python-multipart 0.0.17__tar.gz → 0.0.19__tar.gz

{python_multipart-0.0.17 → python_multipart-0.0.19}/CHANGELOG.md

@@ -1,5 +1,13 @@
 # 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).
+
 ## 0.0.17 (2024-10-31)
 
 * Handle PermissionError in fallback code for old import name [#182](https://github.com/Kludex/python-multipart/pull/182).

{python_multipart-0.0.17 → python_multipart-0.0.19}/PKG-INFO

@@ -1,14 +1,13 @@
 Metadata-Version: 2.3
 Name: python-multipart
-Version: 0.0.17
+Version: 0.0.19
 Summary: A streaming multipart parser for Python
 Project-URL: Homepage, https://github.com/Kludex/python-multipart
 Project-URL: Documentation, https://kludex.github.io/python-multipart/
 Project-URL: Changelog, https://github.com/Kludex/python-multipart/blob/master/CHANGELOG.md
 Project-URL: Source, https://github.com/Kludex/python-multipart
 Author-email: Andrew Dunham <andrew@du.nham.ca>, Marcelo Trylesinski <marcelotryle@gmail.com>
-License-Expression: Apache-2.0
-License-File: LICENSE.txt
+License: Apache-2.0
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Environment :: Web Environment
 Classifier: Intended Audience :: Developers

{python_multipart-0.0.17 → python_multipart-0.0.19}/pyproject.toml

@@ -44,7 +44,7 @@ dev-dependencies = [
     "PyYAML==6.0.1",
     "invoke==2.2.0",
     "pytest-timeout==2.3.1",
-    "ruff==0.3.4",
+    "ruff==0.8.0",
     "mypy",
     "types-PyYAML",
     "atheris==2.3.0; python_version != '3.12'",
@@ -122,4 +122,4 @@ exclude_lines = [
 ]
 
 [tool.check-sdist]
-git-only = ["docs", "fuzz", "scripts", "mkdocs.yml", "uv.lock"]
+git-only = ["docs", "fuzz", "scripts", "mkdocs.yml", "uv.lock", "SECURITY.md"]

{python_multipart-0.0.17 → python_multipart-0.0.19}/python_multipart/__init__.py

@@ -2,7 +2,7 @@
 __author__ = "Andrew Dunham"
 __license__ = "Apache"
 __copyright__ = "Copyright (c) 2012-2013, Andrew Dunham"
-__version__ = "0.0.17"
+__version__ = "0.0.19"
 
 from .multipart import (
     BaseParser,

{python_multipart-0.0.17 → python_multipart-0.0.19}/python_multipart/multipart.py

@@ -1105,7 +1105,6 @@ class MultipartParser(BaseParser):
                 # Skip leading newlines
                 if c == CR or c == LF:
                     i += 1
-                    self.logger.debug("Skipping leading CR/LF at %d", i)
                     continue
 
                 # index is used as in index into our boundary.  Set to 0.
@@ -1398,9 +1397,14 @@ class MultipartParser(BaseParser):
                     i -= 1
 
             elif state == MultipartState.END:
-                # Do nothing and just consume a byte in the end state.
-                if c not in (CR, LF):
-                    self.logger.warning("Consuming a byte '0x%x' in the end state", c)  # pragma: no cover
+                # 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
+                break
 
             else:  # pragma: no cover (error case)
                 # We got into a strange state somehow!  Just stop processing.

{python_multipart-0.0.17 → python_multipart-0.0.19}/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 io import BytesIO
 from typing import TYPE_CHECKING, cast
 from unittest.mock import Mock
 
+import pytest
 import yaml
 
 from python_multipart.decoders import Base64Decoder, QuotedPrintableDecoder
@@ -825,7 +827,7 @@ class TestFormParser(unittest.TestCase):
             return
 
         # No error!
-        self.assertEqual(processed, len(param["test"]))
+        self.assertEqual(processed, len(param["test"]), param["name"])
 
         # Assert that the parser gave us the appropriate fields/files.
         for e in param["result"]["expected"]:
@@ -1210,6 +1212,68 @@ class TestFormParser(unittest.TestCase):
         self.assertEqual(fields[2].field_name, b"baz")
         self.assertEqual(fields[2].value, b"asdf")
 
+    def test_multipart_parser_newlines_before_first_boundary(self) -> None:
+        """This test makes sure that the parser does not handle when there is junk data after the last boundary."""
+        num = 5_000_000
+        data = (
+            "\r\n" * num + "--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--"
+        )
+
+        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")
+        f.write(data.encode("latin-1"))
+
+    def test_multipart_parser_data_after_last_boundary(self) -> None:
+        """This test makes sure that the parser does not handle when there is junk data after the last boundary."""
+        num = 50_000_000
+        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--" + "-" * num + "\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")
+        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"