Merge pull request #1084 from xcube-dev/konstntokas-xxx-small_adjustm…

…ents_https_datastore_for_xcube_zenodo

Bug fix in `has_data` method for `"https"` data store

CHANGES.md

@@ -9,16 +9,21 @@
 * The behaviour of the function `xcube.core.resample.resample_in_space()` has 
   been changed if no `tile_size` is specified for the target grid mapping. It now 
   defaults to the `tile_size` of the source grid mapping, improving the 
-  user-friendliness of resampling and reprojection.
+  user-friendliness of resampling and reprojection. (#1082)
 * The `"https"` data store (`store = new_data_store("https", ...)`) now allows 
   for lazily accessing NetCDF files.
   Implementation note: For this to work, the `DatasetNetcdfFsDataAccessor` 
-  class has been adjusted.
+  class has been adjusted. (#1083)
 
 ### Fixes
 
 * The function `xcube.core.resample.resample_in_space()` now always operates
-   lazily and therefore supports chunk-wise, parallel processing. (#1
+  lazily and therefore supports chunk-wise, parallel processing. (#1082)
+* Bux fix in the `has_data` method of the `"https"` data store
+  (`store = new_data_store("https", ...)`). (#1084) 
+* Bux fix in the `has_data` method of all filesystem-based data store
+  (`"file", "s3", "https"`). `data_type` can be any of the supported data types,
+  e.g. for `.tif` file, `data_type` can be either `dataset` or `mldataset`. (#1084) 
 * The explaination of the parameter `xy_scale` in the method 
   `xcube.core.gridmapping.GridMapping.scale` has been corrected. (#1086)
 

test/core/store/test_store.py

@@ -2,12 +2,15 @@
 # Permissions are hereby granted under the terms of the MIT License:
 # https://opensource.org/licenses/MIT.
 import unittest
+from unittest.mock import patch
+from unittest.mock import MagicMock
 
 from fsspec.registry import register_implementation
 
 from xcube.core.store import DataStoreError
 from xcube.core.store import list_data_store_ids
 from xcube.core.store import new_data_store
+
 import pytest
 
 
@@ -57,6 +60,35 @@ def test_get_data_opener_ids(self):
             store.get_data_opener_ids(data_id="test.geotiff", data_type="mldataset"),
         )
 
+    @patch("fsspec.filesystem")
+    def test_has_data(self, mock_filesystem):
+        # Mock the HTTPFileSystem instance and its `exists` method
+        mock_http_fs = MagicMock()
+        mock_filesystem.return_value = mock_http_fs
+        mock_http_fs.exists.return_value = True
+        mock_http_fs.sep = "/"
+
+        store = new_data_store("https", root="test.org")
+
+        res = store.has_data(data_id="test.tif")
+        self.assertEqual(mock_filesystem.call_count, 1)
+        mock_http_fs.exists.assert_called_once_with("https://test.org/test.tif")
+        self.assertTrue(res)
+
+        res = store.has_data(data_id="test.tif", data_type="dataset")
+        mock_http_fs.exists.assert_called_with("https://test.org/test.tif")
+        self.assertEqual(mock_http_fs.exists.call_count, 2)
+        self.assertTrue(res)
+
+        res = store.has_data(data_id="test.tif", data_type="mldataset")
+        mock_http_fs.exists.assert_called_with("https://test.org/test.tif")
+        self.assertEqual(mock_http_fs.exists.call_count, 3)
+        self.assertTrue(res)
+
+        res = store.has_data(data_id="test.tif", data_type="geodataframe")
+        self.assertEqual(mock_http_fs.exists.call_count, 3)
+        self.assertFalse(res)
+
 
 def test_fsspec_instantiation_error():
     error_string = "deliberate instantiation error for testing"

xcube/core/store/fs/store.py

@@ -275,8 +275,10 @@ def get_data_ids(
 
     def has_data(self, data_id: str, data_type: DataTypeLike = None) -> bool:
         assert_given(data_id, "data_id")
-        if self._is_data_specified(data_id, data_type):
+        if self._is_data_type_available(data_id, data_type):
             fs_path = self._convert_data_id_into_fs_path(data_id)
+            if self.protocol == "https":
+                fs_path = f"{self.protocol}://{fs_path}"
             return self.fs.exists(fs_path)
         return False
 
@@ -509,6 +511,18 @@ def _is_data_specified(
             return False
         return True
 
+    def _is_data_type_available(self, data_id: str, data_type: DataTypeLike) -> bool:
+        ext = self._get_filename_ext(data_id)
+        format_id = _FILENAME_EXT_TO_FORMAT.get(ext.lower())
+        if format_id is None:
+            return False
+        avail_data_types = _FORMAT_TO_DATA_TYPE_ALIASES.get(format_id)
+        data_type = DataType.normalize(data_type)
+        return any(
+            data_type.is_super_type_of(avail_data_type)
+            for avail_data_type in avail_data_types
+        )
+
     def _assert_data_specified(self, data_id, data_type: DataTypeLike):
         self._is_data_specified(data_id, data_type, require=True)