Merge pull request #43 from bcdev/forman-vaerify_vs_validate

More consistency

Author: forman

CHANGES.md

@@ -2,17 +2,28 @@
 
 ## Version 0.5.0 (in development)
 
-- Introduced type aliases `ConfigLike` and `ConfigObjectLike`.
-- Renamed multiple components for improved clarity and consistency:
-  - Renamed `Config` into `ConfigObject` 
-  - Renamed `ConfigList.configs` into `config_objects` 
-  - Renamed `ConfigList` into `Config` 
-  - Renamed `ConfigList.compute_config()` into `compute_config_object()` 
-  - Renamed `Result.config` into `config_object` 
-  - Renamed `XRLint.load_config_list()` into `init_config()`
-  - Renamed `XRLint.verify_datasets()` into `verify_files()`
-- Added class method `from_config()` to `ConfigList`.
-- Removed function `xrlint.config.merge_configs` as it was no longer used.
+### Incompatible API changes:
+
+- Renamed nodes and node properties for consistency and clarity:
+  - renamed `DataArrayNode` into `VariableNode`
+  - renamed `DataArrayNode.data_array` into `VariableNode.array`
+
+- Changed general use of term _verify_ into _validate_: 
+  - prefixed `RuleOp` methods by `validate_` for clarity.
+  - renamed `XRLint.verify_datasets()` into `validate_files()`
+  - renamed `Lint.verify_dataset()` into `validate()`
+
+- Various changes for improved clarity and consistency 
+  regarding configuration management:
+  - introduced type aliases `ConfigLike` and `ConfigObjectLike`.
+  - renamed `Config` into `ConfigObject` 
+  - renamed `ConfigList.configs` into `config_objects` 
+  - renamed `ConfigList` into `Config` 
+  - renamed `ConfigList.compute_config()` into `compute_config_object()` 
+  - renamed `Result.config` into `config_object` 
+  - renamed `XRLint.load_config_list()` into `init_config()`
+  - added class method `from_config()` to `ConfigList`.
+  - removed function `xrlint.config.merge_configs` as it was no longer used.
 
 ## Version 0.4.1 (from 2025-01-31)
 

docs/start.md

@@ -106,5 +106,5 @@ import xrlint.all as xrl
 test_ds = xr.Dataset(attrs={"title": "Test Dataset"})
 
 linter = xrl.new_linter("recommended")
-linter.verify_dataset(test_ds)
+linter.validate(test_ds)
 ```

docs/todo.md

@@ -10,13 +10,6 @@
   - use mkdocstrings ref syntax in docstrings
   - provide configuration examples (use as tests?)
   - add `docs_url` to all existing rules 
-- API changes for v0.5:
-  - clarify when users can pass configuration objects like values 
-    and when configuration like values
-  - config class naming is confusing, 
-    change `Config` -> `ConfigObject`, `ConfigList` -> `Config`
-  - Change `verify` -> `validate`, 
-    prefix `RuleOp` methods by `validate_` for clarity.
 
 ## Desired
 
@@ -51,30 +44,30 @@
 
 ## Generalize data linting
 
-Do not limit verification to `xr.Dataset`.
+Do not limit validations to `xr.Dataset`.
 However, this requires new rule sets.
 
 To allow for other data models, we need to allow 
-for a specific verifier type for a given data type.
+for a specific validator type for a given data type.
 
-The verifier verifies specific node types
+The validator validates specific node types
 that are characteristic for a data type.
 
 To do so a traverser must traverse the elements of the data
-and pass each node to the verifier.
+and pass each node to the validator.
 
 Note, this is the [_Visitor Pattern_](https://en.wikipedia.org/wiki/Visitor_pattern), 
-where the verifier is the _Visitor_ and a node refers to _Element_.
+where the validator is the _Visitor_ and a node refers to _Element_.
 
 To support the CLI mode, we need different data opener 
 types that can read the data from a file path.
 
 1. open data, if given data is a file path: 
    - find opener for file path
    - open data 
-2. verify data
+2. validate data
    - find root element type and visitor type for data 
-   - call the root element `accept(verifier)` that verifies the 
-     root element `verify.root()` and starts traversal of 
+   - call the root element `accept(validator)` that validates the 
+     root element `validate.root()` and starts traversal of 
      child elements.
 

examples/check_s3_bucket.py

@@ -4,5 +4,5 @@
 
 xrlint = xrl.XRLint(no_config_lookup=True)
 xrlint.init_config("recommended")
-results = xrlint.verify_files([URL])
+results = xrlint.validate_files([URL])
 print(xrlint.format_results(results))

examples/plugin_config.py

@@ -14,7 +14,7 @@
 class GoodTitle(RuleOp):
     """Dataset title should be 'Hello World!'."""
 
-    def dataset(self, ctx: RuleContext, node: DatasetNode):
+    def validate_dataset(self, ctx: RuleContext, node: DatasetNode):
         good_title = "Hello World!"
         if node.dataset.attrs.get("title") != good_title:
             ctx.report(

examples/rule_testing.py

@@ -13,7 +13,7 @@
 class GoodTitle(RuleOp):
     """Dataset title should be 'Hello World!'."""
 
-    def dataset(self, ctx: RuleContext, node: DatasetNode):
+    def validate_dataset(self, ctx: RuleContext, node: DatasetNode):
         good_title = "Hello World!"
         if node.dataset.attrs.get("title") != good_title:
             ctx.report(

examples/virtual_plugin_config.py

@@ -10,7 +10,7 @@
 
 @define_rule("good-title", description="Dataset title should be 'Hello World!'.")
 class GoodTitle(RuleOp):
-    def dataset(self, ctx: RuleContext, node: DatasetNode):
+    def validate_dataset(self, ctx: RuleContext, node: DatasetNode):
         good_title = "Hello World!"
         if node.dataset.attrs.get("title") != good_title:
             ctx.report(

notebooks/xrlint-linter.ipynb

@@ -532,7 +532,7 @@
     }
    ],
    "source": [
-    "linter.verify_dataset(ds)"
+    "linter.validate(ds)"
    ]
   },
   {
@@ -1019,7 +1019,7 @@
     }
    ],
    "source": [
-    "linter.verify_dataset(invalid_ds)"
+    "linter.validate(invalid_ds)"
    ]
   },
   {
@@ -1100,7 +1100,7 @@
     }
    ],
    "source": [
-    "linter.verify_dataset(invalid_ds)"
+    "linter.validate(invalid_ds)"
    ]
   },
   {
@@ -1159,7 +1159,7 @@
     }
    ],
    "source": [
-    "linter.verify_dataset(invalid_ds)"
+    "linter.validate(invalid_ds)"
    ]
   },
   {

tests/test_linter.py

@@ -6,7 +6,7 @@
 from xrlint.config import Config, ConfigObject
 from xrlint.constants import CORE_PLUGIN_NAME, NODE_ROOT_NAME
 from xrlint.linter import Linter, new_linter
-from xrlint.node import AttrNode, AttrsNode, DataArrayNode, DatasetNode
+from xrlint.node import AttrNode, AttrsNode, VariableNode, DatasetNode
 from xrlint.plugin import new_plugin
 from xrlint.processor import ProcessorOp
 from xrlint.result import Message, Result
@@ -50,34 +50,34 @@ def test_new_linter_all(self):
         self.assertIn("coords-for-dims", config_obj_1.rules)
 
 
-class LinterVerifyConfigTest(TestCase):
+class LinterValidateWithConfigTest(TestCase):
     def test_config_with_config_list(self):
         linter = new_linter()
-        result = linter.verify_dataset(
+        result = linter.validate(
             xr.Dataset(),
             config=Config.from_value([{"rules": {"no-empty-attrs": 2}}]),
         )
         self.assert_result_ok(result, "Missing metadata, attributes are empty.")
 
     def test_config_with_list_of_config(self):
         linter = new_linter()
-        result = linter.verify_dataset(
+        result = linter.validate(
             xr.Dataset(),
             config=[{"rules": {"no-empty-attrs": 2}}],
         )
         self.assert_result_ok(result, "Missing metadata, attributes are empty.")
 
     def test_config_with_config_obj(self):
         linter = new_linter()
-        result = linter.verify_dataset(
+        result = linter.validate(
             xr.Dataset(),
             config={"rules": {"no-empty-attrs": 2}},
         )
         self.assert_result_ok(result, "Missing metadata, attributes are empty.")
 
     def test_no_config(self):
         linter = Linter()
-        result = linter.verify_dataset(
+        result = linter.validate(
             xr.Dataset(),
         )
         self.assert_result_ok(result, "No configuration given or matches '<dataset>'.")
@@ -89,27 +89,27 @@ def assert_result_ok(self, result: Result, expected_message: str):
         self.assertEqual(expected_message, result.messages[0].message)
 
 
-class LinterVerifyTest(TestCase):
+class LinterValidateTest(TestCase):
     def setUp(self):
         plugin = new_plugin(name="test")
 
         @plugin.define_rule("no-space-in-attr-name")
         class AttrVer(RuleOp):
-            def attr(self, ctx: RuleContext, node: AttrNode):
+            def validate_attr(self, ctx: RuleContext, node: AttrNode):
                 if " " in node.name:
                     ctx.report(f"Attribute name with space: {node.name!r}")
 
         @plugin.define_rule("no-empty-attrs")
         class AttrsVer(RuleOp):
-            def attrs(self, ctx: RuleContext, node: AttrsNode):
+            def validate_attrs(self, ctx: RuleContext, node: AttrsNode):
                 if not node.attrs:
                     ctx.report("Empty attributes")
 
         @plugin.define_rule("data-var-dim-must-have-coord")
         class DataArrayVer(RuleOp):
-            def data_array(self, ctx: RuleContext, node: DataArrayNode):
+            def validate_variable(self, ctx: RuleContext, node: VariableNode):
                 if node.in_data_vars():
-                    for dim_name in node.data_array.dims:
+                    for dim_name in node.array.dims:
                         if dim_name not in ctx.dataset.coords:
                             ctx.report(
                                 f"Dimension {dim_name!r}"
@@ -119,7 +119,7 @@ def data_array(self, ctx: RuleContext, node: DataArrayNode):
 
         @plugin.define_rule("dataset-without-data-vars")
         class DatasetVer(RuleOp):
-            def dataset(self, ctx: RuleContext, node: DatasetNode):
+            def validate_dataset(self, ctx: RuleContext, node: DatasetNode):
                 if len(node.dataset.data_vars) == 0:
                     ctx.report("Dataset does not have data variables")
                     raise RuleExit  # no need to traverse further
@@ -157,7 +157,7 @@ def test_rules_are_ok(self):
         )
 
     def test_linter_respects_rule_severity_error(self):
-        result = self.linter.verify_dataset(
+        result = self.linter.validate(
             xr.Dataset(), rules={"test/dataset-without-data-vars": 2}
         )
         self.assertEqual(
@@ -182,7 +182,7 @@ def test_linter_respects_rule_severity_error(self):
         )
 
     def test_linter_respects_rule_severity_warn(self):
-        result = self.linter.verify_dataset(
+        result = self.linter.validate(
             xr.Dataset(), rules={"test/dataset-without-data-vars": 1}
         )
         self.assertEqual(
@@ -207,7 +207,7 @@ def test_linter_respects_rule_severity_warn(self):
         )
 
     def test_linter_respects_rule_severity_off(self):
-        result = self.linter.verify_dataset(
+        result = self.linter.validate(
             xr.Dataset(), rules={"test/dataset-without-data-vars": 0}
         )
         self.assertEqual(
@@ -225,9 +225,7 @@ def test_linter_respects_rule_severity_off(self):
         )
 
     def test_linter_recognized_unknown_rule(self):
-        result = self.linter.verify_dataset(
-            xr.Dataset(), rules={"test/dataset-is-fast": 2}
-        )
+        result = self.linter.validate(xr.Dataset(), rules={"test/dataset-is-fast": 2})
         self.assertEqual(
             [
                 Message(
@@ -266,7 +264,7 @@ def test_linter_real_life_scenario(self):
         )
         dataset.encoding["source"] = "chl-tsm.zarr"
 
-        result = self.linter.verify_dataset(
+        result = self.linter.validate(
             dataset,
             config={
                 "rules": {
@@ -325,7 +323,7 @@ def test_linter_real_life_scenario(self):
         )
 
     def test_processor_ok(self):
-        result = self.linter.verify_dataset(
+        result = self.linter.validate(
             "test.levels",
             config={
                 "processor": "test/multi-level-dataset",
@@ -352,7 +350,7 @@ def test_processor_ok(self):
         )
 
     def test_processor_fail(self):
-        result = self.linter.verify_dataset(
+        result = self.linter.validate(
             "bad.levels",
             config={
                 "processor": "test/multi-level-dataset",

tests/test_testing.py

@@ -9,7 +9,7 @@
 
 
 class ForceTitle(RuleOp):
-    def dataset(self, ctx: RuleContext, node: DatasetNode):
+    def validate_dataset(self, ctx: RuleContext, node: DatasetNode):
         title = node.dataset.attrs.get("title")
         if not title:
             ctx.report("Datasets must have a title")