power-grid-model-io 1.2.89__py3-none-any.whl → 1.2.90__py3-none-any.whl

power_grid_model_io/data_stores/excel_file_store.py

@@ -167,14 +167,16 @@ class ExcelFileStore(BaseDataStore[TabularData]):
         if to_rename:
             columns = data.columns.values.copy()
             for col_idx, new_name in to_rename.items():
+                new_name = new_name[0] if isinstance(new_name, tuple) else new_name
+                full_new_name = (new_name, columns[col_idx][1])
                 self._log.warning(
                     "Column is renamed",
                     sheet_name=sheet_name,
                     col_name=columns[col_idx],
-                    new_name=new_name,
+                    new_name=full_new_name,
                     col_idx=col_idx,
                 )
-                columns[col_idx] = new_name
+                columns[col_idx] = full_new_name
 
             if data.columns.nlevels == 1:
                 data.columns = pd.Index(columns)
@@ -218,7 +220,7 @@ class ExcelFileStore(BaseDataStore[TabularData]):
                 if isinstance(col_name, tuple):
                     to_rename[dup_idx] = (f"{col_name[0]}_{counter}",) + col_name[1:]
                 else:
-                    to_rename[dup_idx] = f"{col_name[0]}_{counter}"
+                    to_rename[dup_idx] = f"{col_name}_{counter}"
 
         return to_rename
 
@@ -253,7 +255,7 @@ class ExcelFileStore(BaseDataStore[TabularData]):
         grouped: Dict[Union[str, Tuple[str, ...]], Set[int]] = {}
         columns = data.columns.values
         for col_idx, col_name in enumerate(columns):
-            if col_name not in grouped:
-                grouped[col_name] = set()
-            grouped[col_name].add(col_idx)
+            if col_name[0] not in grouped:
+                grouped[col_name[0]] = set()
+            grouped[col_name[0]].add(col_idx)
         return grouped

power_grid_model_io/functions/filters.py

@@ -16,7 +16,7 @@ def exclude_empty(row: pd.Series, col: str) -> bool:
     """
     filter out empty
     """
-    if col not in row:        
+    if col not in row:
         raise ValueError(f"The column: '{col}' cannot be found for the filter")
     result = has_value(row[col])
     if isinstance(result, pd.Series):

power_grid_model_io/utils/excel_ambiguity_checker.py

@@ -0,0 +1,165 @@
+# SPDX-FileCopyrightText: Contributors to the Power Grid Model project <powergridmodel@lfenergy.org>
+#
+# SPDX-License-Identifier: MPL-2.0
+"""
+This module provides the ExcelAmbiguityChecker class, which is designed to identify and report ambiguous column names
+within the sheets of an Excel (.xlsx) file. It parses the Excel file, extracts the names of columns from a specified
+row across all sheets, and checks for any duplicates within those names to flag them as ambiguous.
+
+Usage:
+    checker = ExcelAmbiguityChecker(file_path='path/to/excel/file.xlsx', column_name_in_row=0)
+    has_ambiguity, ambiguous_columns = checker.check_ambiguity()
+    if has_ambiguity:
+        print("Ambiguous column names found:", ambiguous_columns)
+    else:
+        print("No ambiguous column names found.")
+
+Requirements:
+    - Python 3.9 or higher (PGM library dependencies)
+    - xml.etree.ElementTree for parsing XML structures within the Excel file.
+    - zipfile to handle the Excel file as a ZIP archive for parsing.
+"""
+import os
+import xml.etree.ElementTree as ET
+import zipfile
+from collections import Counter
+from typing import Dict, List, Optional, Tuple
+
+XML_NAME_SPACE = {"": "http://schemas.openxmlformats.org/spreadsheetml/2006/main"}  # NOSONAR
+WORK_BOOK = "xl/workbook.xml"
+SHARED_STR_PATH = "xl/sharedStrings.xml"
+FIND_T = ".//t"
+FIND_C = ".//c"
+FIND_V = ".//v"
+NAME = "name"
+FIND_ROW = ".//row"
+FIND_SHEET = ".//sheet"
+FIND_TYPE = "t"
+TYPE_STR = "s"
+
+
+class ExcelAmbiguityChecker:
+    """
+    A class to check for ambiguous column names within the sheets of an Excel (.xlsx) file.
+
+    Attributes:
+        _file_path (str): The path to the Excel file to be checked.
+        _col_name_in_row (int): The row index (0-based) where column names are expected. Default is 0.
+        sheets (dict): A dictionary storing sheet names as keys and lists of column names as values.
+
+    Methods:
+        __init__(self, file_path, column_name_in_row=0): Initializes the ExcelAmbiguityChecker instance.
+        _parse_zip(self, zip_file): Parses the shared strings XML file within the Excel ZIP archive.
+        _get_column_names_from_row(self, row, shared_strings): Extracts column names from a specified row.
+        _parse_excel_file(self): Parses the Excel file to extract sheet names and their corresponding column names.
+    """
+
+    def __init__(self, file_path, column_name_in_row=0) -> None:
+        """
+        Initializes the ExcelAmbiguityChecker with the path to an Excel file and the row index for column names.
+
+        Parameters:
+            file_path (str): The path to the Excel file.
+            column_name_in_row (int): The row index (0-based) where column names are expected. Default is 0.
+        """
+        self._valid_file = file_path.endswith(".xlsx") and os.path.exists(file_path)
+        if self._valid_file:
+            self._file_path = file_path
+            self._col_name_in_row = column_name_in_row
+            self.sheets: Dict[str, List[str]] = {}
+            self._parse_excel_file()
+
+    def _parse_zip(self, zip_file) -> List[Optional[str]]:
+        """
+        Parses the shared strings XML file within the Excel ZIP archive to extract all shared strings.
+
+        Parameters:
+            zip_file (zipfile.ZipFile): The opened Excel ZIP file.
+
+        Returns:
+            list: A list of shared strings used in the Excel file.
+        """
+        shared_strings_path = SHARED_STR_PATH
+        shared_strings = []
+        with zip_file.open(shared_strings_path) as f:
+            tree = ET.parse(f)
+            for si in tree.findall(FIND_T, namespaces=XML_NAME_SPACE):
+                shared_strings.append(si.text)
+        return shared_strings
+
+    def _get_column_names_from_row(self, row, shared_strings) -> List[Optional[str]]:
+        """
+        Extracts column names from a specified row using shared strings for strings stored in the shared string table.
+
+        Parameters:
+            row (xml.etree.ElementTree.Element): The XML element representing the row.
+            shared_strings (list): A list of shared strings extracted from the Excel file.
+
+        Returns:
+            list: A list of column names found in the row.
+        """
+        column_names = []
+        for c in row.findall(FIND_C, namespaces=XML_NAME_SPACE):
+            cell_type = c.get(FIND_TYPE)
+            value = c.find(FIND_V, namespaces=XML_NAME_SPACE)
+            if cell_type == TYPE_STR and value is not None:
+                column_names.append(shared_strings[int(value.text)])
+            elif value is not None:
+                column_names.append(value.text)
+            else:
+                column_names.append(None)
+        return column_names
+
+    def _parse_excel_file(self) -> None:
+        """
+        Parses the Excel file to extract sheet names and their corresponding column names.
+        """
+        with zipfile.ZipFile(self._file_path) as z:
+            shared_strings = self._parse_zip(z)
+            workbook_xml = z.read(WORK_BOOK)
+            xml_tree = ET.fromstring(workbook_xml)
+            sheets = xml_tree.findall(FIND_SHEET, namespaces=XML_NAME_SPACE)
+
+            for index, sheet in enumerate(sheets, start=1):
+                sheet_name = str(sheet.get(NAME))
+                sheet_file_path = f"xl/worksheets/sheet{index}.xml"
+
+                with z.open(sheet_file_path) as f:
+                    sheet_tree = ET.parse(f)
+                    rows = sheet_tree.findall(FIND_ROW, namespaces=XML_NAME_SPACE)
+                    if rows:
+                        column_names = self._get_column_names_from_row(rows[self._col_name_in_row], shared_strings)
+                        self.sheets[sheet_name] = [name for name in column_names if name is not None]
+
+    def list_sheets(self) -> List[str]:
+        """
+        Get the list of all sheet names in the Excel file.
+
+        Returns:
+            List[str]: list of all sheet names
+        """
+        return list(self.sheets.keys())
+
+    def check_ambiguity(self) -> Tuple[bool, Dict[str, List[str]]]:
+        """
+        Check if there is ambiguity in column names across sheets.
+
+        Returns:
+            Tuple[bool, Dict[str, List[str]]]: A tuple containing a boolean indicating if any ambiguity was found,
+            and a dictionary with sheet names as keys and lists of ambiguous column names as values.
+        """
+        res: Dict[str, List[str]] = {}
+        if not self._valid_file:
+            return False, res
+        for sheet_name, column_names in self.sheets.items():
+            column_name_counts = Counter(column_names)
+            duplicates = [name for name, count in column_name_counts.items() if count > 1]
+            if duplicates:
+                res[sheet_name] = duplicates
+        return bool(res), res
+
+
+# Example usage
+if __name__ == "__main__":
+    excel_file_checker = ExcelAmbiguityChecker("excel_ambiguity_check_data.xlsx")
+    excel_file_checker.check_ambiguity()

{power_grid_model_io-1.2.89.dist-info → power_grid_model_io-1.2.90.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: power-grid-model-io
-Version: 1.2.89
+Version: 1.2.90
 Summary: Power Grid Model Input/Output
 Author-email: Contributors to the Power Grid Model project <powergridmodel@lfenergy.org>
 License: MPL-2.0

{power_grid_model_io-1.2.89.dist-info → power_grid_model_io-1.2.90.dist-info}/RECORD

@@ -15,7 +15,7 @@ power_grid_model_io/converters/vision_excel_converter.py,sha256=aGEoOh8Y-ZK1O5oS
 power_grid_model_io/data_stores/__init__.py,sha256=qwbj1j-Aa_yRB-E3j35pEVtF3mgH8CVIXAnog5mOry0,138
 power_grid_model_io/data_stores/base_data_store.py,sha256=DJfLtRwvx_tXKnpjtBdfbMqPjWc324Eo5WeKTXjWXqc,1706
 power_grid_model_io/data_stores/csv_dir_store.py,sha256=H8ICXZRLDvp9OkbjkfHnoh4y7uNSXNepHAW6W53VsIw,1877
-power_grid_model_io/data_stores/excel_file_store.py,sha256=Nl5GsC4N6Nf-PpC64wUcdWBgYv2xRt47Rc8CSOaeKi4,10704
+power_grid_model_io/data_stores/excel_file_store.py,sha256=uyEwCzFzIt09QY5aI7D0ZtxBTpBhb81Yw4iOF8FMTv0,10868
 power_grid_model_io/data_stores/json_file_store.py,sha256=0njL2YZn_fImNcZqnIRpHp2UtIS6WGaQQ46TjIK8tyo,3954
 power_grid_model_io/data_stores/vision_excel_file_store.py,sha256=85mZXoXaWpFHy_t-Ra0w4xCIjYK9b2Tr8cFZj3hPIbM,1059
 power_grid_model_io/data_types/__init__.py,sha256=63A_PkOsQkVd3To7Kl4FTUX7lbPG9BS9MSLzXTW6Ktk,383
@@ -23,7 +23,7 @@ power_grid_model_io/data_types/_data_types.py,sha256=9xH5vBGrRVUSlPh4HXmORtKo3LF
 power_grid_model_io/data_types/tabular_data.py,sha256=sV6S4kqCEuQiNZTOdKS7CiA2M8Ny1oGXvtFoN-xkYBg,8582
 power_grid_model_io/functions/__init__.py,sha256=pamhvKX5c_5fkVMRrUp6zhHWex2R63otRJk1Sfsw6y0,495
 power_grid_model_io/functions/_functions.py,sha256=tqwwZ0G8AeDza0IiS6CSMwKB0lV1hDo2D8e9-ARHXQM,2843
-power_grid_model_io/functions/filters.py,sha256=JW36XTVhE2uD0kSge1FQ_kK89WCyMZ0C7D4surgw4v8,1319
+power_grid_model_io/functions/filters.py,sha256=T_Gsy1FPxMx9eQn0rxuok2hXC8sJwb2O2EZsMk_Ccrw,1311
 power_grid_model_io/functions/phase_to_phase.py,sha256=zbaDXIj8S4cLO42LjkpcQoUrEW1frzBUj1OmKu-xkTg,4459
 power_grid_model_io/mappings/__init__.py,sha256=qwbj1j-Aa_yRB-E3j35pEVtF3mgH8CVIXAnog5mOry0,138
 power_grid_model_io/mappings/field_mapping.py,sha256=YfrwKolNG06kIC1sbUYnYmxuOrbNbNo1dYtnF8rNItw,1659
@@ -35,13 +35,14 @@ power_grid_model_io/utils/__init__.py,sha256=qwbj1j-Aa_yRB-E3j35pEVtF3mgH8CVIXAn
 power_grid_model_io/utils/auto_id.py,sha256=H7F00_Lc5fIjxrb0O04esgT-LnpzhPgn_IBg3c-uGZU,4122
 power_grid_model_io/utils/dict.py,sha256=CDZM8iMWpLqfzxiyZZnvIUdWihwuczJQKHpfEGFsf2s,1014
 power_grid_model_io/utils/download.py,sha256=enEoj42ByC5j5rj_iZ1Y9we7t8Nmlwre0-9Njon-Tqg,9457
+power_grid_model_io/utils/excel_ambiguity_checker.py,sha256=MqqmGKTVn_TJ0rNO0KSHauXgJW2K4RmgR-v-NJASxvE,6918
 power_grid_model_io/utils/json.py,sha256=dQDRd2Vb8pfqLU2hTuWYv2cpSIBBbFhd0LOBP21YxJI,3327
 power_grid_model_io/utils/modules.py,sha256=a4IdozSL-sOZcmIQON_aQS7-cpnCyt-3p7zs40wRFkU,928
 power_grid_model_io/utils/parsing.py,sha256=XB1QSHnslIieFJBKFXZCtiydqpOqQBiX_CXDbItXgAQ,4522
 power_grid_model_io/utils/uuid_excel_cvtr.py,sha256=H1iWhW_nluJBUJ3hK-Gc0xJjGnH5e35WrBz_fA3YXZs,7626
 power_grid_model_io/utils/zip.py,sha256=VXHX4xWPPZbhOlZUAbMDy3MgQFzK6_l7sRvGXihNUY4,3875
-power_grid_model_io-1.2.89.dist-info/LICENSE,sha256=7Pm2fWFFHHUG5lDHed1vl5CjzxObIXQglnYsEdtjo_k,14907
-power_grid_model_io-1.2.89.dist-info/METADATA,sha256=JMkJFUJCplvAQ2MOe81QG07AHGaaI8P49taw7QbAAnY,8038
-power_grid_model_io-1.2.89.dist-info/WHEEL,sha256=mguMlWGMX-VHnMpKOjjQidIo1ssRlCFu4a4mBpz1s2M,91
-power_grid_model_io-1.2.89.dist-info/top_level.txt,sha256=7sq9VveemMm2R0RgTBa4tH8y_xF4_1hxbufmX9OjCTo,20
-power_grid_model_io-1.2.89.dist-info/RECORD,,
+power_grid_model_io-1.2.90.dist-info/LICENSE,sha256=7Pm2fWFFHHUG5lDHed1vl5CjzxObIXQglnYsEdtjo_k,14907
+power_grid_model_io-1.2.90.dist-info/METADATA,sha256=9dhMaKJXZfaMqrN4F5qz3DE4pek3gl0XJRd1gWYnp68,8038
+power_grid_model_io-1.2.90.dist-info/WHEEL,sha256=y4mX-SOX4fYIkonsAGA5N0Oy-8_gI4FXw5HNI1xqvWg,91
+power_grid_model_io-1.2.90.dist-info/top_level.txt,sha256=7sq9VveemMm2R0RgTBa4tH8y_xF4_1hxbufmX9OjCTo,20
+power_grid_model_io-1.2.90.dist-info/RECORD,,

{power_grid_model_io-1.2.89.dist-info → power_grid_model_io-1.2.90.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (70.1.1)
+Generator: setuptools (70.2.0)
 Root-Is-Purelib: true
 Tag: py3-none-any