fix utf-8 with bom, fix typo

frappe/core/doctype/file/file.py

@@ -531,15 +531,18 @@ def get_content(self) -> bytes:
 			self.validate_file_url()
 		file_path = self.get_full_path()
 
-		# read the file
+		# read file with proper encoding
 		with open(file_path, mode="rb") as f:
 			self._content = f.read()
-			try:
-				# for plain text files
-				self._content = self._content.decode()
-			except UnicodeDecodeError:
-				# for .png, .jpg, etc
-				pass
+			encodings = ["utf-8-sig", "utf-8", "windows-1250", "windows-1252"]
+			for encoding in encodings:
+				try:
+					# for plain text files
+					self._content = self._content.decode(encoding)
+					break
+				except UnicodeDecodeError:
+					# for .png, .jpg, etc
+					continue
 
 		return self._content
 

frappe/utils/csvutils.py

@@ -40,7 +40,7 @@ def read_csv_content_from_attached_file(doc):
 def read_csv_content(fcontent):
 	if not isinstance(fcontent, str):
 		decoded = False
-		for encoding in ["utf-8", "windows-1250", "windows-1252"]:
+		for encoding in ["utf-8-sig", "utf-8", "windows-1250", "windows-1252"]:
 			try:
 				fcontent = str(fcontent, encoding)
 				decoded = True
@@ -68,7 +68,7 @@ def read_csv_content(fcontent):
 	except csv.Error:
 		# if sniff fails, use default dialect
 		frappe.msgprint(
-			_("Delimiter detection failed. Try enable Custom d elimiters and adjust Delimiter options."),
+			_("Delimiter detection failed. Try enable Custom delimiters and adjust Delimiter options."),
 			indicator="orange",
 			alert=True,
 		)