ENH: Add support to read notes from excel (openpyxl engine) (pandas-dev#58070)

Co-authored-by: Dacops <[email protected]>

Author: diogomsmiranda

pandas/io/excel/_base.py

@@ -510,6 +510,10 @@ def read_excel(
     if engine_kwargs is None:
         engine_kwargs = {}
 
+        # set to false so cells have a comment attribute
+        if notes is not None and engine == "openpyxl":
+            engine_kwargs = {"read_only": False}
+
     if not isinstance(io, ExcelFile):
         should_close = True
         io = ExcelFile(

pandas/io/excel/_openpyxl.py

@@ -37,6 +37,8 @@
         WriteExcelBuffer,
     )
 
+from pandas.core.frame import DataFrame
+
 
 class OpenpyxlWriter(ExcelWriter):
     _engine = "openpyxl"
@@ -626,11 +628,43 @@ def _convert_cell(self, cell) -> Scalar:
         return cell.value
 
     def get_sheet_data(
-        self, sheet, file_rows_needed: int | None = None
+        self, sheet, file_rows_needed: int | None = None, notes: DataFrame | None = None
     ) -> list[list[Scalar]]:
         if self.book.read_only:
             sheet.reset_dimensions()
 
+        if notes is not None:
+            data_notes = []
+            for row in sheet.rows:
+                row_notes = [
+                    cell.comment.content if cell.comment else "" for cell in row
+                ]
+                data_notes.append(row_notes)
+
+            # trimming trailing empty rows and columns
+            while data_notes and all(cell == "" for cell in data_notes[0]):
+                data_notes.pop(0)
+
+            while data_notes and all(cell == "" for cell in data_notes[-1]):
+                data_notes.pop()
+
+            while data_notes and all(
+                cell == "" for cell in [row[0] for row in data_notes]
+            ):
+                for row in data_notes:
+                    row.pop(0)
+
+            while data_notes and all(
+                cell == "" for cell in [row[-1] for row in data_notes]
+            ):
+                for row in data_notes:
+                    row.pop()
+
+            notes_df = DataFrame(data_notes)
+
+            for col in notes_df.columns:
+                notes[col] = notes_df[col]
+
         data: list[list[Scalar]] = []
         last_row_with_data = -1
         for row_number, row in enumerate(sheet.rows):