view contrib/fuzz/manifest.cc @ 51723:9367571fea21

cext: correct the argument handling of `b85encode()`

The type stub indicated that this argument is `Optional`, which implies None is
allowed.  I don't see in the documentation where that's the case for `i`[1], and
trying it in `hg debugshell` resulted in the method failing with a TypeError.  I
guess it was typed as an `int` argument because the `p` format unit wasn't added
until Python 3.3[2].

In any event, 2 clients in core (`pvec` and `obsolete`) call this with no
argument supplied, and `mdiff` calls it with True.  So I guess we've avoided the
None arg case, and when no arg is supplied, it defaults to the 0 initialization
of the `pad` variable in C.  Since the `p` format unit accepts both `int` and
None, as well as `bool`, I'm not bothering to bump the module version- this code
is more permissive than it was, in addition to being more correct.

Interestingly, when I first imported the `cext` and `pure` methods in the same
manner as the previous commit, it dropped the `Optional` part of the argument
type when generating `util.pyi`.  No idea why.

[1] https://docs.python.org/3/c-api/arg.html#numbers
[2] https://docs.python.org/3/c-api/arg.html#other-objects

#include <Python.h>
#include <assert.h>
#include <stdlib.h>
#include <unistd.h>

#include "FuzzedDataProvider.h"
#include "pyutil.h"

#include <string>

extern "C" {

static PYCODETYPE *code;

extern "C" int LLVMFuzzerInitialize(int *argc, char ***argv)
{
	contrib::initpy(*argv[0]);
	code = (PYCODETYPE *)Py_CompileString(R"py(
try:
  lm = parsers.lazymanifest(mdata)
  # iterate the whole thing, which causes the code to fully parse
  # every line in the manifest
  for e, _, _ in lm.iterentries():
      # also exercise __getitem__ et al
      lm[e]
      e in lm
      (e + 'nope') in lm
  lm[b'xyzzy'] = (b'\0' * nlen, 'x')
  # do an insert, text should change
  assert lm.text() != mdata, "insert should change text and didn't: %r %r" % (lm.text(), mdata)
  cloned = lm.filtercopy(lambda x: x != 'xyzzy')
  assert cloned.text() == mdata, 'cloned text should equal mdata'
  cloned.diff(lm)
  del lm[b'xyzzy']
  cloned.diff(lm)
  # should be back to the same
  assert lm.text() == mdata, "delete should have restored text but didn't: %r %r" % (lm.text(), mdata)
except Exception as e:
  pass
  # uncomment this print if you're editing this Python code
  # to debug failures.
  # print e
)py",
	                                      "fuzzer", Py_file_input);
	return 0;
}

int LLVMFuzzerTestOneInput(const uint8_t *Data, size_t Size)
{
	// Don't allow fuzzer inputs larger than 100k, since we'll just bog
	// down and not accomplish much.
	if (Size > 100000) {
		return 0;
	}
	FuzzedDataProvider provider(Data, Size);
	Py_ssize_t nodelength = provider.ConsumeBool() ? 20 : 32;
	PyObject *nlen = PyLong_FromSsize_t(nodelength);
	PyObject *mtext =
	    PyBytes_FromStringAndSize((const char *)Data, (Py_ssize_t)Size);
	PyObject *locals = PyDict_New();
	PyDict_SetItemString(locals, "mdata", mtext);
	PyDict_SetItemString(locals, "nlen", nlen);
	PyObject *res = PyEval_EvalCode(code, contrib::pyglobals(), locals);
	if (!res) {
		PyErr_Print();
	}
	Py_XDECREF(res);
	Py_DECREF(locals);
	Py_DECREF(mtext);
	return 0; // Non-zero return values are reserved for future use.
}
}