From 67640b334133e2304a8d2818657adb89baaee814 Mon Sep 17 00:00:00 2001
From: Tomasz Sowa <t.sowa@ttmath.org>
Date: Thu, 5 Nov 2026 07:54:36 +0100
Subject: [PATCH] allow to skip a BOM mark character when parsing a CSV file

---
 src/csv/csvparser.cpp | 17 +++++++++++++++--
 src/csv/csvparser.h   |  8 +++++++-
 2 files changed, 22 insertions(+), 3 deletions(-)

diff --git a/src/csv/csvparser.cpp b/src/csv/csvparser.cpp
index df7ceb3..a1a7d16 100644
--- a/src/csv/csvparser.cpp
+++ b/src/csv/csvparser.cpp
@@ -5,7 +5,7 @@
  */
 
 /*
- * Copyright (c) 2021, Tomasz Sowa
+ * Copyright (c) 2021-2026, Tomasz Sowa
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -43,7 +43,8 @@ namespace pt
 
 CSVParser::CSVParser()
 {
-	input_as_utf8    = true;
+	input_as_utf8 = true;
+	skip_bom_char = false;
 }
 
 
@@ -139,6 +140,13 @@ CSVParser::Status CSVParser::parse(const std::wstring & str, Space & out_space)
 }
 
 
+bool CSVParser::skip_bom(bool skip_bom_char)
+{
+	bool old_value = this->skip_bom_char;
+	this->skip_bom_char = skip_bom_char;
+	return old_value;
+}
+
 
 void CSVParser::parse()
 {
@@ -148,6 +156,11 @@ void CSVParser::parse()
 	space->set_empty_table();
 	read_char(); // put first character to lastc
 
+	if( skip_bom_char && lastc == 0xFEFF )
+	{
+		read_char(); // skip the BOM mark character
+	}
+
 	if( lastc == -1 )
 	{
 		// an empty file/string, in such a case we return such a space struct (if would be serialized to json): [[]]
diff --git a/src/csv/csvparser.h b/src/csv/csvparser.h
index 176042c..5f991a1 100644
--- a/src/csv/csvparser.h
+++ b/src/csv/csvparser.h
@@ -5,7 +5,7 @@
  */
 
 /*
- * Copyright (c) 2021, Tomasz Sowa
+ * Copyright (c) 2021-2026, Tomasz Sowa
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -73,6 +73,7 @@ public:
 	Status parse(const wchar_t * str,                 Space & out_space);
 	Status parse(const std::wstring & str,            Space & out_space);
 
+	bool skip_bom(bool skip_bom_char);
 
 
 protected:
@@ -83,6 +84,11 @@ protected:
 	*/
 	Status status;
 
+	/*
+	 * if true then skip the BOM mark character (if exists)
+	 * default: false;
+	 */
+	bool skip_bom_char;
 
 	Space * space;