Add hypothesis harness, tarfile strategies

.gitignore

@@ -0,0 +1,216 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#   Usually these files are written by a python script from a template
+#   before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+# Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+# uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+# poetry.lock
+# poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+# pdm.lock
+# pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+# pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# Redis
+*.rdb
+*.aof
+*.pid
+
+# RabbitMQ
+mnesia/
+rabbitmq/
+rabbitmq-data/
+
+# ActiveMQ
+activemq-data/
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#   JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#   be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#   and can be added to the global gitignore or merged into this file.  For a more nuclear
+#   option (not recommended) you can uncomment the following to ignore the entire idea folder.
+# .idea/
+
+# Abstra
+#   Abstra is an AI-powered process automation framework.
+#   Ignore directories containing user credentials, local state, and settings.
+#   Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#   Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore
+#   that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#   and can be added to the global gitignore or merged into this file. However, if you prefer,
+#   you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Streamlit
+.streamlit/secrets.toml

Makefile

@@ -1,4 +1,4 @@
-all : fuzzer-html fuzzer-email fuzzer-httpclient fuzzer-json fuzzer-difflib fuzzer-csv fuzzer-decode fuzzer-ast fuzzer-tarfile fuzzer-zipfile fuzzer-re fuzzer-configparser fuzzer-tomllib fuzzer-plistlib fuzzer-xml
+all : fuzzer-html fuzzer-email fuzzer-httpclient fuzzer-json fuzzer-difflib fuzzer-csv fuzzer-decode fuzzer-ast fuzzer-tarfile fuzzer-tarfile-hypothesis fuzzer-zipfile fuzzer-re fuzzer-configparser fuzzer-tomllib fuzzer-plistlib fuzzer-xml
 
 PYTHON_CONFIG_PATH=$(CPYTHON_INSTALL_PATH)/bin/python3-config
 CXXFLAGS += $(shell $(PYTHON_CONFIG_PATH) --cflags)
@@ -26,6 +26,8 @@ fuzzer-zipfile:
 	clang++ $(CXXFLAGS) $(LIB_FUZZING_ENGINE) -std=c++17 fuzzer.cpp -DPYTHON_HARNESS_PATH="\"zipfile.py\"" -ldl $(LDFLAGS) -o fuzzer-zipfile
 fuzzer-tarfile:
 	clang++ $(CXXFLAGS) $(LIB_FUZZING_ENGINE) -std=c++17 fuzzer.cpp -DPYTHON_HARNESS_PATH="\"tarfile.py\"" -ldl $(LDFLAGS) -o fuzzer-tarfile
+fuzzer-tarfile-hypothesis:
+	clang++ $(CXXFLAGS) $(LIB_FUZZING_ENGINE) -std=c++17 fuzzer.cpp -DPYTHON_HARNESS_PATH="\"tarfile_hypothesis.py\"" -ldl $(LDFLAGS) -o fuzzer-tarfile-hypothesis
 fuzzer-configparser:
 	clang++ $(CXXFLAGS) $(LIB_FUZZING_ENGINE) -std=c++17 fuzzer.cpp -DPYTHON_HARNESS_PATH="\"configparser.py\"" -ldl $(LDFLAGS) -o fuzzer-configparser
 fuzzer-tomllib:

hypothesis_strategies/fspaths.py

@@ -0,0 +1,71 @@
+# Copyright 2017 Christoph Reiter
+#
+# Permission is hereby granted, free of charge, to any person obtaining
+# a copy of this software and associated documentation files (the
+# "Software"), to deal in the Software without restriction, including
+# without limitation the rights to use, copy, modify, merge, publish,
+# distribute, sublicense, and/or sell copies of the Software, and to
+# permit persons to whom the Software is furnished to do so, subject to
+# the following conditions:
+#
+# The above copyright notice and this permission notice shall be included
+# in all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+# IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
+# CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
+# TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
+# SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+
+import os
+import sys
+
+from vendored.hypothesis.strategies import (
+    composite,
+    sampled_from,
+    lists,
+    integers,
+    binary,
+    randoms,
+)
+
+
+@composite
+def fspaths(draw, max_size: int | None = None) -> str:
+    """A hypothesis strategy which gives valid path values.
+
+    Valid path values are everything which when passed to open() will not raise
+    ValueError or TypeError (but might raise OSError due to file system or
+    operating system restrictions).
+    """
+
+    if os.name == "nt":
+        hight_surrogate = integers(min_value=0xD800, max_value=0xDBFF).map(
+            lambda i: chr(i)
+        )
+        low_surrogate = integers(min_value=0xDC00, max_value=0xDFFF).map(
+            lambda i: chr(i)
+        )
+        uni_char = integers(min_value=1, max_value=sys.maxunicode).map(lambda i: chr(i))
+        any_char = sampled_from(
+            [draw(uni_char), draw(hight_surrogate), draw(low_surrogate)]
+        )
+        any_text = lists(any_char, max_size=max_size).map(lambda l: "".join(l))
+        path_text = any_text
+    else:
+        unix_path_bytes = binary(max_size=max_size).map(lambda b: b.replace(b"\x00", b" "))
+        path_text = unix_path_bytes.map(
+            lambda b: b.decode(sys.getfilesystemencoding(), "surrogateescape")
+        )
+        r = draw(randoms())
+
+        def shuffle_text(t):
+            l = list(t)
+            r.shuffle(l)
+            return "".join(l)
+
+        path_text = path_text.map(shuffle_text)
+
+    return draw(path_text)

hypothesis_strategies/tar.py

@@ -0,0 +1,71 @@
+import io
+import tarfile
+
+import vendored.hypothesis.strategies as st
+from .fspaths import fspaths
+
+
+def tar_integers(
+    format: int, digits: int = 1, allow_negative: bool = False
+) -> st.SearchStrategy[int]:
+    """tar has a unique way of encoding integers that is format-dependent
+    and based on the number of "digits" allowed for a value.
+    """
+    if digits <= 0:
+        raise ValueError("Digits must be greater than one.")
+    if format == tarfile.GNU_FORMAT:
+        min_value = -(256 ** (digits - 1)) if allow_negative else 0
+        max_value = (256 ** (digits - 1)) - 1
+    else:
+        min_value = 0
+        max_value = (4**digits) - 1
+    return st.integers(min_value=min_value, max_value=max_value)
+
+
+@st.composite
+def tar_archives(draw):
+    buf = io.BytesIO()
+    format = draw(
+        st.sampled_from((tarfile.GNU_FORMAT, tarfile.PAX_FORMAT, tarfile.USTAR_FORMAT))
+    )
+    tar = tarfile.TarFile(fileobj=buf, format=format, mode="w")
+    types = list(tarfile.REGULAR_TYPES)
+
+    for _ in range(draw(st.integers(min_value=1, max_value=10))):
+        info = tarfile.TarInfo(
+            name=draw(fspaths(max_size=tarfile.LENGTH_NAME))
+        )
+        fileobj = None
+
+        info.type = draw(st.sampled_from(types))
+        info.mode = draw(tar_integers(format=format, digits=8))
+        info.uid = draw(tar_integers(format=format, digits=8))
+        info.gid = draw(tar_integers(format=format, digits=8))
+        info.mtime = draw(tar_integers(format=format, digits=12))
+        info.devmajor = draw(tar_integers(format=format, digits=8))
+        info.devminor = draw(tar_integers(format=format, digits=8))
+
+        if draw(st.booleans()):
+            info.linkname = draw(fspaths(max_size=tarfile.LENGTH_LINK))
+
+        def maybe_set_pax_header(obj, name, value):
+            if draw(st.booleans()):
+                obj.pax_headers[name] = value
+
+        if format == tarfile.PAX_FORMAT:
+            maybe_set_pax_header(info, "uname", draw(st.text(max_size=32)))
+            maybe_set_pax_header(info, "gname", draw(st.text(max_size=32)))
+            maybe_set_pax_header(
+                info,
+                "path",
+                draw(fspaths(max_size=tarfile.LENGTH_NAME)),
+            )
+            maybe_set_pax_header(
+                info,
+                "linkpath",
+                draw(fspaths(max_size=tarfile.LENGTH_LINK)),
+            )
+
+        tar.addfile(info, fileobj=fileobj)
+
+    return buf.getvalue()

tarfile_hypothesis.py

@@ -0,0 +1,15 @@
+import io
+import tarfile
+
+from vendored.hypothesis import given
+from hypothesis_strategies import tar
+
+
+
+@given(tar.tar_archives())
+def tar_archive_fuzz_target(tar_archive: bytes) -> None:
+    tarfile.TarFile(fileobj=io.BytesIO(tar_archive))
+
+
+# Exposes the Hypothesis fuzz target for integrating with OSS-Fuzz.
+FuzzerRunOne = tar_archive_fuzz_target.hypothesis.fuzz_one_input