From e8aeb0db6aea6561ea35886a1955743817ca9c49 Mon Sep 17 00:00:00 2001
From: Yibei Chen <yibeichan@gmail.com>
Date: Mon, 25 Nov 2024 15:31:02 -0500
Subject: [PATCH] change options for slider (#79)

* change options for slider

* fix slider choice and comma error

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
---
 reproschema/redcap2reproschema.py         | 76 ++++++++++++++---------
 reproschema/tests/test_process_choices.py | 17 +++++
 2 files changed, 64 insertions(+), 29 deletions(-)

diff --git a/reproschema/redcap2reproschema.py b/reproschema/redcap2reproschema.py
index 2e93a7d..e6adec3 100644
--- a/reproschema/redcap2reproschema.py
+++ b/reproschema/redcap2reproschema.py
@@ -200,40 +200,43 @@ def process_choices(choices_str, field_name):
 
     choices = []
     choices_value_type = []
-    for ii, choice in enumerate(choices_str.split("|")):
-        choice = (
-            choice.strip()
-        )  # Strip leading/trailing whitespace for each choice
-        parts = [p.strip() for p in choice.split(",")]
-
-        # Handle the case where the choice is something like "1,"
-        if len(parts) == 1:
+    for choice in choices_str.split("|"):
+        choice = choice.strip()
+
+        # Split only on the first comma to separate value from label
+        first_comma_split = choice.split(",", 1)
+        value_part = first_comma_split[0].strip()
+
+        # Get the full label part (keeping all commas and equals signs)
+        if len(first_comma_split) > 1:
+            label_part = first_comma_split[1].strip()
+        else:
+            # Handle cases where there's no comma
             if choice.endswith(","):
-                parts = [parts[0][:-1], ""]
+                label_part = ""
             else:
                 print(
-                    f"Warning: Invalid choice format '{choice}' in a {field_name} field, adding integer as a value"
+                    f"Warning: Invalid choice format '{choice}' in {field_name} field"
                 )
-                parts = [ii, parts[0]]
+                label_part = choice
 
-        # Determine if value should be treated as an integer or string
-        if parts[0] == "0":
-            # Special case for "0", treat it as an integer
+        # Determine value type
+        if value_part == "0":
             value = 0
             choices_value_type.append("xsd:integer")
-        elif parts[0].isdigit() and parts[0][0] == "0":
-            # If it has leading zeros, treat it as a string
-            value = parts[0]
+        elif value_part.isdigit() and value_part[0] == "0":
+            value = value_part
             choices_value_type.append("xsd:string")
         else:
             try:
-                value = int(parts[0])
+                value = int(value_part)
                 choices_value_type.append("xsd:integer")
             except ValueError:
-                value = parts[0]
+                value = value_part
                 choices_value_type.append("xsd:string")
+
         choice_obj = {
-            "name": {"en": " ".join(parts[1:]).strip()},
+            "name": {"en": label_part},
             "value": value,
         }
         choices.append(choice_obj)
@@ -308,15 +311,30 @@ def process_row(
             and value
             and input_type in ["radio", "select", "slider"]
         ):
-            choices, choices_val_type_l = process_choices(
-                value, field_name=field["Variable / Field Name"]
-            )
-            rowData["responseOptions"].update(
-                {
-                    "choices": choices,
-                    "valueType": choices_val_type_l,
-                },  # updating value type for choices (can be int or str)
-            )
+            if input_type == "slider":
+                # For sliders, add both choices and min/max values
+                choices, choices_val_type_l = process_choices(
+                    value, field_name=field["Variable / Field Name"]
+                )
+                rowData["responseOptions"].update(
+                    {
+                        "choices": choices,
+                        "valueType": choices_val_type_l,
+                        "minValue": 0,  # hardcoded for redcap/now
+                        "maxValue": 100,  # hardcoded for redcap/now
+                    }
+                )
+            else:
+                # For radio and select, just process choices normally
+                choices, choices_val_type_l = process_choices(
+                    value, field_name=field["Variable / Field Name"]
+                )
+                rowData["responseOptions"].update(
+                    {
+                        "choices": choices,
+                        "valueType": choices_val_type_l,
+                    }
+                )
         # for now adding only for numerics, sometimes can be string or date.. TODO
         elif (
             SCHEMA_MAP.get(key) in RESPONSE_COND
diff --git a/reproschema/tests/test_process_choices.py b/reproschema/tests/test_process_choices.py
index 147e822..620c157 100644
--- a/reproschema/tests/test_process_choices.py
+++ b/reproschema/tests/test_process_choices.py
@@ -116,6 +116,23 @@ def test_process_choices_spaces_in_values():
     assert sorted(value_types) == ["xsd:string"]
 
 
+def test_process_choices_likert_scale():
+    # Test Likert scale choices with number prefixes in descriptions
+    choices_str = "0, 0=None (Not at all) | 1, 1=Slight (Rare, less than a day or two) | 2, 2=Mild (Several days) | 3, 3=Moderate (More than half the days) | 4, 4=Severe (Nearly every day)"
+    choices, value_types = process_choices(choices_str, "likert_scale")
+    assert choices == [
+        {"name": {"en": "0=None (Not at all)"}, "value": 0},
+        {
+            "name": {"en": "1=Slight (Rare, less than a day or two)"},
+            "value": 1,
+        },
+        {"name": {"en": "2=Mild (Several days)"}, "value": 2},
+        {"name": {"en": "3=Moderate (More than half the days)"}, "value": 3},
+        {"name": {"en": "4=Severe (Nearly every day)"}, "value": 4},
+    ]
+    assert value_types == ["xsd:integer"]
+
+
 # Run pytest if script is called directly
 if __name__ == "__main__":
     pytest.main()