PyPI - python-multipart - Versions diffs - 0.0.18__tar.gz → 0.0.20__tar.gz - Mend

@@ -130,7 +130,8 @@ class MultipartState(IntEnum):
     PART_DATA_START = 8
     PART_DATA = 9
     PART_DATA_END = 10
-    END = 11
+    END_BOUNDARY = 11
+    END = 12
 # Flags for the multipart parser.
@@ -1119,7 +1120,10 @@ class MultipartParser(BaseParser):
                 # Check to ensure that the last 2 characters in our boundary
                 # are CRLF.
                 if index == len(boundary) - 2:
-                    if c != CR:
+                    if c == HYPHEN:
+                        # Potential empty message.
+                        state = MultipartState.END_BOUNDARY
+                    elif c != CR:
                         # Error!
                         msg = "Did not find CR at end of boundary (%d)" % (i,)
                         self.logger.warning(msg)
@@ -1396,7 +1400,23 @@ class MultipartParser(BaseParser):
                     # the start of the boundary itself.
                     i -= 1
+            elif state == MultipartState.END_BOUNDARY:
+                if index == len(boundary) - 2 + 1:
+                    if c != HYPHEN:
+                        msg = "Did not find - at end of boundary (%d)" % (i,)
+                        self.logger.warning(msg)
+                        e = MultipartParseError(msg)
+                        e.offset = i
+                        raise e
+                    index += 1
+                    self.callback("end")
+                    state = MultipartState.END
             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
@@ -1703,8 +1723,8 @@ class FormParser:
             def _on_end() -> None:
                 nonlocal writer
-                assert writer is not None
-                writer.finalize()
+                if writer is not None:
+                    writer.finalize()
                 if self.on_end is not None:
                     self.on_end()

@@ -1,5 +1,13 @@
 # Changelog
+## 0.0.20 (2024-12-16)
+* Handle messages containing only end boundary [#142](https://github.com/Kludex/python-multipart/pull/142).
+## 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).

@@ -1,13 +1,14 @@
-Metadata-Version: 2.3
+Metadata-Version: 2.4
 Name: python-multipart
-Version: 0.0.18
+Version: 0.0.20
 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: Apache-2.0
+License-Expression: Apache-2.0
+License-File: LICENSE.txt
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Environment :: Web Environment
 Classifier: Intended Audience :: Developers

@@ -47,7 +47,7 @@ dev-dependencies = [
     "ruff==0.8.0",
     "mypy",
     "types-PyYAML",
-    "atheris==2.3.0; python_version != '3.12'",
+    "atheris==2.3.0; python_version <= '3.11'",
     # Documentation
     "mkdocs",
     "mkdocs-material",

@@ -2,7 +2,7 @@
 __author__ = "Andrew Dunham"
 __license__ = "Apache"
 __copyright__ = "Copyright (c) 2012-2013, Andrew Dunham"
-__version__ = "0.0.18"
+__version__ = "0.0.20"
 from .multipart import (
     BaseParser,

@@ -0,0 +1,3 @@
+boundary: --boundary
+expected:
+    error: 13

@@ -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
@@ -1248,6 +1250,30 @@ class TestFormParser(unittest.TestCase):
         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"

	@@ -0,0 +1 @@
1	+ ----boundary--

	@@ -0,0 +1,2 @@
1	+ boundary: --boundary
2	+ expected: []

	@@ -0,0 +1 @@
1	+ ----boundary-X

python-multipart 0.0.18__tar.gz → 0.0.20__tar.gz

python-multipart 0.0.18tar.gz → 0.0.20tar.gz