ENH: XLSX table template generator works with multiple choice arrays

src/caosadvancedtools/table_json_conversion/table_generator.py

@@ -42,7 +42,8 @@ class ColumnType(Enum):
     SCALAR = 1
     LIST = 2
     FOREIGN = 3
-    IGNORE = 4
+    MULTIPLE_CHOICE = 4
+    IGNORE = 5
 
 
 class RowType(Enum):
@@ -189,15 +190,16 @@ class TableTemplateGenerator(ABC):
 
         # if it is an array, value defs are in 'items'
         if schema.get('type') == 'array':
-            if (schema['items'].get('type') == 'object'
-                    and len(path) > 1):  # list of references; special treatment
+            items = schema['items']
+            # list of references; special treatment
+            if (items.get('type') == 'object' and len(path) > 1):
                 # we add a new sheet with columns generated from the subtree of the schema
                 sheetname = p2s(path)
                 if sheetname in sheets:
                     raise ValueError("The schema would lead to two sheets with the same name, "
                                      f"which is forbidden: {sheetname}")
                 col_def = self._treat_schema_element(
-                    schema=schema['items'], sheets=sheets, path=path, foreign_keys=foreign_keys,
+                    schema=items, sheets=sheets, path=path, foreign_keys=foreign_keys,
                     level_in_sheet_name=len(path),
                     array_paths=array_paths+[path]  # since this level is an array extend the list
                 )
@@ -223,8 +225,23 @@ class TableTemplateGenerator(ABC):
                 # current sheet.
                 return {}
 
+            # List of enums: represent as checkbox columns
+            if (schema.get("uniqueItems") is True and "enum" in items and len(items) == 1):
+                choices = items["enum"]
+                assert len(path) >= 1
+                prop_name = path[-1]
+                result = {}
+                for choice in choices:
+                    name = f"{prop_name}.{choice}"
+                    result[name] = (
+                        ColumnType.MULTIPLE_CHOICE,
+                        schema.get('description'),
+                        path + [str(choice)],
+                    )
+                return result
+
             # it is a list of primitive types -> semicolon separated list
-            schema = schema['items']
+            schema = items
             ctype = ColumnType.LIST
 
         # This should only be the case for "new or existing reference".
@@ -247,9 +264,8 @@ class TableTemplateGenerator(ABC):
             return cols
 
         # The schema is a leaf.
-        description = schema['description'] if 'description' in schema else None
         # definition of a single column
-        default_return = {p2s(path[level_in_sheet_name:]): (ctype, description, path)}
+        default_return = {p2s(path[level_in_sheet_name:]): (ctype, schema.get('description'), path)}
         if 'type' not in schema and 'enum' in schema:
             return default_return
         if 'type' not in schema and 'anyOf' in schema:
@@ -350,12 +366,12 @@ class XLSXTemplateGenerator(TableTemplateGenerator):
             ordered_cols = self._get_ordered_cols(sheetdef)
 
             # create other columns
-            for index, (colname, ct, desc, path) in enumerate(ordered_cols):
-                ws.cell(1, 2 + index, ct.name)
+            for index, (colname, coltype, desc, path) in enumerate(ordered_cols):
+                ws.cell(1, 2 + index, coltype.name)
                 for path_index, el in enumerate(path):
                     ws.cell(2 + path_index, 2 + index, el)
                 ws.cell(header_index, 2 + index, colname)
-                if ct == ColumnType.FOREIGN:
+                if coltype == ColumnType.FOREIGN:
                     # Visual highlighting
                     ws.cell(header_index, 2 + index).fill = yellowfill
                 if desc:

src/doc/table-json-conversion/specs.md

@@ -46,13 +46,15 @@ XLSX file. These properties have an attribute name and a value. The value can be
 a. A primitive (text, number, boolean, ...)
 b. A record
 c. A list of primitive types
-d. A list of records
+d. A list of unique enums (multiple choice)
+e. A list of records
 
 In cases *a.* and *c.*, a cell is created in the column corresponding to the property in the XLSX
 file.  In case *b.*, columns are created for the Properties of the record, where for each of the
-Properties the cases *a.* - *d.* are considered recursively.
+Properties the cases *a.* - *e.* are considered recursively.  Case *d.* leads to a number of
+columns, one for each of the possible choices.
 
-For case *d.* however, the two-dimensional structure of an XLSX sheet is not sufficient. Therefore,
+For case *e.* however, the two-dimensional structure of an XLSX sheet is not sufficient. Therefore,
 for such cases, *new* XLSX sheets/tables are created.
 
 In these sheets/tables, the referenced records are treated as described above (new columns for the
@@ -124,7 +126,31 @@ This entry would be represented in an XLSX sheet with the following content:
 The list elements are written into the cell separated by `;` (semicolon). If the elements contain
 the separator `;`, it is escaped with `\\`.
 
-### d. Properties containing lists with references ###
+### d. Multiple choice properties ###
+
+```JSON
+{
+    "Training": {
+        "date": "2024-04-17",
+        "skills": [
+              "Planning",
+              "Evaluation"
+        ]
+    }
+}
+```
+
+If the `skills` list is denoted as an `enum` array with `"uniqueItems": true` in the json schema,
+this entry would be represented like this in an XLSX:
+
+| date       | skills.Planning | skills.Communication | skills.Evaluation |
+|------------|-----------------|----------------------|-------------------|
+| 2024-04-17 | x               |                      | x                 |
+
+Note that this example assumes that the list of possible choices, as given in the json schema, was
+"Planning, Communication, Evaluation".
+
+### e. Properties containing lists with references ###
 
 ```JSON
 {
@@ -176,7 +202,8 @@ special treatment.  The following values are used:
 
 - ``IGNORE``: This row is ignored.  It can be used for explanatory texts or layout.
 - ``COL_TYPE``: Typically the first row that is not `IGNORE`.  It indicates the row that defines the
-  type of columns (`FOREIGN`, `SCALAR`, `LIST`, `IGNORE`).  This row may occur only once.
+  type of columns (`FOREIGN`, `SCALAR`, `LIST`, `MULTIPLE_CHOICE`, `IGNORE`).  This row must occur
+  exactly once per sheet.
 - ``PATH``: Indicates that the row is used to define the path within the JSON.  These rows are
   typically hidden for users.
 

unittests/table_json_conversion/data/multiple_choice_schema.json

+{
+  "type": "object",
+  "properties": {
+    "Training": {
+      "type": "object",
+      "required": [],
+      "additionalProperties": false,
+      "title": "Training",
+      "properties": {
+        "name": {
+          "type": "string",
+          "description": "The name of the Record to be created"
+        },
+        "date": {
+          "description": "The date of the training.",
+          "anyOf": [
+            {
+              "type": "string",
+              "format": "date"
+            },
+            {
+              "type": "string",
+              "format": "date-time"
+            }
+          ]
+        },
+        "skills": {
+          "description": "Skills that are trained.",
+          "type": "array",
+          "items": {
+            "enum": [
+              "Planning",
+	            "Communication",
+	            "Evaluation"
+            ]
+          },
+          "uniqueItems": true
+        }
+      }
+    }
+  },
+  "required": [
+    "Training"
+  ],
+  "additionalProperties": false,
+  "$schema": "https://json-schema.org/draft/2020-12/schema"
+}

unittests/table_json_conversion/test_table_template_generator.py

@@ -267,6 +267,12 @@ def test_model_with_indirect_reference():
         foreign_keys={"Wrapper": ["Training.name", "Training.url"]},
         outfile=None)
 
+def test_model_with_multiple_choice():
+    _compare_generated_to_known_good(
+        schema_file=rfp("data/multiple_choice_schema.json"),
+        known_good=rfp("data/multiple_choice_template.xlsx"),
+        outfile=None)
+
 
 def test_exceptions():
     # Foreign keys must be lists