Merge pull request #638 from FAIRmat-NFDI/599-undescriptive-error-message-cleanup

add a separate error for names with wrong type and remove such keys

Author: lukaspie

CITATION.cff

@@ -4,7 +4,7 @@ message:
   If you use this software, please cite it using the
   metadata from this file.
 type: software
-version: 0.10.6
+version: 0.10.7
 authors:
   - given-names: Sherjeel
     family-names: Shabih

src/pynxtools/data/NXtest.nxdl.xml

@@ -45,8 +45,8 @@
         </group>
         <group type="NXdata" name="specified_group" nameType="specified">
             <doc>A group with a name and nameType="specified".</doc>
-            <field name="specified_field" type="NX_FLOAT" units="NX_ANY">
-                <attribute name="specified_attr_in_field"/>
+            <field name="specified_field" nameType="specified" type="NX_FLOAT" units="NX_ANY">
+                <attribute name="specified_attr_in_field" nameType="specified"/>
             </field>
             <attribute name="specified_attr"/>
         </group>

src/pynxtools/dataconverter/convert.py

@@ -176,18 +176,12 @@ def transfer_data_into_template(
     for entry_name in entry_names:
         helpers.write_nexus_def_to_entry(data, entry_name, nxdl_name)
     if not skip_verify:
-        valid, keys_to_remove = validate_dict_against(
+        valid = validate_dict_against(
             nxdl_name,
             data,
             ignore_undocumented=ignore_undocumented,
         )
 
-        # remove attributes that belong to non-existing fields
-
-        for key in keys_to_remove:
-            # data.__delitem__(key)
-            del data[key]
-
         if fail and not valid:
             raise ValidationFailed(
                 "The data does not match the given NXDL. "

src/pynxtools/dataconverter/helpers.py

@@ -22,7 +22,7 @@
 import os
 import re
 from datetime import datetime, timezone
-from enum import Enum
+from enum import Enum, auto
 from functools import lru_cache
 from typing import Any, Callable, List, Optional, Tuple, Union, Sequence, cast
 
@@ -46,30 +46,32 @@
 
 
 class ValidationProblem(Enum):
-    UnitWithoutDocumentation = 1
-    InvalidEnum = 2
-    OpenEnumWithNewItem = 3
-    MissingRequiredGroup = 4
-    MissingRequiredField = 5
-    MissingRequiredAttribute = 6
-    InvalidType = 7
-    InvalidDatetime = 8
-    IsNotPosInt = 9
-    ExpectedGroup = 10
-    MissingDocumentation = 11
-    MissingUnit = 12
-    ChoiceValidationError = 13
-    UnitWithoutField = 14
-    AttributeForNonExistingField = 15
-    BrokenLink = 16
-    FailedNamefitting = 17
-    NXdataMissingSignalData = 18
-    NXdataMissingAxisData = 19
-    NXdataAxisMismatch = 20
-    KeyToBeRemoved = 21
-    InvalidConceptForNonVariadic = 22
-    ReservedSuffixWithoutField = 23
-    ReservedPrefixInWrongContext = 24
+    UnitWithoutDocumentation = auto()
+    InvalidEnum = auto()
+    OpenEnumWithNewItem = auto()
+    MissingRequiredGroup = auto()
+    MissingRequiredField = auto()
+    MissingRequiredAttribute = auto()
+    InvalidType = auto()
+    InvalidDatetime = auto()
+    IsNotPosInt = auto()
+    ExpectedGroup = auto()
+    ExpectedField = auto()
+    MissingDocumentation = auto()
+    MissingUnit = auto()
+    ChoiceValidationError = auto()
+    UnitWithoutField = auto()
+    AttributeForNonExistingField = auto()
+    BrokenLink = auto()
+    FailedNamefitting = auto()
+    NXdataMissingSignalData = auto()
+    NXdataMissingAxisData = auto()
+    NXdataAxisMismatch = auto()
+    KeyToBeRemoved = auto()
+    InvalidConceptForNonVariadic = auto()
+    ReservedSuffixWithoutField = auto()
+    ReservedPrefixInWrongContext = auto()
+    InvalidNexusTypeForNamedConcept = auto()
 
 
 class Collector:
@@ -96,9 +98,9 @@ def _log(self, path: str, log_type: ValidationProblem, value: Optional[Any], *ar
                 f"The value at {path} does not match with the enumerated items from the open enumeration: {value}."
             )
         elif log_type == ValidationProblem.MissingRequiredGroup:
-            logger.warning(f"The required group, {path}, hasn't been supplied.")
+            logger.error(f"The required group, {path}, hasn't been supplied.")
         elif log_type == ValidationProblem.MissingRequiredField:
-            logger.warning(
+            logger.error(
                 f"The data entry corresponding to {path} is required "
                 "and hasn't been supplied by the reader.",
             )
@@ -118,9 +120,9 @@ def _log(self, path: str, log_type: ValidationProblem, value: Optional[Any], *ar
                 f"The value at {path} should be a positive int, but is {value}."
             )
         elif log_type == ValidationProblem.ExpectedGroup:
-            logger.warning(
-                f"Expected a group at {path} but found a field or attribute."
-            )
+            logger.error(f"Expected a group at {path} but found a field or attribute.")
+        elif log_type == ValidationProblem.ExpectedField:
+            logger.error(f"Expected a field at {path} but found a group.")
         elif log_type == ValidationProblem.MissingDocumentation:
             if "@" in path.rsplit("/")[-1]:
                 logger.warning(f"Attribute {path} written without documentation.")
@@ -140,7 +142,7 @@ def _log(self, path: str, log_type: ValidationProblem, value: Optional[Any], *ar
                 "but the field does not exist."
             )
         elif log_type == ValidationProblem.BrokenLink:
-            logger.warning(f"Broken link at {path} to {value}")
+            logger.warning(f"Broken link at {path} to {value}.")
         elif log_type == ValidationProblem.FailedNamefitting:
             logger.warning(f"Found no namefit of {path} in {value}.")
         elif log_type == ValidationProblem.NXdataMissingSignalData:
@@ -152,7 +154,7 @@ def _log(self, path: str, log_type: ValidationProblem, value: Optional[Any], *ar
                 f"Length of axis {path} does not match to {value} in dimension {args[0]}"
             )
         elif log_type == ValidationProblem.KeyToBeRemoved:
-            logger.warning(f"The attribute {path} will not be written.")
+            logger.warning(f"The {value} {path} will not be written.")
         elif log_type == ValidationProblem.InvalidConceptForNonVariadic:
             value = cast(Any, value)
             log_text = f"Given {value.type} name '{path}' conflicts with the non-variadic name '{value}'"
@@ -169,6 +171,12 @@ def _log(self, path: str, log_type: ValidationProblem, value: Optional[Any], *ar
             if value != "<unknown>":
                 log_text += f" It is only valid in the context of {value}."
             logger.error(log_text)
+        elif log_type == ValidationProblem.InvalidNexusTypeForNamedConcept:
+            value = cast(Any, value)
+            logger.error(
+                f"The type ('{args[0] if args else '<unknown>'}') of the given concept '{path}' "
+                f"conflicts with another existing concept of the same name, which is of type '{value.type}'."
+            )
 
     def collect_and_log(
         self,