titlecase operator

cdisc_rules_engine/check_operators/dataframe_operators.py

@@ -15,14 +15,15 @@
     apply_rounding,
     is_in,
 )
-
+from cdisc_rules_engine.enums.dataset_title_case import DatasetTitleCase
 from cdisc_rules_engine.constants import NULL_FLAVORS
 from cdisc_rules_engine.utilities.utils import dates_overlap, parse_date
 import numpy as np
 import dask.dataframe as dd
 import pandas as pd
 import re
 import operator
+from titlecase import titlecase
 from uuid import uuid4
 from cdisc_rules_engine.models.dataset.dask_dataset import DaskDataset
 from cdisc_rules_engine.models.dataset.dataset_interface import DatasetInterface
@@ -1073,7 +1074,7 @@ def not_contains_all(self, other_value: dict):
     @log_operator_execution
     @type_operator(FIELD_DATAFRAME)
     def invalid_date(self, other_value):
-        target = self.replace_prefix(other_value.get("target"))
+        target = other_value.get("target")
         results = ~vectorized_is_valid(self.value[target])
         return self.value.convert_to_series(results)
 
@@ -1140,7 +1141,7 @@ def is_incomplete_date(self, other_value):
     @log_operator_execution
     @type_operator(FIELD_DATAFRAME)
     def is_complete_date(self, other_value):
-        target = self.replace_prefix(other_value.get("target"))
+        target = other_value.get("target")
         results = vectorized_is_complete_date(self.value[target])
         return self.value.convert_to_series(results)
 
@@ -1944,3 +1945,39 @@ def check_order(row):
     @type_operator(FIELD_DATAFRAME)
     def is_not_ordered_subset_of(self, other_value: dict):
         return ~self.is_ordered_subset_of(other_value)
+
+    @log_operator_execution
+    @type_operator(FIELD_DATAFRAME)
+    def is_title_case(self, other_value: dict):
+        """
+        Checks if target column values are in proper title case.
+        """
+        target = other_value.get("target")
+        acronyms = DatasetTitleCase.Acronyms.value
+        lowercase_exceptions = DatasetTitleCase.Lowercase_Exceptions.value
+
+        def acronym_callback(word, **kwargs):
+            if word.lower() in lowercase_exceptions:
+                return word.lower()
+            if any(word.upper() == acr.upper() for acr in acronyms):
+                return word.upper()
+            return None
+
+        def check_title_case(value):
+            if pd.isna(value) or value == "" or value in NULL_FLAVORS:
+                return True
+            str_value = str(value).strip()
+            expected = titlecase(str_value, callback=acronym_callback)
+            expected = expected[0].upper() + expected[1:]
+            return str_value == expected
+
+        results = self.value[target].apply(check_title_case)
+        return self.value.convert_to_series(results)
+
+    @log_operator_execution
+    @type_operator(FIELD_DATAFRAME)
+    def is_not_title_case(self, other_value: dict):
+        """
+        Checks if target column values are NOT in proper title case.
+        """
+        return ~self.is_title_case(other_value)

cdisc_rules_engine/enums/dataset_title_case.py

@@ -0,0 +1,6 @@
+from cdisc_rules_engine.enums.base_enum import BaseEnum
+
+
+class DatasetTitleCase(BaseEnum):
+    Acronyms = ["ID"]
+    Lowercase_Exceptions = ["per", "and/or", "is", "with"]

requirements.txt

@@ -23,3 +23,4 @@ pyyaml==6.0.2
 redis==4.5.0
 requests~=2.32.3
 setuptools~=75.6.0
+titlecase==2.4.1

resources/schema/rule/Operator.json

@@ -525,6 +525,16 @@
       "properties": { "operator": { "const": "is_not_ordered_subset_of" } },
       "required": ["operator", "value"],
       "type": "object"
+    },
+    {
+      "properties": { "operator": { "const": "is_title_case" } },
+      "required": ["operator"],
+      "type": "object"
+    },
+    {
+      "properties": { "operator": { "const": "is_not_title_case" } },
+      "required": ["operator"],
+      "type": "object"
     }
   ],
   "properties": {

resources/schema/rule/Operator.md

@@ -446,6 +446,29 @@ Complement of `split_parts_have_equal_length`. Returns True when parts have uneq
   separator: "/"
 ```
 
+### is_title_case
+
+Validates that variable labels follow proper title case formatting rules using the titlecase PyPi library. Title case capitalizes the first word and all major words, while keeping articles (a, an, the), conjunctions (and, but, or), and prepositions (in, of, for) in lowercase unless they are the first word.  
+NOTE: The titlecase library may produce false positives or false negatives in syntactic edge cases (e.g. hyphenated words, slash-separated terms, uncommon prepositions).
+
+> Check that AELABEL values are in proper title case
+
+```yaml
+- name: AELABEL
+  operator: is_title_case
+```
+
+### is_not_title_case
+
+Complement of `is_title_case`. Returns True when values are NOT in proper title case.
+
+> Flag AELABEL values that violate title case rules
+
+```yaml
+- name: AELABEL
+  operator: is_not_title_case
+```
+
 ## Date
 
 Date and time specific operations for comparing dates, validating date completeness, checking date formats, and validating ISO-8601 durations.