hdx-python-api 6.6.8__py3-none-any.whl → 6.7.0__py3-none-any.whl

hdx/api/_version.py

@@ -18,7 +18,7 @@ version_tuple: tuple[int | str, ...]
 commit_id: str | None
 __commit_id__: str | None
 
-__version__ = version = '6.6.8'
-__version_tuple__ = version_tuple = (6, 6, 8)
+__version__ = version = '6.7.0'
+__version_tuple__ = version_tuple = (6, 7, 0)
 
 __commit_id__ = commit_id = None

hdx/api/hdx_base_configuration.yaml

@@ -72,6 +72,10 @@ organization:
     - name
     - title
     - description
+group:
+  required_fields:
+    - name
+    - title
 "resource view":
   required_fields:
     - resource_id

hdx/api/locations.py

@@ -3,6 +3,7 @@
 from collections.abc import Sequence
 
 from hdx.api.configuration import Configuration
+from hdx.data.location import Location
 
 
 class Locations:
@@ -22,10 +23,8 @@ class Locations:
             A list of valid locations
         """
         if cls._validlocations is None:
-            if configuration is None:
-                configuration = Configuration.read()
-            cls._validlocations = configuration.call_remoteckan(
-                "group_list", {"all_fields": True}
+            cls._validlocations = Location.get_all_location_names(
+                configuration=configuration, all_fields=True
             )
         return cls._validlocations
 

hdx/data/location.py

@@ -0,0 +1,237 @@
+"""Location class containing all logic for creating, checking, and updating locations."""
+
+import logging
+from collections.abc import Sequence
+from typing import Any, Optional
+
+from hdx.api.configuration import Configuration
+from hdx.data.hdxobject import HDXObject
+
+logger = logging.getLogger(__name__)
+
+
+class Location(HDXObject):
+    """Location class containing all logic for creating, checking, and updating locations.
+    A location is a CKAN group.
+
+    Args:
+        initial_data: Initial location metadata dictionary. Defaults to None.
+        configuration: HDX configuration. Defaults to global configuration.
+    """
+
+    def __init__(
+        self,
+        initial_data: dict | None = None,
+        configuration: Configuration | None = None,
+    ) -> None:
+        if not initial_data:
+            initial_data = {}
+        super().__init__(initial_data, configuration=configuration)
+
+    @staticmethod
+    def actions() -> dict[str, str]:
+        """Dictionary of actions that can be performed on object
+
+        Returns:
+            Dictionary of actions that can be performed on object
+        """
+        return {
+            "show": "group_show",
+            "update": "group_update",
+            "create": "group_create",
+            "delete": "group_delete",
+            "list": "group_list",
+            "autocomplete": "group_autocomplete",
+        }
+
+    @classmethod
+    def read_from_hdx(
+        cls, identifier: str, configuration: Configuration | None = None
+    ) -> Optional["Location"]:
+        """Reads the location given by identifier from HDX and returns Location object
+
+        Args:
+            identifier: Identifier of location
+            configuration: HDX configuration. Defaults to global configuration.
+
+        Returns:
+            Location object if successful read, None if not
+        """
+        return cls._read_from_hdx_class("group", identifier, configuration)
+
+    def check_required_fields(self, ignore_fields: Sequence[str] = ()) -> None:
+        """Check that metadata for location is complete. The parameter ignore_fields should
+        be set if required to any fields that should be ignored for the particular operation.
+
+        Args:
+            ignore_fields: Fields to ignore. Default is ().
+
+        Returns:
+            None
+        """
+        self._check_required_fields("group", ignore_fields)
+
+    def update_in_hdx(self, **kwargs: Any) -> None:
+        """Check if location exists in HDX and if so, update location
+
+        Returns:
+            None
+        """
+        self._update_in_hdx("group", "id", **kwargs)
+
+    def create_in_hdx(self, **kwargs: Any) -> None:
+        """Check if location exists in HDX and if so, update it, otherwise create location
+
+        Returns:
+            None
+        """
+        self._create_in_hdx("group", "id", "name", **kwargs)
+
+    def delete_from_hdx(self) -> None:
+        """Deletes a location from HDX.
+
+        Returns:
+            None
+        """
+        self._delete_from_hdx("group", "id")
+
+    def get_datasets(self, query: str = "*:*", **kwargs: Any) -> list["Dataset"]:  # noqa: F821
+        """Get list of datasets in location
+
+        Args:
+            query: Restrict datasets returned to this query (in Solr format). Defaults to '*:*'.
+            **kwargs: See below
+            sort (string): Sorting of the search results. Defaults to 'relevance asc, metadata_modified desc'.
+            rows (int): Number of matching rows to return. Defaults to all datasets (sys.maxsize).
+            start (int): Offset in the complete result for where the set of returned datasets should begin
+            facet (string): Whether to enable faceted results. Default to True.
+            facet.mincount (int): Minimum counts for facet fields should be included in the results
+            facet.limit (int): Maximum number of values the facet fields return (- = unlimited). Defaults to 50.
+            facet.field (list[str]): Fields to facet upon. Default is empty.
+            use_default_schema (bool): Use default package schema instead of custom schema. Defaults to False.
+
+        Returns:
+            List of datasets in location
+        """
+        import hdx.data.dataset  # avoid circular import
+
+        return hdx.data.dataset.Dataset.search_in_hdx(
+            query=query,
+            configuration=self.configuration,
+            fq=f"groups:{self.data['name']}",
+            **kwargs,
+        )
+
+    @staticmethod
+    def get_all_location_names(
+        configuration: Configuration | None = None, **kwargs: Any
+    ) -> list[str]:
+        """Get all location names in HDX
+
+        Args:
+            configuration: HDX configuration. Defaults to global configuration.
+            **kwargs: See below
+            sort (str): Sort the search results according to field name and sort-order. Allowed fields are ‘name’, ‘package_count’ and ‘title’. Defaults to 'name asc'.
+            groups (list[str]): List of names of the groups to return.
+            all_fields (bool): Return group dictionaries instead of just names. Only core fields are returned - get some more using the include_* options. Defaults to False.
+            include_extras (bool): If all_fields, include the group extra fields. Defaults to False.
+            include_tags (bool): If all_fields, include the group tags. Defaults to False.
+            include_groups (bool): If all_fields, include the groups the groups are in. Defaults to False.
+
+        Returns:
+            List of all location names in HDX
+        """
+        location = Location(configuration=configuration)
+
+        # Early return for the standard, non-paginated case
+        if not kwargs.get("all_fields"):
+            return location._write_to_hdx("list", kwargs)
+
+        compiled_locations = {}
+        # Extract limit and offset to dictate our paging sizes, defaulting to 400 and 0
+        page_size = kwargs.pop("limit", 400)
+        current_offset = kwargs.pop("offset", 0)
+
+        # 1. Fetch in pages using the provided/default page size
+        while True:
+            page_kwargs = kwargs.copy()
+            page_kwargs["limit"] = page_size
+            page_kwargs["offset"] = current_offset
+
+            page_data = location._write_to_hdx("list", page_kwargs)
+
+            if not page_data:
+                break
+
+            # Store by name to automatically deduplicate offset shifts
+            for loc in page_data:
+                compiled_locations[loc["name"]] = loc
+
+            if len(page_data) < page_size:
+                break
+
+            current_offset += page_size
+
+        # 2. Establish Ground Truth LAST (without limit/offset constraints)
+        truth_kwargs = kwargs.copy()
+        truth_kwargs["all_fields"] = False
+
+        ground_truth_names = location._write_to_hdx("list", truth_kwargs)
+
+        # 3 & 4. Check for missing IDs, fetch individually, and implicitly prune deletes
+        final_locations = []
+        for name in ground_truth_names:
+            if name in compiled_locations:
+                final_locations.append(compiled_locations[name])
+            else:
+                try:
+                    missing_location = location._write_to_hdx("show", {"id": name})
+                    if missing_location:
+                        final_locations.append(missing_location)
+                except Exception:
+                    pass
+
+        return final_locations
+
+    @staticmethod
+    def get_data_grid_countries(
+        configuration: Configuration | None = None,
+    ) -> list[str]:
+        """Fetch HDX's active Data Grid countries (3-letter group names).
+
+        Treated as a live/short-TTL lookup rather than a frozen static list, since Data Grid
+        membership changes over time.
+
+        Args:
+            configuration: HDX configuration. Defaults to global configuration.
+
+        Returns:
+            Sorted list of active Data Grid country (group) names
+        """
+        groups = Location.get_all_location_names(
+            configuration=configuration, all_fields=True, include_extras=True
+        )
+        return sorted(
+            group["name"]
+            for group in groups
+            if len(group["name"]) == 3 and group.get("data_completeness") == "active"
+        )
+
+    @classmethod
+    def autocomplete(
+        cls,
+        name: str,
+        limit: int = 20,
+        configuration: Configuration | None = None,
+    ) -> list:
+        """Autocomplete a location name and return matches
+
+        Args:
+            name: Name to autocomplete
+            limit: Maximum number of matches to return
+            configuration: HDX configuration. Defaults to global configuration.
+
+        Returns:
+            Autocomplete matches
+        """
+        return cls._autocomplete(name, limit, configuration)

hdx/data/resource.py

@@ -1,5 +1,6 @@
 """Resource class containing all logic for creating, checking, and updating resources."""
 
+import json
 import logging
 from collections.abc import Sequence
 from datetime import datetime
@@ -33,6 +34,9 @@ class Resource(HDXObject):
     """
 
     _formats_dict = None
+    _valid_data_dictionary_types = frozenset(
+        {"text", "numeric", "date", "timestamp without time zone"}
+    )
 
     def __init__(
         self,
@@ -263,6 +267,56 @@ class Resource(HDXObject):
         self.data["format"] = file_format
         return file_format
 
+    def get_hdx_data_dictionary(self) -> list[dict] | None:
+        """Get the resource's data dictionary (column definitions)
+
+        Returns:
+            List of column definition dictionaries or None if not set
+        """
+        data_dictionary = self.data.get("hdx_data_dictionary")
+        if data_dictionary is None:
+            return None
+        if isinstance(data_dictionary, str):
+            return json.loads(data_dictionary)
+        return data_dictionary
+
+    def set_hdx_data_dictionary(self, data_dictionary: Sequence[dict]) -> None:
+        """Set the resource's data dictionary (column definitions). Each column
+        definition must be a dict with non-empty string values for field
+        (column name in the CSV file), label (human-readable column label) and
+        description (human-readable description of the column). If present,
+        data_type must be one of the PostgreSQL types produced by DataPusher+
+        (text, numeric, date, timestamp without time zone).
+
+        Args:
+            data_dictionary: Sequence of column definition dictionaries
+
+        Returns:
+            None
+        """
+        if not data_dictionary:
+            raise HDXError("hdx_data_dictionary must be a non-empty list!")
+        for i, column in enumerate(data_dictionary):
+            if not isinstance(column, dict):
+                raise HDXError(f"hdx_data_dictionary[{i}] must be a dict!")
+            for required_key in ("field", "label", "description"):
+                value = column.get(required_key)
+                if not isinstance(value, str) or not value.strip():
+                    raise HDXError(
+                        f"hdx_data_dictionary[{i}] is missing a non-empty '{required_key}'!"
+                    )
+            if "data_type" in column:
+                data_type = column["data_type"]
+                if data_type not in self._valid_data_dictionary_types:
+                    valid_types = ", ".join(sorted(self._valid_data_dictionary_types))
+                    raise HDXError(
+                        f"hdx_data_dictionary[{i}] has invalid 'data_type' "
+                        f"'{data_type}'! Must be one of: {valid_types}"
+                    )
+        self.data["hdx_data_dictionary"] = json.dumps(
+            data_dictionary, separators=(",", ":")
+        )
+
     def clean_format(self) -> str:
         """Clean the resource's format, setting it to None if it is invalid and
         cannot be mapped

{hdx_python_api-6.6.8.dist-info → hdx_python_api-6.7.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
-Metadata-Version: 2.4
+Metadata-Version: 2.5
 Name: hdx-python-api
-Version: 6.6.8
+Version: 6.7.0
 Summary: HDX Python API for interacting with the Humanitarian Data Exchange
 Project-URL: Homepage, https://github.com/OCHA-DAP/hdx-python-api
 Author: Michael Rans
@@ -28,8 +28,8 @@ Requires-Python: >=3.10
 Requires-Dist: ckanapi>=4.11
 Requires-Dist: defopt>=7.0.0
 Requires-Dist: email-validator
-Requires-Dist: hdx-python-country>=4.1.1
-Requires-Dist: hdx-python-utilities>=4.0.8
+Requires-Dist: hdx-python-country>=4.1.3
+Requires-Dist: hdx-python-utilities>=4.1.2
 Requires-Dist: makefun
 Requires-Dist: requests
 Provides-Extra: docs

{hdx_python_api-6.6.8.dist-info → hdx_python_api-6.7.0.dist-info}/RECORD

@@ -1,8 +1,8 @@
 hdx/api/__init__.py,sha256=11ozJKiUsqDCZ3_mcAHhGYUyGK_Unl54djVSBBExFB4,59
-hdx/api/_version.py,sha256=DuBvygFq7Ca-heE19aRqV-dGslR55qXsxEXRXjW5FNM,520
+hdx/api/_version.py,sha256=ySRWjy-IYGDZdNB2wR2G-LZ8vwxqmQqgeGjL_1f7wkc,520
 hdx/api/configuration.py,sha256=9WvuVI-3th2Dv70_t_4VoyrlJwB_9qUSN5_zUKbp4sQ,23805
-hdx/api/hdx_base_configuration.yaml,sha256=9yJYroZwoyMQo6tcxGfWHWvYahnTma7Szx0J5Z378z4,2173
-hdx/api/locations.py,sha256=blnqOjEASvh0mWgmo2iEE7ES_xOuRwQo3fOMqTPV_P0,4139
+hdx/api/hdx_base_configuration.yaml,sha256=jj2t5b7NnI499rHVwOjj3Q5BAjE8i7NDGVKnWZ5P5-4,2222
+hdx/api/locations.py,sha256=bFl_cKz_AEQzkE_xWOkrRlUQ0GT2LMPSk-G_LsbV-Ns,4099
 hdx/api/remotehdx.py,sha256=IjKwP3jutlkrjvWCJPP7YM-xzg3pP_QVmiJfblllBY0,2079
 hdx/api/utilities/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 hdx/api/utilities/date_helper.py,sha256=sXxjRtXz-2rpBVZBbJAk80gfjpYKl_AtHplWr-rniIk,6396
@@ -13,8 +13,9 @@ hdx/api/utilities/url_utils.py,sha256=Pb4r-BAqIHYmeoB_i7QjutDp6nOAUh_OHvCtiNLda3
 hdx/data/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 hdx/data/dataset.py,sha256=0gS7tQSswTgG0g8YeXg0FL8pFVkocBQSRPFpQAurN00,99455
 hdx/data/hdxobject.py,sha256=_jlwYjb_CcjaXsTXObknMfq-OiNOcpJfLJ9b1vKV1Zo,27494
+hdx/data/location.py,sha256=WIQRdY1boy6xPweIWRczWNiJLFrp4w0DVUwppHeNccU,8765
 hdx/data/organization.py,sha256=HGopFsCYOWrR7sUtZzZSXq6wLFw4djus2gzg6yNXOqc,12296
-hdx/data/resource.py,sha256=YcxGzKuFduLZIOnCvo-zcwJfnTGOmnvtDeFr2xKeOM4,35647
+hdx/data/resource.py,sha256=SBAEou9Fj5sgpfoDmQ6j33W0srMMmhlsj00hiTuW86Y,38097
 hdx/data/resource_matcher.py,sha256=Yzk9pWa4zk1p09m6zcZMj0XZf5Y16Pa3KToOdUt7rP8,4247
 hdx/data/resource_view.py,sha256=GcYkh0iDAe6_m2ErY_A6i3Z7ZFX949eGt1TLnLZv_8s,7346
 hdx/data/showcase.py,sha256=vnRZ45xd9Ct65eFQkWZtMIJPFifZfKOrH4obO5D5Pvc,14062
@@ -24,7 +25,7 @@ hdx/facades/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 hdx/facades/infer_arguments.py,sha256=DvyDuozfOPmoaV7HjhQySojGIrMWW9nos31auQBVVl8,4032
 hdx/facades/keyword_arguments.py,sha256=aVapHCfqBO6H7xxBgTdK9ISdgrBFsNypPDWihfQ3edU,1125
 hdx/facades/simple.py,sha256=QWsBkaHG_UM6X3Zu2u3LWVOQzeR24q-EUClrfsL_mkM,1064
-hdx_python_api-6.6.8.dist-info/METADATA,sha256=tRdOttf0O-eRc7iASB0HkCahGiC4dzf5SIVCCv8VHxw,4946
-hdx_python_api-6.6.8.dist-info/WHEEL,sha256=QccIxa26bgl1E6uMy58deGWi-0aeIkkangHcxk2kWfw,87
-hdx_python_api-6.6.8.dist-info/licenses/LICENSE,sha256=wc-4GpMn-ODs-U_bTe1YCiPVgvcjzrpYOx2wPuyAeII,1079
-hdx_python_api-6.6.8.dist-info/RECORD,,
+hdx_python_api-6.7.0.dist-info/METADATA,sha256=RYuk0RvwKnxNcRzipF3cYH0_Vk-16d0XRt7lbt8x6yo,4946
+hdx_python_api-6.7.0.dist-info/WHEEL,sha256=zOwg4jB6zX2kU910N-cMawjivD6tO8NEWvE12je1bVk,87
+hdx_python_api-6.7.0.dist-info/licenses/LICENSE,sha256=wc-4GpMn-ODs-U_bTe1YCiPVgvcjzrpYOx2wPuyAeII,1079
+hdx_python_api-6.7.0.dist-info/RECORD,,

{hdx_python_api-6.6.8.dist-info → hdx_python_api-6.7.0.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: hatchling 1.29.0
+Generator: hatchling 1.32.0
 Root-Is-Purelib: true
 Tag: py3-none-any