From 5fa94765d68aebf32e738d64a4031dd182c46bf4 Mon Sep 17 00:00:00 2001
From: Philipp Hoffmann <Philipp.Hoffmann@protonmail.com>
Date: Thu, 28 Mar 2024 19:10:56 +0100
Subject: [PATCH] BUG: #57954 encoding ignored for filelike (#57968)

* add exception when encodings exist and do not match

* add exception when encodings exist and do not match

* add test for mismatching encodings warning

* add test for mismatching encodings warning

* add encoding for python 3.10+

* move to _check_file; invert var and condition
---
 pandas/io/parsers/readers.py                 | 11 +++++++++++
 pandas/tests/io/parser/test_c_parser_only.py |  2 +-
 pandas/tests/io/parser/test_textreader.py    |  7 +++++++
 3 files changed, 19 insertions(+), 1 deletion(-)

diff --git a/pandas/io/parsers/readers.py b/pandas/io/parsers/readers.py
index b234a6b78e051..7ecd8cd6d5012 100644
--- a/pandas/io/parsers/readers.py
+++ b/pandas/io/parsers/readers.py
@@ -1310,6 +1310,16 @@ def _check_file_or_buffer(self, f, engine: CSVEngine) -> None:
             raise ValueError(
                 "The 'python' engine cannot iterate through this file buffer."
             )
+        if hasattr(f, "encoding"):
+            file_encoding = f.encoding
+            orig_reader_enc = self.orig_options.get("encoding", None)
+            any_none = file_encoding is None or orig_reader_enc is None
+            if file_encoding != orig_reader_enc and not any_none:
+                file_path = getattr(f, "name", None)
+                raise ValueError(
+                    f"The specified reader encoding {orig_reader_enc} is different "
+                    f"from the encoding {file_encoding} of file {file_path}."
+                )
 
     def _clean_options(
         self, options: dict[str, Any], engine: CSVEngine
@@ -1485,6 +1495,7 @@ def _make_engine(
             "pyarrow": ArrowParserWrapper,
             "python-fwf": FixedWidthFieldParser,
         }
+
         if engine not in mapping:
             raise ValueError(
                 f"Unknown engine: {engine} (valid options are {mapping.keys()})"
diff --git a/pandas/tests/io/parser/test_c_parser_only.py b/pandas/tests/io/parser/test_c_parser_only.py
index 090235c862a2a..98a460f221592 100644
--- a/pandas/tests/io/parser/test_c_parser_only.py
+++ b/pandas/tests/io/parser/test_c_parser_only.py
@@ -511,7 +511,7 @@ def __next__(self):
 def test_buffer_rd_bytes_bad_unicode(c_parser_only):
     # see gh-22748
     t = BytesIO(b"\xb0")
-    t = TextIOWrapper(t, encoding="ascii", errors="surrogateescape")
+    t = TextIOWrapper(t, encoding="UTF-8", errors="surrogateescape")
     msg = "'utf-8' codec can't encode character"
     with pytest.raises(UnicodeError, match=msg):
         c_parser_only.read_csv(t, encoding="UTF-8")
diff --git a/pandas/tests/io/parser/test_textreader.py b/pandas/tests/io/parser/test_textreader.py
index 6aeed2377a3aa..eeb783f1957b7 100644
--- a/pandas/tests/io/parser/test_textreader.py
+++ b/pandas/tests/io/parser/test_textreader.py
@@ -48,6 +48,13 @@ def test_StringIO(self, csv_path):
         reader = TextReader(src, header=None)
         reader.read()
 
+    def test_encoding_mismatch_warning(self, csv_path):
+        # GH-57954
+        with open(csv_path, encoding="UTF-8") as f:
+            msg = "latin1 is different from the encoding"
+            with pytest.raises(ValueError, match=msg):
+                read_csv(f, encoding="latin1")
+
     def test_string_factorize(self):
         # should this be optional?
         data = "a\nb\na\nb\na"