Strip leading UTF-8 BOM when reading INI files

src/iniconfig/_parse.py

@@ -1,9 +1,11 @@
 from collections.abc import Mapping
+from typing import Final
 from typing import NamedTuple
 
 from .exceptions import ParseError
 
 COMMENTCHARS = "#;"
+UTF8_BOM: Final = "\N{BYTE ORDER MARK}"
 
 
 class ParsedLine(NamedTuple):
@@ -34,6 +36,8 @@ def parse_ini_data(
         - sections_data: mapping of section -> {name -> value}
         - sources: mapping of (section, name) -> line number
     """
+    data = data.removeprefix(UTF8_BOM)
+
     tokens = parse_lines(
         path,
         data.splitlines(True),

testing/test_iniconfig.py

@@ -412,3 +412,23 @@ def test_unicode_whitespace_in_key_names() -> None:
     )
     assert "key" in config["section"]
     assert config["section"]["key"] == "value"
+
+
+def test_utf8_bom_file(tmp_path: Path) -> None:
+    """Files saved with a UTF-8 BOM (common on Windows editors) must parse."""
+    path = tmp_path / "bom.ini"
+    path.write_bytes(b"\xef\xbb\xbf[section]\nkey = value\n")
+    config = IniConfig(path)
+    assert config["section"]["key"] == "value"
+
+
+def test_utf8_bom_in_data_string() -> None:
+    config = IniConfig("x.ini", data="\ufeff[section]\nkey = value\n")
+    assert config["section"]["key"] == "value"
+
+
+def test_parse_utf8_bom_file(tmp_path: Path) -> None:
+    path = tmp_path / "bom.ini"
+    path.write_bytes(b"\xef\xbb\xbf[section]\nkey = value\n")
+    config = IniConfig.parse(path)
+    assert config["section"]["key"] == "value"