fix(excel2json): if gui_order is empty no warning is longer displayed (…

…DEV-3469) (#908)

src/dsp_tools/commands/excel2json/resources.py

@@ -118,14 +118,18 @@ def _row2resource(
     """
 
     class_name = class_info_row["name"]
-    labels = {lang: class_info_row[f"label_{lang}"] for lang in languages if class_info_row.get(f"label_{lang}")}
+    labels = {
+        lang: class_info_row[f"label_{lang}"] for lang in languages if not pd.isna(class_info_row[f"label_{lang}"])
+    }
     if not labels:
-        labels = {lang: class_info_row[lang] for lang in languages if class_info_row.get(lang)}
+        labels = {lang: class_info_row[lang] for lang in languages if not pd.isna(class_info_row[lang])}
     supers = [s.strip() for s in class_info_row["super"].split(",")]
 
     resource = {"name": class_name, "super": supers, "labels": labels}
 
-    comments = {lang: class_info_row[f"comment_{lang}"] for lang in languages if class_info_row.get(f"comment_{lang}")}
+    comments = {
+        lang: class_info_row[f"comment_{lang}"] for lang in languages if not pd.isna(class_info_row[f"comment_{lang}"])
+    }
     if comments:
         resource["comments"] = comments
 
@@ -167,12 +171,17 @@ def _create_all_cardinalities(class_name: str, class_df_with_cardinalities: pd.D
 
 def _check_complete_gui_order(class_name: str, class_df_with_cardinalities: pd.DataFrame) -> pd.DataFrame:
     detail_problem_msg = ""
+    attempt_conversion = False
     if "gui_order" not in class_df_with_cardinalities:
-        detail_problem_msg = "the column 'gui_order' does not exist."
+        pass
+    elif class_df_with_cardinalities["gui_order"].isna().all():
+        pass
     elif class_df_with_cardinalities["gui_order"].isna().any():
         detail_problem_msg = "some rows in the column 'gui_order' are empty."
+    elif not class_df_with_cardinalities["gui_order"].isna().all():
+        attempt_conversion = True
 
-    if not detail_problem_msg:
+    if attempt_conversion:
         try:
             class_df_with_cardinalities["gui_order"] = [int(float(x)) for x in class_df_with_cardinalities["gui_order"]]
             return class_df_with_cardinalities
@@ -184,13 +193,14 @@ def _check_complete_gui_order(class_name: str, class_df_with_cardinalities: pd.D
 
     class_df_with_cardinalities["gui_order"] = list(range(1, len(class_df_with_cardinalities) + 1))
 
-    complete_msg = (
-        f"In the sheet '{class_name}' of the file 'resources.xlsx', "
-        f"{detail_problem_msg}\n"
-        f"Values have been filled in automatically, "
-        f"so that the gui-order reflects the order of the properties in the file."
-    )
-    warnings.warn(complete_msg)
+    if detail_problem_msg:
+        complete_msg = (
+            f"In the sheet '{class_name}' of the file 'resources.xlsx', "
+            f"{detail_problem_msg}\n"
+            f"Values have been filled in automatically, "
+            f"so that the gui-order reflects the order of the properties in the file."
+        )
+        warnings.warn(complete_msg)
     return class_df_with_cardinalities
 
 

src/dsp_tools/commands/excel2json/utils.py

@@ -206,7 +206,7 @@ def get_comments(df_row: pd.Series[Any]) -> dict[str, str] | None:
     Returns:
         A dictionary with the language tag and the content of the cell
     """
-    comments = {lang: df_row[f"comment_{lang}"] for lang in languages if df_row[f"comment_{lang}"] is not pd.NA}
+    comments = {lang: df_row[f"comment_{lang}"] for lang in languages if not pd.isna(df_row[f"comment_{lang}"])}
     return comments or None
 
 

src/dsp_tools/utils/shared.py

@@ -42,7 +42,7 @@ def prepare_dataframe(
     required_columns = [x.strip().lower() for x in required_columns]
     # strip every cell, and insert "" if there is no valid word in it
     new_df = new_df.map(
-        lambda x: str(x).strip() if pd.notna(x) and regex.search(r"[\w\p{L}]", str(x), flags=regex.U) else ""
+        lambda x: str(x).strip() if pd.notna(x) and regex.search(r"[\w\p{L}]", str(x), flags=regex.U) else pd.NA
     )
     # delete rows that don't have the required columns
     for req in required_columns:

test/unittests/commands/excel2json/test_resources.py

@@ -10,15 +10,8 @@
 class TestCheckCompleteGuiOrder:
     def test_column_does_not_exist(self) -> None:
         df = pd.DataFrame({"prop": [1, 2, 3]})
-        expected_msg = (
-            "In the sheet 'class_name' of the file 'resources.xlsx', "
-            "the column 'gui_order' does not exist.\n"
-            "Values have been filled in automatically, "
-            "so that the gui-order reflects the order of the properties in the file."
-        )
         expected_df = pd.DataFrame({"prop": [1, 2, 3], "gui_order": [1, 2, 3]})
-        with pytest.warns(Warning, match=expected_msg):
-            res = _check_complete_gui_order("class_name", df)
+        res = _check_complete_gui_order("class_name", df)
         assert_frame_equal(res, expected_df)
 
     def test_na_in_row(self) -> None:

test/unittests/commands/excel2json/test_utils.py

@@ -163,14 +163,14 @@ def test_get_comments(self) -> None:
                 "comment_en": ["text_en", pd.NA],
                 "comment_de": ["text_de", pd.NA],
                 "comment_fr": ["text_fr", pd.NA],
-                "comment_it": ["text_it", pd.NA],
+                "comment_it": [pd.NA, pd.NA],
                 "comment_rm": ["text_rm", pd.NA],
             }
         )
-        expected_dict = {"de": "text_de", "en": "text_en", "fr": "text_fr", "it": "text_it", "rm": "text_rm"}
+        expected_dict = {"de": "text_de", "en": "text_en", "fr": "text_fr", "rm": "text_rm"}
         returned_dict = utl.get_comments(cast("pd.Series[Any]", original_df.loc[0, :]))
         assert returned_dict
-        self.assertDictEqual(expected_dict, returned_dict)
+        assert expected_dict == returned_dict
 
         assert not utl.get_comments(cast("pd.Series[Any]", original_df.loc[1, :]))
 

test/unittests/utils/test_shared.py

@@ -21,7 +21,7 @@ def test_prepare_dataframe() -> None:
         {
             "title of column 1": ["0-1", "1-n", "0-n"],
             "title of column 2": ["1", "1", "text"],
-            "title of column 3": ["", "", ""],
+            "title of column 3": [pd.NA, pd.NA, pd.NA],
         },
         index=[1, 2, 7],
     )