla_dataset_path_info.contains_data_from),
             contains_data_until=str(dapla_dataset_path_info.contains_data_until),
-            data_source_path=self.dataset_path,
+            file_path=str(self.dataset_path),
             metadata_created_by=user_info.get_user_info_for_current_platform().short_email,
             # TODO @mmwinther: Remove multiple_language_support once the model is updated.
             # https://github.com/statisticsnorway/ssb-datadoc-model/issues/41

src/datadoc/frontend/callbacks/register_callbacks.py

@@ -25,9 +25,8 @@
 from datadoc.frontend.callbacks.utils import update_global_language_state
 from datadoc.frontend.callbacks.variables import accept_variable_metadata_date_input
 from datadoc.frontend.callbacks.variables import accept_variable_metadata_input
+from datadoc.frontend.callbacks.variables import populate_variables_workspace
 from datadoc.frontend.components.builders import build_dataset_edit_section
-from datadoc.frontend.components.builders import build_edit_section
-from datadoc.frontend.components.builders import build_ssb_accordion
 from datadoc.frontend.components.dataset_tab import SECTION_WRAPPER_ID
 from datadoc.frontend.components.variables_tab import ACCORDION_WRAPPER_ID
 from datadoc.frontend.components.variables_tab import VARIABLES_INFORMATION_ID
@@ -39,8 +38,6 @@
 from datadoc.frontend.fields.display_dataset import OBLIGATORY_EDITABLE_DATASET_METADATA
 from datadoc.frontend.fields.display_dataset import OPTIONAL_DATASET_METADATA
 from datadoc.frontend.fields.display_dataset import DatasetIdentifiers
-from datadoc.frontend.fields.display_variables import OBLIGATORY_VARIABLES_METADATA
-from datadoc.frontend.fields.display_variables import OPTIONAL_VARIABLES_METADATA
 from datadoc.frontend.fields.display_variables import VariableIdentifiers
 
 if TYPE_CHECKING:
@@ -143,39 +140,24 @@ def callback_populate_variables_info_section(
     @app.callback(
         Output(ACCORDION_WRAPPER_ID, "children"),
         Input("language-dropdown", "value"),
+        Input("search-variables", "value"),
         prevent_initial_call=True,
     )
     def callback_populate_variables_workspace(
         language: str,
+        search_query: str,
     ) -> list:
-        """Create variable workspace with accordions for variables."""
+        """Create variable workspace with accordions for variables.
+
+        Allows for filtering which variables are displayed via the search box.
+        """
         update_global_language_state(SupportedLanguages(language))
-        logger.info("Populating new variables workspace")
-        return [
-            build_ssb_accordion(
-                variable.short_name,
-                {
-                    "type": "variables-accordion",
-                    "id": f"{variable.short_name}-{language}",  # Insert language into the ID to invalidate browser caches
-                },
-                variable.short_name,
-                children=[
-                    build_edit_section(
-                        OBLIGATORY_VARIABLES_METADATA,
-                        "Obligatorisk",
-                        variable,
-                        state.current_metadata_language.value,
-                    ),
-                    build_edit_section(
-                        OPTIONAL_VARIABLES_METADATA,
-                        "Anbefalt",
-                        variable,
-                        state.current_metadata_language.value,
-                    ),
-                ],
-            )
-            for variable in list(state.metadata.variables)
-        ]
+        logger.debug("Populating variables workspace. Search query: %s", search_query)
+        return populate_variables_workspace(
+            state.metadata.variables,
+            state.current_metadata_language,
+            search_query,
+        )
 
     @app.callback(
         Output(SECTION_WRAPPER_ID, "children"),
@@ -189,7 +171,7 @@ def callback_populate_dataset_workspace(
     ) -> list:
         """Create dataset workspace with sections."""
         update_global_language_state(SupportedLanguages(language))
-        logger.info("Populating new dataset workspace")
+        logger.debug("Populating dataset workspace")
         if n_clicks:
             return [
                 build_dataset_edit_section(

src/datadoc/frontend/callbacks/variables.py

@@ -11,17 +11,61 @@
 from datadoc.frontend.callbacks.utils import MetadataInputTypes
 from datadoc.frontend.callbacks.utils import find_existing_language_string
 from datadoc.frontend.callbacks.utils import parse_and_validate_dates
+from datadoc.frontend.components.builders import build_edit_section
+from datadoc.frontend.components.builders import build_ssb_accordion
 from datadoc.frontend.fields.display_variables import (
     MULTIPLE_LANGUAGE_VARIABLES_METADATA,
 )
+from datadoc.frontend.fields.display_variables import OBLIGATORY_VARIABLES_METADATA
+from datadoc.frontend.fields.display_variables import OPTIONAL_VARIABLES_METADATA
 from datadoc.frontend.fields.display_variables import VariableIdentifiers
 
 if TYPE_CHECKING:
+    from datadoc_model import model
     from datadoc_model.model import LanguageStringType
 
+    from datadoc.enums import SupportedLanguages
+
 logger = logging.getLogger(__name__)
 
 
+def populate_variables_workspace(
+    variables: list[model.Variable],
+    language: SupportedLanguages,
+    search_query: str,
+) -> list:
+    """Create variable workspace with accordions for variables.
+
+    Allows for filtering which variables are displayed via the search box.
+    """
+    return [
+        build_ssb_accordion(
+            variable.short_name or "",
+            {
+                "type": "variables-accordion",
+                "id": f"{variable.short_name}-{language.value}",  # Insert language into the ID to invalidate browser caches
+            },
+            variable.short_name or "",
+            children=[
+                build_edit_section(
+                    OBLIGATORY_VARIABLES_METADATA,
+                    "Obligatorisk",
+                    variable,
+                    language.value,
+                ),
+                build_edit_section(
+                    OPTIONAL_VARIABLES_METADATA,
+                    "Anbefalt",
+                    variable,
+                    language.value,
+                ),
+            ],
+        )
+        for variable in variables
+        if search_query in (variable.short_name or "")
+    ]
+
+
 def handle_multi_language_metadata(
     metadata_field: str,
     new_value: MetadataInputTypes | LanguageStringType,

src/datadoc/frontend/components/variables_tab.py

@@ -36,8 +36,8 @@ def build_variables_tab() -> dbc.Tab:
                         ssb.Input(
                             label="Søk i variabler",
                             searchField=True,
-                            disabled=True,
-                            placeholder="Kommer...",
+                            disabled=False,
+                            placeholder="Variabel kortnavn...",
                             id="search-variables",
                             n_submit=0,
                             value="",

src/datadoc/frontend/fields/display_base.py

@@ -10,7 +10,6 @@
 from typing import TYPE_CHECKING
 from typing import Any
 
-import dash_bootstrap_components as dbc
 import ssb_dash_components as ssb
 from dash import dcc
 
@@ -228,16 +227,16 @@ def render(
         variable_id: dict,
         language: str,  # noqa: ARG002 Required by Dash
         variable: model.Variable,
-    ) -> dbc.Checkbox:
+    ) -> ssb.Checkbox:
         """Build Checkbox component."""
         value = self.value_getter(variable, self.identifier)
-        return dbc.Checkbox(
+        return ssb.Checkbox(
             label=self.display_name,
             id=variable_id,
             disabled=not self.editable,
-            label_class_name="ssb-checkbox checkbox-label",
-            class_name="ssb-checkbox",
             value=value,
+            showDescription=True,
+            description=self.description,
         )
 
 

src/datadoc/frontend/fields/display_dataset.py

@@ -256,6 +256,7 @@ class DatasetIdentifiers(str, Enum):
         description="Filstien inneholder datasettets navn og stien til hvor det er lagret.",
         obligatory=True,
         editable=False,
+        value_getter=get_metadata_and_stringify,
     ),
     DatasetIdentifiers.METADATA_CREATED_DATE: MetadataInputField(
         identifier=DatasetIdentifiers.METADATA_CREATED_DATE.value,

src/datadoc/frontend/fields/display_variables.py

@@ -89,7 +89,7 @@ class VariableIdentifiers(str, Enum):
     VariableIdentifiers.DIRECT_PERSON_IDENTIFYING: MetadataCheckboxField(
         identifier=VariableIdentifiers.DIRECT_PERSON_IDENTIFYING.value,
         display_name="Direkte personidentifiserende informasjon",
-        description="Direkte personidentifiserende informasjon (DPI)",
+        description="Velges hvis variabelen inneholder informasjon som innebærer at enkeltpersoner kan identifiseres. Gjelder ikke hvis kolonnen er pseudonymisert eller anonymisert.",
         obligatory=True,
     ),
     VariableIdentifiers.DATA_SOURCE: MetadataInputField(

tests/backend/test_datadoc_metadata.py

@@ -177,6 +177,14 @@ def test_existing_metadata_valid_id(
     assert post_write_id == pre_open_id
 
 
+def test_dataset_short_name(metadata: DataDocMetadata):
+    assert metadata.dataset.short_name == "person_data"
+
+
+def test_dataset_file_path(metadata: DataDocMetadata):
+    assert metadata.dataset.file_path == str(metadata.dataset_path)
+
+
 def test_variable_role_default_value(metadata: DataDocMetadata):
     assert all(
         v.variable_role == VariableRole.MEASURE.value for v in metadata.variables