ssb-klass-python 1.0.6__tar.gz → 1.0.7__tar.gz

{ssb_klass_python-1.0.6 → ssb_klass_python-1.0.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ssb-klass-python
-Version: 1.0.6
+Version: 1.0.7
 Summary: A Python package built on top of KLASS's API for retrieving classifications, codes, correspondences etc.
 License-Expression: MIT
 License-File: LICENSE
@@ -17,6 +17,7 @@ Classifier: Programming Language :: Python :: 3.14
 Requires-Dist: ipython (<9)
 Requires-Dist: ipywidgets (>=8.0.6)
 Requires-Dist: pandas (>=1.5.3)
+Requires-Dist: pyarrow (>=10.0.1)
 Requires-Dist: python-dateutil (>=2.8.2)
 Requires-Dist: requests (>=2.31.0)
 Requires-Dist: toml (>=0.10.2)

{ssb_klass_python-1.0.6 → ssb_klass_python-1.0.7}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "ssb-klass-python"
-version = "1.0.6"
+version = "1.0.7"
 description = "A Python package built on top of KLASS's API for retrieving classifications, codes, correspondences etc."
 authors = [{name="Carl Corneil", email="ssb-pythonistas <ssb-pythonistas@ssb.no>"}, {name = "Statistics Norway" }]
 license = "MIT"
@@ -12,10 +12,10 @@ dependencies = [
     "toml >=0.10.2",
     "ipywidgets >=8.0.6",
     "pandas >=1.5.3",
+    "pyarrow >=10.0.1",
     "requests >=2.31.0",
     "ipython <9",
     "typing-extensions >=4.12.2",
-
 ]
 
 [project.urls]
@@ -38,7 +38,7 @@ Changelog = "https://github.com/statisticsnorway/ssb-klass-python/releases"
 pygments = ">=2.10.0"
 black = { extras = ["jupyter"], version = ">=24.3.0" }
 coverage = { extras = ["toml"], version = ">=6.2" }
-darglint = {version= ">=1.8.1", python = ">=3.10, <4.0"}
+pydoclint = ">=0.8.3"
 furo = ">=2021.11.12"
 mypy = ">=0.930"
 ipykernel = ">=6.15.3"
@@ -127,6 +127,7 @@ ignore = [
     "ANN202", # Don't requiere return type annotation for private functions.
     "ANN401", # Allow type annotation with type Any.
     "D100",   # Supress undocumented-public-module. Only doc of public api required.
+    "D107",   # We are of the opinion that inits dont need a docstring, when the class has one...
     "E402",   # Supress module-import-not-at-top-of-file, needed in jupyter notebooks.
     "E501",   # Supress line-too-long warnings: trust black's judgement on this one.
 ]
@@ -167,6 +168,11 @@ classmethod-decorators = [
 ]
 "demo/*.py" = ["B018"] # Ignore the useless expressions in the notebooks
 
+[tool.pydoclint]
+style = "google"
+arg-type-hints-in-docstring = false
+native-mode-noqa-location = "definition"
+
 [build-system]
 requires = ["poetry-core>=1.0.0"]
 build-backend = "poetry.core.masonry.api"

{ssb_klass_python-1.0.6 → ssb_klass_python-1.0.7}/src/klass/classes/classification.py

@@ -33,33 +33,10 @@ class KlassClassification:
     you first need to get the classification at a specific time (a KlassVersion)
     by using get_version() for example.
 
-    Attributes:
-        versions (list): A list of the data the Classifications has on its versions.
-            Versions represent the changes to the classifications codelists placed in time.
-        name (str): The name of the classification.
-        classification_id (str): The ID of the classification.
-        classificationType (str): The type of the classification.
-        lastModified (str): The last time the classification was modified. ISO-stringified datetime(ISO-datetime)
-        description (str): A longer description of the classification.
-        primaryLanguage (str): The primary language of the classification. "nb", "nn" or "en".
-        language (str): The language chosen at initialization of the classification. "nb", "nn" or "en".
-        copyrighted (bool): Whether the classification is copyrighted.
-        includeShortName (bool): If true, indicates that classificationItems may have shortnames.
-        includeNotes (bool): If true, indicates that classificationItems may have notes.
-        contactPerson (dict): A dictionary containing the contact person of the classification.
-        owningSection (str): The section (part of Statistics Norway)that owns the classification.
-        statisticalUnits (list): Statistical units assigned to classification
-        include_future (bool): Whether to include future versions of the classification.
-        _links (dict): A dictionary containing the links to different possible endpoints using the classification.
-
     Args:
         classification_id: The classification_id of the classification. For example: '36'
         language: The language of the classification. "nb", "nn" or "en".
         include_future: Whether to include future versions of the classification.
-
-    Raises:
-        ValueError: If the language is not "no", "nb" or "en".
-            If the include_future is not a bool.
     """
 
     def __init__(
@@ -68,7 +45,6 @@ class KlassClassification:
         language: Language = "nb",
         include_future: bool = False,
     ) -> None:
-        """Get the data for the classification from the API."""
         self.classification_id = classification_id
         self.language: Language = language
         self.include_future = include_future
@@ -163,7 +139,7 @@ class KlassClassification:
         """Reformats the versions into a simple dict with just the IDs as keys and names as values.
 
         Returns:
-            dict: Version IDs as keys, and version names as values.
+            dict[int, str]: Version IDs as keys, and version names as values.
         """
         return {v["version_id"]: v["name"] for v in self.versions[::-1]}
 

{ssb_klass_python-1.0.6 → ssb_klass_python-1.0.7}/src/klass/classes/codes.py

@@ -7,6 +7,8 @@ from typing_extensions import Self
 from ..requests.klass_requests import codes
 from ..requests.klass_requests import codes_at
 from ..requests.klass_types import Language
+from ..utility.filters import apply_presentation_name_fallback
+from ..utility.filters import limit_na_level
 
 
 class KlassCodes:
@@ -14,12 +16,6 @@ class KlassCodes:
 
     The codelist is owned by the Classification through a Version, and will be valid for a time period.
 
-    Attributes:
-        data (pd.DataFrame): The pandas DataFrame of the codes.
-        classification_id (str): The classification ID.
-        from_date (str): The start date of the time period. "YYYY-MM-DD".
-        to_date (str): The end date of the time period. "YYYY-MM-DD".
-
     Args:
         classification_id: The classification ID.
         from_date: The start date of the time period. "YYYY-MM-DD".
@@ -29,14 +25,6 @@ class KlassCodes:
         presentation_name_pattern: A pattern for filtering the code names.
         language: The language of the code names. Defaults to "nb".
         include_future: Whether to include future codes. Defaults to False.
-
-    Raises:
-        ValueError: If from_date or to_date is not a valid date or date-string YYYY-MM-DD.
-        ValueError: If select_codes contains anything except numbers and the special characters "*" (star) or "-" (dash).
-        ValueError: If select_level is anything except a whole number.
-        ValueError: If presentation_name_pattern is not a valid pattern.
-        ValueError: If language is not "nb", "nn" or "en".
-        ValueError: If include_future is not a bool.
     """
 
     def __init__(
@@ -50,7 +38,6 @@ class KlassCodes:
         language: Language = "nb",
         include_future: bool = False,
     ) -> None:
-        """Get the data from the KLASS-api belonging to the code-list."""
         self.classification_id = classification_id
         if not from_date:
             from_date = datetime.now().strftime("%Y-%m-%d")
@@ -110,7 +97,7 @@ class KlassCodes:
             include_future: Whether to include future codes.
 
         Returns:
-            self (KlassSearchFamilies): Returns self to make the method more easily chainable.
+            Self: Returns self to make the method more easily chainable.
         """
         if not from_date:
             from_date = datetime.now().strftime("%Y-%m-%d")
@@ -132,7 +119,7 @@ class KlassCodes:
             raise_on_empty_data: Whether to raise an error if the returned dataframe is empty. Defaults to True.
 
         Returns:
-            self (KlassSearchFamilies): Returns self to make the method more easily chainable.
+            Self: Returns self to make the method more easily chainable.
 
         Raises:
             ValueError: If the returned dataframe is empty, there is probably something too narrow in the parameters.
@@ -169,6 +156,8 @@ class KlassCodes:
         key: str = "code",
         value: str | None = None,  # default is "name" if not set
         other: str | None = None,
+        remove_na: bool = True,
+        select_level: int | None = None,
     ) -> dict[str, str] | defaultdict[str, str]:
         """Extract two columns from the data, turning them into a dict.
 
@@ -178,9 +167,11 @@ class KlassCodes:
             key: The name of the column with the values you want as keys.
             value: The name of the column with the values you want as values in your dict.
             other: If key is missing from dict, return this value instead, if you specify an OTHER-value.
+            remove_na: Set to False if you want to keep empty mappings over the key and value columns. Empty is defined as empty strings or NA-types.
+            select_level: Keep only a specific level defines the variants codes / groups.
 
         Returns:
-            dict | defaultdict: The extracted columns as a dict or defaultdict.
+            dict[str, str] | defaultdict[str, str]: The extracted columns as a dict or defaultdict.
         """
         if not value:
             # If you bothered specifying a pattern, we assume you want it
@@ -188,7 +179,9 @@ class KlassCodes:
                 value = "presentationName"
             else:
                 value = "name"
-        mapping = dict(zip(self.data[key], self.data[value], strict=False))
+        data, value_col = apply_presentation_name_fallback(self.data, value)
+        limit_data = limit_na_level(data, key, value_col, remove_na, select_level)
+        mapping = dict(zip(limit_data[key], limit_data[value_col], strict=False))
         if other:
             mapping = defaultdict(lambda: other, mapping)
         return mapping

{ssb_klass_python-1.0.6 → ssb_klass_python-1.0.7}/src/klass/classes/correspondence.py

@@ -12,6 +12,8 @@ from ..requests.klass_requests import corresponds
 from ..requests.klass_types import CorrespondsType
 from ..requests.klass_types import Language
 from ..requests.klass_types import T_correspondanceMaps
+from ..utility.filters import apply_presentation_name_fallback
+from ..utility.filters import limit_na_level
 
 
 class KlassCorrespondence:
@@ -23,19 +25,6 @@ class KlassCorrespondence:
     You can identify the correspondence by their individual ids,
     or by the source classification ID + the target classification ID + a specific time.
 
-    Attributes:
-        data (pd.DataFrame): The pandas DataFrame of the correspondences.
-        correspondence (list): The list of the correspondences returned by the API.
-        correspondence_id (str): The ID of the correspondence.
-        source_classification_id (str): The ID of the source classification.
-        target_classification_id (str): The ID of the target classification.
-        from_date (str): The start date of the correspondence.
-        to_date (str, optional): The end date of the correspondence.
-        contain_quarter (int): The number of quarters the correspondence should contain,
-            this replaces the to_date during initialization.
-        language (str): The language of the correspondence. "nb", "nn" or "en".
-        include_future (bool): If the correspondence should include future correspondences.
-
     Args:
         correspondence_id: The ID of the correspondence.
         source_classification_id: The ID of the source classification.
@@ -85,7 +74,6 @@ class KlassCorrespondence:
         language: Language = "nb",
         include_future: bool = False,
     ) -> None:
-        """Get the correspondence-data from the API."""
         self.correspondence_id = correspondence_id
         self.source_classification_id = source_classification_id
         self.target_classification_id = target_classification_id
@@ -136,7 +124,7 @@ class KlassCorrespondence:
         Gets and reshapes correspondences based on attributes on the class.
 
         Returns:
-            self (KlassCorrespondence): Returns self to make the method more easily chainable.
+            Self: Returns self to make the method more easily chainable.
 
         Raises:
             ValueError: If you are filling out the wrong combination of correspondence_id, source_classification_id,
@@ -194,7 +182,7 @@ class KlassCorrespondence:
         Uses the attribute "contain_quarter" to determine which quarter to use.
 
         Returns:
-            The last date of the quarter.
+            str: The last date of the quarter.
 
         Raises:
             ValueError: if from date is missing
@@ -234,19 +222,11 @@ class KlassCorrespondence:
             select_level: Keep only a specific level defines the variants codes / groups.
 
         Returns:
-            dict | defaultdict: The dictionary of the correspondence.
+            dict[str, str | None] | defaultdict[str, str | None]: The dictionary of the correspondence.
         """
-        limit_data = self.data
-        if remove_na:
-            limit_data = limit_data[
-                (limit_data[[key, value]].notna().all(axis=1))
-                | (limit_data[[key, value]].astype("string") == "")
-            ]
-        if select_level:
-            limit_data = limit_data[
-                limit_data["level"].astype("string[pyarrow]") == str(select_level)
-            ]
-        mapping = dict(zip(limit_data[key], limit_data[value], strict=False))
+        data, value_col = apply_presentation_name_fallback(self.data, value)
+        limit_data = limit_na_level(data, key, value_col, remove_na, select_level)
+        mapping = dict(zip(limit_data[key], limit_data[value_col], strict=False))
         if other:
             mapping = defaultdict(lambda: other, mapping)
         return mapping

{ssb_klass_python-1.0.6 → ssb_klass_python-1.0.7}/src/klass/classes/family.py

@@ -10,18 +10,11 @@ class KlassFamily:
     Families in Klass "own" / "have" several classifications.
     Families are owned by sections (a part of Statistics Norway who is responsible for the family).
 
-    Attributes:
-        classifications (list): A list of classifications in the family.
-        family_id (str): The ID of the family.
-        name (str): The name of the family.
-        _links (dict): A dictionary of API links referencing itself.
-
     Args:
         family_id: The ID of the family.
     """
 
     def __init__(self, family_id: str | int) -> None:
-        """Get the family data from the klass-api, setting it as attributes on the object."""
         self.family_id = family_id
         # Setting for mypy
         result: ClassificationFamiliesByIdType = classificationfamilies_by_id(

{ssb_klass_python-1.0.6 → ssb_klass_python-1.0.7}/src/klass/classes/search.py

@@ -12,13 +12,6 @@ from .family import KlassFamily
 class KlassSearchClassifications:
     """Use to search for classifications.
 
-    Attributes:
-        classifications (list): A list of KlassClassification objects.
-        query (str): The search query.
-        include_codelists (bool): Whether to include codelists in the search results.
-        ssbsection (str): The SSB section who owns the classification you are searching for.
-        no_dupes (bool): Whether to remove duplicates from the search results.
-
     Args:
         query: The search query.
         include_codelists: Whether to include codelists in the search results.
@@ -34,7 +27,6 @@ class KlassSearchClassifications:
         ssbsection: str = "",
         no_dupes: bool = False,
     ) -> None:
-        """Get data from the KLASS-api, setting it as attributes on this object."""
         self.query = query
         self.include_codelists = include_codelists
         self.ssbsection = ssbsection
@@ -79,7 +71,7 @@ class KlassSearchClassifications:
             no_dupes: Set to True if you want equal results to be filtered out.
 
         Returns:
-            list: The cleaned classifications.
+            list[ClassificationSearchResultsPartType]: The cleaned classifications.
         """
         classification_replace: list[ClassificationSearchResultsPartType] = []
         seen = []
@@ -172,7 +164,6 @@ class KlassSearchFamilies:
         include_codelists: bool = False,
         language: Language = "nb",
     ) -> None:
-        """Get data from the KLASS-api, setting it as attributes on this object."""
         self.ssbsection = ssbsection
         self.include_codelists = include_codelists
         self.language = language
@@ -205,7 +196,7 @@ class KlassSearchFamilies:
         attributes.
 
         Returns:
-            self (KlassSearchFamilies): Returns self to make the method more easily chainable.
+            Self: Returns self to make the method more easily chainable.
         """
         result = classificationfamilies(
             ssbsection=self.ssbsection,

{ssb_klass_python-1.0.6 → ssb_klass_python-1.0.7}/src/klass/classes/variant.py

@@ -8,6 +8,8 @@ from ..requests.klass_requests import variants_by_id
 from ..requests.klass_types import CorrespondenceTablesType
 from ..requests.klass_types import Language
 from ..requests.klass_types import VariantsByIdType
+from ..utility.filters import apply_presentation_name_fallback
+from ..utility.filters import limit_na_level
 
 
 class KlassVariant:
@@ -22,25 +24,6 @@ class KlassVariant:
     It sets a new upper level of codes (amount of study points),
     for a set of lower-level existing codes (NUS codes, level 5).
 
-    Attributes:
-        data (pd.DataFrame): The classificationItems as a pandas dataframe. Usually what you're after?
-        variant_id (str): The variant_id of the variant. For example: '36'.
-        name (str): The name of the variant.
-        contactPerson (dict): The contact person of the variant.
-        owningSection (str): The owning section of the variant.
-        lastModified (str): Stringified iso-datetime for last modification.
-        published (list[str]): Languages that the variant is published in.
-        validFrom (str): Date-string from when the version is valid.
-        validTo (str, optional): Date-string to when the version is valid.
-        introduction (str): A longer description of the variant.
-        correspondenceTables (list): The correspondence tables of the variant.
-        changelogs (list): The changelogs of the variant.
-        levels (list[dict]): The levels contained in the codelist (items).
-        classificationItems (list[dict]): The codelist-elements of the variant.
-        select_level (int): The level of the dataset to keep. For example: 0.
-        language (str): The language of the variant to select. For example: 'nb'.
-        _links (dict): The links returned from the API.
-
     Args:
         variant_id: The variant_id of the variant. For example: '1959'.
         select_level: The level of the dataset to keep. For example: 5.
@@ -53,7 +36,6 @@ class KlassVariant:
         select_level: int | None = None,
         language: Language = "nb",
     ) -> None:
-        """Get the data from the KLASS-api to populate this objects attributes."""
         self.variant_id = variant_id
         self.select_level = select_level
         self.language: Language = language
@@ -139,19 +121,11 @@ class KlassVariant:
             select_level: Usually you want level 2, not level 1, as level 1 just defines the variants codes / groups.
 
         Returns:
-            dict | defaultdict: The extracted columns as a dict or defaultdict.
+            dict[str, str] | defaultdict[str, str]: The extracted columns as a dict or defaultdict.
         """
-        limit_data = self.data
-        if remove_na:
-            limit_data = limit_data[
-                (limit_data[[key, value]].notna().all(axis=1))
-                | (limit_data[[key, value]].astype("string") == "")
-            ]
-        if select_level:
-            limit_data = limit_data[
-                limit_data["level"].astype("string[pyarrow]") == str(select_level)
-            ]
-        mapping = dict(zip(limit_data[key], limit_data[value], strict=False))
+        data, value_col = apply_presentation_name_fallback(self.data, value)
+        limit_data = limit_na_level(data, key, value_col, remove_na, select_level)
+        mapping = dict(zip(limit_data[key], limit_data[value_col], strict=False))
         if other:
             mapping = defaultdict(lambda: other, mapping)
         return mapping
@@ -170,20 +144,6 @@ class KlassVariantSearchByName(KlassVariant):
     It does not have to be extensive (all filled out), but can, for example,
     redefine upper levels, for some lower-level codes.
 
-    Attributes:
-        data (pd.DataFrame): The codelists from the Variant as a pandas dataframe. Usually what you're after?
-        classification_id (str): The classification ID.
-        variant_name (str): The start of the variant name.
-        from_date (str): The start of the date range.
-        to_date (str): The end of the date range.
-        select_codes (str): Limit the result to codes matching this pattern.
-            See rules: https://data.ssb.no/api/klass/v1/api-guide.html#_selectcodes
-        select_level (str): The level of codes to keep in the dataset.
-        presentation_name_pattern (str): Used to build an alternative presentation name for the codes.
-            See rules: https://data.ssb.no/api/klass/v1/api-guide.html#_presentationnamepattern
-        language (str): Language of the names, select "en", "nb" or "nn".
-        include_future (bool): Whether to include future codes. Defaults to False.
-
     Args:
         classification_id: The classification ID.
         variant_name: The start of the variant name.
@@ -210,7 +170,6 @@ class KlassVariantSearchByName(KlassVariant):
         language: Language = "nb",
         include_future: bool = False,
     ) -> None:
-        """Get the data from the KLASS-api, setting it as attributes on the object."""
         self.classification_id = classification_id
         self.variant_name = variant_name
         self.from_date = from_date

{ssb_klass_python-1.0.6 → ssb_klass_python-1.0.7}/src/klass/classes/version.py

@@ -16,21 +16,6 @@ class KlassVersion:
 
     For example, the ID of NUS valid in 2023 is 1954, while the ID of NUS without being time-specific is 36.
 
-    Attributes:
-        data (pd.DataFrame): The codelist of the classification-version as a pandas dataframe.
-        name (str): The name of the version.
-        validFrom (str): The date the version is valid from.
-        validTo (str): The date the version is valid to (if any).
-        lastModified (str): The date the version was last modified.
-        published (list): A list of languages that the version is published in.
-        introduction (str): A longer description of the version.
-        contactPerson (dict): A dictionary of the contact person of the version.
-        owningSection (str): The name of the section that owns the version.
-        legalBase (str): The basis in law for the classification.
-        publications (str): Where the classification is published (URL).
-        derivedFrom (str): Notes on where the classification was derived from.
-        correspondenceTables (list): A list of correspondence-tables of the version.
-
     Args:
         version_id: The ID of the version.
         select_level: The level in the codelist-data to keep. Defaults to 0 (keep all).
@@ -45,7 +30,6 @@ class KlassVersion:
         language: Language = "nb",
         include_future: bool = False,
     ) -> None:
-        """Set up the object with data from the KLASS-API."""
         self.version_id = version_id
         self.select_level = select_level
         self.language = language.lower()
@@ -139,7 +123,7 @@ class KlassVersion:
             select_level: The level of the version to keep in the data. Setting to 0 keeps all levels.
 
         Returns:
-            self (KlassVersion): Returns self to make the method more easily chainable.
+            Self: Returns self to make the method more easily chainable.
         """
         select_level = select_level if select_level else self.select_level
         data = pd.json_normalize(self.classificationItems)
@@ -272,7 +256,7 @@ class KlassVersion:
         With the IDs as keys.
 
         Returns:
-            dict: A nested dictionary of the available correspondences.
+            dict[str, dict[str, str]]: A nested dictionary of the available correspondences.
         """
         tables = {}
         for tab in self.correspondenceTables:

{ssb_klass_python-1.0.6 → ssb_klass_python-1.0.7}/src/klass/requests/klass_requests.py

@@ -38,8 +38,8 @@ def get_json(url: str, params: ParamsAfterType) -> Any:
     Used in most of the following functions.
 
     Args:
-        url (str): The URL to the endpoint.
-        params (ParamsAfterType): The parameters to send to the endpoint.
+        url: The URL to the endpoint.
+        params: The parameters to send to the endpoint.
 
     Returns:
         Any: The JSON response from the endpoint, hard to type because all endpoints have differently structured responses.

ssb_klass_python-1.0.7/src/klass/utility/filters.py

@@ -0,0 +1,82 @@
+from typing import Final
+from typing import Literal
+from typing import cast
+
+import pandas as pd
+
+STRING_DTYPE: Final[Literal["string[pyarrow]"]] = "string[pyarrow]"
+
+
+def limit_na_level(
+    df: pd.DataFrame,
+    key: str,
+    value: str,
+    remove_na: bool = True,
+    select_level: int | None = None,
+) -> pd.DataFrame:
+    """Filter a correspondence DataFrame by NA/empty values and optional level.
+
+    Creates a filtered copy of the input DataFrame where rows may be removed
+    based on missing or empty values in the specified key/value columns and/or
+    restricted to a specific classification level.
+
+    If ``remove_na`` is True, rows are kept only if both ``key`` and ``value``:
+    - are not NA
+    - are not empty strings (after string conversion)
+
+    If ``select_level`` is provided, only rows where the ``level`` column
+    matches the given value are retained.
+
+    Args:
+        df: The input DataFrame containing correspondence data.
+        key: Column name used as dictionary keys in downstream mapping.
+        value: Column name used as dictionary values in downstream mapping.
+        remove_na: Whether to remove rows where key/value are NA or empty strings.
+        select_level: Optional classification level to filter on.
+
+    Returns:
+        pd.DataFrame: A filtered copy of the input DataFrame.
+    """
+    limit_data = df.copy()
+    if remove_na:
+        print(key, value)
+        non_empty = (
+            limit_data[[key, value]].astype(STRING_DTYPE).fillna("") != ""
+        ).all(axis=1)
+        mask = cast(pd.Series, limit_data[[key, value]].notna().all(axis=1) & non_empty)
+        limit_data = limit_data.loc[mask]
+        print(limit_data)
+    if select_level:
+        level_mask = cast(
+            pd.Series,
+            limit_data["level"].astype(STRING_DTYPE) == str(select_level),
+        )
+        limit_data = limit_data.loc[level_mask]
+    return limit_data
+
+
+def apply_presentation_name_fallback(
+    df: pd.DataFrame,
+    value: str,
+    fallback: str = "name",
+    fallback_col: str = "_value_fallback",
+) -> tuple[pd.DataFrame, str]:
+    """Create a fallback value column when presentation names are empty.
+
+    Args:
+        df: Input DataFrame.
+        value: The value column name requested.
+        fallback: The fallback column name to use when presentation names are empty.
+        fallback_col: The name of the temporary column to store the fallback result.
+
+    Returns:
+        tuple[pd.DataFrame, str]: The DataFrame (possibly augmented) and the effective value column name.
+    """
+    if value != "presentationName" or fallback not in df.columns:
+        return df, value
+    data = df.copy()
+    data[fallback_col] = data["presentationName"].astype(STRING_DTYPE).fillna("")
+    empty_mask = cast(pd.Series, data[fallback_col] == "")
+    if empty_mask.any():
+        data.loc[empty_mask, fallback_col] = data[fallback].astype(STRING_DTYPE)
+    return data, fallback_col

{ssb_klass_python-1.0.6 → ssb_klass_python-1.0.7}/src/klass/widgets/search_ipywidget.py

@@ -17,8 +17,8 @@ def search_classification(no_dupes: bool = True) -> widgets.VBox:
     that'll let you get data from the classification.
 
     Args:
-        no_dupes (bool): To include duplicate results or not in the result.
-                        Dupes are caused by multiple languages being returned.
+        no_dupes: To include duplicate results or not in the result.
+            Dupes are caused by multiple languages being returned.
 
     Returns:
         widgets.VBox: Containing the nested ipywidgets-GUI. Jupyter will automatically display it.
@@ -86,7 +86,7 @@ def format_classification_text(search_class: KlassSearchClassifications) -> str:
     """Format the classifications from a search into a html-string that can be used in the widget results.
 
     Args:
-        search_class (KlassSearchClassifications): The search-results.
+        search_class: The search-results.
 
     Returns:
         str: The formatted html-string.