Merge branch 'fix-readonly' of github.com:yibeichan/reproschema-py in…

…to fix-readonly
ReproNim · Nov 27, 2024 · efb170d · efb170d
2 parents b330126 + df7a66f
commit efb170d
Show file tree

Hide file tree

Showing 2 changed files with 61 additions and 42 deletions.
diff --git a/reproschema/redcap2reproschema.py b/reproschema/redcap2reproschema.py
@@ -3,9 +3,9 @@
 import re
 from pathlib import Path
 
+import pandas as pd
 import yaml
 from bs4 import BeautifulSoup
-import pandas as pd
 
 from .context_url import CONTEXTFILE_URL
 from .jsonldutils import get_context_version
@@ -137,10 +137,14 @@ def process_field_properties(data):
         condition = normalize_condition(condition)
     else:
         condition = True
-        
+
     # Check Field Annotation for special flags
     annotation = data.get("Field Annotation", "").upper()
-    if condition and ("@READONLY" in annotation or "@HIDDEN" in annotation or "@CALCTEXT" in annotation):
+    if condition and (
+        "@READONLY" in annotation
+        or "@HIDDEN" in annotation
+        or "@CALCTEXT" in annotation
+    ):
         condition = False
 
     prop_obj = {
@@ -504,24 +508,30 @@ def parse_language_iso_codes(input_string):
     ]
 
 
-def process_csv_with_pandas(csv_file, abs_folder_path, schema_context_url, protocol_name):
+def process_csv_with_pandas(
+    csv_file, abs_folder_path, schema_context_url, protocol_name
+):
     datas = {}
     order = {}
     compute = {}
     languages = []
 
     df = pd.read_csv(csv_file, encoding="utf-8")
-    df = df.applymap(lambda x: x.strip() if isinstance(x, str) else x)  # Clean headers
+    df = df.applymap(
+        lambda x: x.strip() if isinstance(x, str) else x
+    )  # Clean headers
 
     for form_name, group in df.groupby("Form Name"):
         datas[form_name] = group.to_dict(orient="records")
         order[form_name] = []
         compute[form_name] = []
-        os.makedirs(f"{abs_folder_path}/activities/{form_name}/items", exist_ok=True)
+        os.makedirs(
+            f"{abs_folder_path}/activities/{form_name}/items", exist_ok=True
+        )
 
         # TODO: should we bring back the language
-            # if not languages:
-            #    languages = parse_language_iso_codes(row["Field Label"])
+        # if not languages:
+        #    languages = parse_language_iso_codes(row["Field Label"])
 
         for _, row in group.iterrows():
             field_name = row["Variable / Field Name"]
@@ -531,26 +541,31 @@ def process_csv_with_pandas(csv_file, abs_folder_path, schema_context_url, proto
                     row["Choices, Calculations, OR Slider Labels"],
                     field_type=row["Field Type"],
                 )
-                compute[form_name].append({
-                    "variableName": field_name,
-                    "jsExpression": condition,
-                })
+                compute[form_name].append(
+                    {
+                        "variableName": field_name,
+                        "jsExpression": condition,
+                    }
+                )
             elif "@CALCTEXT" in row.get("Field Annotation", "").upper():
                 calc_text = row["Field Annotation"]
                 match = re.search(r"@CALCTEXT\((.*)\)", calc_text)
                 if match:
                     js_expression = match.group(1)
                     js_expression = normalize_condition(js_expression)
-                    compute[form_name].append({
-                        "variableName": field_name,
-                        "jsExpression": js_expression,
-                    })
+                    compute[form_name].append(
+                        {
+                            "variableName": field_name,
+                            "jsExpression": js_expression,
+                        }
+                    )
             else:
                 order[form_name].append(f"items/{field_name}")
 
     os.makedirs(f"{abs_folder_path}/{protocol_name}", exist_ok=True)
     return datas, order, compute, languages
 
+
 # todo adding output path
 def redcap2reproschema(
     csv_file, yaml_file, output_path, schema_context_url=None

diff --git a/reproschema/tests/test_field_property.py b/reproschema/tests/test_field_property.py
@@ -1,4 +1,5 @@
 import csv
+
 import pytest
 
 from ..redcap2reproschema import process_field_properties
@@ -13,63 +14,65 @@ def test_process_field_properties_calctext():
                 "Variable / Field Name": "test_var",
                 "Required Field?": "",
                 "Field Annotation": "@CALCTEXT",
-                "Branching Logic (Show field only if...)": ""
+                "Branching Logic (Show field only if...)": "",
             },
             "expected": {
                 "variableName": "test_var",
                 "isAbout": "items/test_var",
-                "isVis": False
-            }
+                "isVis": False,
+            },
         },
         # Complex CALCTEXT with conditional logic
         {
             "input": {
                 "Variable / Field Name": "parkinsons_diagnosis",
                 "Required Field?": "",
                 "Field Annotation": "@CALCTEXT(if(([diagnosis_parkinsons_gsd_category_1(bradykinesia)] && ([diagnosis_parkinsons_gsd_category_1(tremor)] || [diagnosis_parkinsons_gsd_category_1(rigidity)])), 'Yes', 'No'))",
-                "Branching Logic (Show field only if...)": "[some_other_condition] = 1"
+                "Branching Logic (Show field only if...)": "[some_other_condition] = 1",
             },
             "expected": {
                 "variableName": "parkinsons_diagnosis",
                 "isAbout": "items/parkinsons_diagnosis",
-                "isVis": False
-            }
+                "isVis": False,
+            },
         },
         # CALCTEXT with numerical operations
         {
             "input": {
                 "Variable / Field Name": "bmi",
                 "Required Field?": "",
                 "Field Annotation": "@CALCTEXT([weight]/([height]*[height]))",
-                "Branching Logic (Show field only if...)": "[weight] > 0 and [height] > 0"
+                "Branching Logic (Show field only if...)": "[weight] > 0 and [height] > 0",
             },
             "expected": {
                 "variableName": "bmi",
                 "isAbout": "items/bmi",
-                "isVis": False
-            }
+                "isVis": False,
+            },
         },
         # CALCTEXT with multiple nested conditions
         {
             "input": {
                 "Variable / Field Name": "complex_score",
                 "Required Field?": "",
                 "Field Annotation": "@CALCTEXT(if([score1] > 10 && [score2] < 5, 'High', if([score1] > 5, 'Medium', 'Low')))",
-                "Branching Logic (Show field only if...)": ""
+                "Branching Logic (Show field only if...)": "",
             },
             "expected": {
                 "variableName": "complex_score",
                 "isAbout": "items/complex_score",
-                "isVis": False
-            }
-        }
+                "isVis": False,
+            },
+        },
     ]
-    
+
     for test_case in test_cases:
         result = process_field_properties(test_case["input"])
         for key, expected_value in test_case["expected"].items():
-            assert result[key] == expected_value, \
-                f"Failed for {key} in test case with annotation: {test_case['input']['Field Annotation']}"
+            assert (
+                result[key] == expected_value
+            ), f"Failed for {key} in test case with annotation: {test_case['input']['Field Annotation']}"
+
 
 def test_process_field_properties_mixed_annotations():
     """Test fields with multiple annotations"""
@@ -80,34 +83,35 @@ def test_process_field_properties_mixed_annotations():
                 "Variable / Field Name": "test_var",
                 "Required Field?": "",
                 "Field Annotation": "@CALCTEXT @READONLY",
-                "Branching Logic (Show field only if...)": ""
+                "Branching Logic (Show field only if...)": "",
             },
-            "expected": {"isVis": False}
+            "expected": {"isVis": False},
         },
         # CALCTEXT with HIDDEN
         {
             "input": {
                 "Variable / Field Name": "test_var",
                 "Required Field?": "",
                 "Field Annotation": "@HIDDEN @CALCTEXT(if([var1] > 0, 1, 0))",
-                "Branching Logic (Show field only if...)": ""
+                "Branching Logic (Show field only if...)": "",
             },
-            "expected": {"isVis": False}
+            "expected": {"isVis": False},
         },
         # Complex CALCTEXT with other annotations
         {
             "input": {
                 "Variable / Field Name": "test_var",
                 "Required Field?": "",
                 "Field Annotation": "@CALCTEXT(if(([var1] && [var2]), 'Yes', 'No')) @READONLY @HIDDEN-SURVEY",
-                "Branching Logic (Show field only if...)": "[condition] = 1"
+                "Branching Logic (Show field only if...)": "[condition] = 1",
             },
-            "expected": {"isVis": False}
-        }
+            "expected": {"isVis": False},
+        },
     ]
-    
+
     for test_case in test_cases:
         result = process_field_properties(test_case["input"])
         for key, expected_value in test_case["expected"].items():
-            assert result[key] == expected_value, \
-                f"Failed for {key} in test case with annotation: {test_case['input']['Field Annotation']}"
+            assert (
+                result[key] == expected_value
+            ), f"Failed for {key} in test case with annotation: {test_case['input']['Field Annotation']}"