From c4fe4d3cebc08c660e57dd709af1ffa7059b3177 Mon Sep 17 00:00:00 2001
From: Marcelo Trylesinski <marcelotryle@gmail.com>
Date: Sun, 1 Dec 2024 07:59:34 +0100
Subject: [PATCH] Don't warn when CRLF is found after last boundary (#193)

---
 CHANGELOG.md                  |  4 ++++
 python_multipart/__init__.py  |  2 +-
 python_multipart/multipart.py |  4 ++++
 scripts/check                 |  2 +-
 tests/test_multipart.py       | 26 ++++++++++++++++++++++++++
 5 files changed, 36 insertions(+), 2 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 2c7faf0..50074c8 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,5 +1,9 @@
 # Changelog
 
+## 0.0.19 (2024-11-30)
+
+* Don't warn when CRLF is found after last boundary on `MultipartParser` [#193](https://github.com/Kludex/python-multipart/pull/193).
+
 ## 0.0.18 (2024-11-28)
 
 * Hard break if found data after last boundary on `MultipartParser` [#189](https://github.com/Kludex/python-multipart/pull/189).
diff --git a/python_multipart/__init__.py b/python_multipart/__init__.py
index 69a3ed4..d555f80 100644
--- a/python_multipart/__init__.py
+++ b/python_multipart/__init__.py
@@ -2,7 +2,7 @@
 __author__ = "Andrew Dunham"
 __license__ = "Apache"
 __copyright__ = "Copyright (c) 2012-2013, Andrew Dunham"
-__version__ = "0.0.18"
+__version__ = "0.0.19"
 
 from .multipart import (
     BaseParser,
diff --git a/python_multipart/multipart.py b/python_multipart/multipart.py
index be76d24..a996379 100644
--- a/python_multipart/multipart.py
+++ b/python_multipart/multipart.py
@@ -1397,6 +1397,10 @@ def data_callback(name: CallbackName, end_i: int, remaining: bool = False) -> No
                     i -= 1
 
             elif state == MultipartState.END:
+                # Don't do anything if chunk ends with CRLF.
+                if c == CR and i + 1 < length and data[i + 1] == LF:
+                    i += 2
+                    continue
                 # Skip data after the last boundary.
                 self.logger.warning("Skipping data after last boundary")
                 i = length
diff --git a/scripts/check b/scripts/check
index 13ce9ed..bc37333 100755
--- a/scripts/check
+++ b/scripts/check
@@ -6,5 +6,5 @@ SOURCE_FILES="python_multipart multipart tests"
 
 uvx ruff format --check --diff $SOURCE_FILES
 uvx ruff check $SOURCE_FILES
-uvx --with types-PyYAML mypy $SOURCE_FILES
+uv run mypy $SOURCE_FILES
 uvx check-sdist
diff --git a/tests/test_multipart.py b/tests/test_multipart.py
index 7fbeff7..ce92ff4 100644
--- a/tests/test_multipart.py
+++ b/tests/test_multipart.py
@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+import logging
 import os
 import random
 import sys
@@ -9,6 +10,7 @@
 from typing import TYPE_CHECKING, cast
 from unittest.mock import Mock
 
+import pytest
 import yaml
 
 from python_multipart.decoders import Base64Decoder, QuotedPrintableDecoder
@@ -1248,6 +1250,30 @@ def on_file(f: FileProtocol) -> None:
         f = FormParser("multipart/form-data", on_field=Mock(), on_file=on_file, boundary="boundary")
         f.write(data.encode("latin-1"))
 
+    @pytest.fixture(autouse=True)
+    def inject_fixtures(self, caplog: pytest.LogCaptureFixture) -> None:
+        self._caplog = caplog
+
+    def test_multipart_parser_data_end_with_crlf_without_warnings(self) -> None:
+        """This test makes sure that the parser does not handle when the data ends with a CRLF."""
+        data = (
+            "--boundary\r\n"
+            'Content-Disposition: form-data; name="file"; filename="filename.txt"\r\n'
+            "Content-Type: text/plain\r\n\r\n"
+            "hello\r\n"
+            "--boundary--\r\n"
+        )
+
+        files: list[File] = []
+
+        def on_file(f: FileProtocol) -> None:
+            files.append(cast(File, f))
+
+        f = FormParser("multipart/form-data", on_field=Mock(), on_file=on_file, boundary="boundary")
+        with self._caplog.at_level(logging.WARNING):
+            f.write(data.encode("latin-1"))
+            assert len(self._caplog.records) == 0
+
     def test_max_size_multipart(self) -> None:
         # Load test data.
         test_file = "single_field_single_file.http"