Update on the CSV helper class with UTF detection for BOM reading

src/corelibs/csv_handling/csv_interface.py

@@ -7,10 +7,13 @@ from typing import Any, Sequence
 from pathlib import Path
 from collections import Counter
 import csv
+from corelibs.file_handling.file_bom_encoding import is_bom_encoded, is_bom_encoded_info
 from corelibs.exceptions.csv_exceptions import (
     NoCsvReader, CompulsoryCsvHeaderCheckFailed, CsvHeaderDataMissing
 )
 
+ENCODING = 'utf-8'
+ENCODING_UTF8_SIG = 'utf-8-sig'
 DELIMITER = ","
 QUOTECHAR = '"'
 # type: _QuotingType
@@ -27,6 +30,7 @@ class CsvWriter:
         file_name: Path,
         header_mapping: dict[str, str],
         header_order: list[str] | None = None,
+        encoding: str = ENCODING,
         delimiter: str = DELIMITER,
         quotechar: str = QUOTECHAR,
         quoting: Any = QUOTING,
@@ -38,6 +42,7 @@ class CsvWriter:
         self.__delimiter = delimiter
         self.__quotechar = quotechar
         self.__quoting = quoting
+        self.__encoding = encoding
         self.csv_file_writer = self.__open_csv(header_order)
 
     def __open_csv(self, header_order: list[str] | None) -> csv.DictWriter[str]:
@@ -69,7 +74,8 @@ class CsvWriter:
         try:
             fp = open(
                 self.__file_name,
-                "w", encoding="utf-8"
+                "w",
+                encoding=self.__encoding
             )
             csv_file_writer = csv.DictWriter(
                 fp,
@@ -109,6 +115,7 @@ class CsvReader:
         self,
         file_name: Path,
         header_check: Sequence[str] | None = None,
+        encoding: str = ENCODING,
         delimiter: str = DELIMITER,
         quotechar: str = QUOTECHAR,
         quoting: Any = QUOTING,
@@ -118,6 +125,7 @@ class CsvReader:
         self.__delimiter = delimiter
         self.__quotechar = quotechar
         self.__quoting = quoting
+        self.__encoding = encoding
         self.header: Sequence[str] | None = None
         self.csv_file_reader = self.__open_csv()
 
@@ -129,9 +137,16 @@ class CsvReader:
             csv.DictReader | None: _description_
         """
         try:
+            # if UTF style check if this is BOM
+            if self.__encoding.lower().startswith('utf-') and is_bom_encoded(self.__file_name):
+                bom_info = is_bom_encoded_info(self.__file_name)
+                if bom_info['encoding'] == 'utf-8':
+                    self.__encoding = ENCODING_UTF8_SIG
+                else:
+                    self.__encoding = bom_info['encoding'] or self.__encoding
             fp = open(
                 self.__file_name,
-                "r", encoding="utf-8"
+                "r", encoding=self.__encoding
             )
             csv_file_reader = csv.DictReader(
                 fp,