view contrib/fuzz/dirstate.cc @ 47346:f27f2afb15da

dirstate-tree: Skip readdir() in `hg status -mard`

When running the status algorithm in a mode where we don’t list unknown
or ignored files, all we care about are files that are listed in the dirstate.
We can there for skip making expensive calls to readdir() to list the contents
of filesystem directories, and instead only run stat() to get the filesystem
state of files listed in the dirstate. (This state may be an error for files
that don’t exist anymore on the filesystem.)

On 16 CPU threads, this reduces the time spent in the `status()` function for
`hg status -mard` on an old snapshot of mozilla-central from ~70ms to ~50ms.

Differential Revision: https://phab.mercurial-scm.org/D10752

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

#include <string>

#include "pyutil.h"

extern "C" {

static PYCODETYPE *code;

extern "C" int LLVMFuzzerInitialize(int *argc, char ***argv)
{
	contrib::initpy(*argv[0]);
	code = (PYCODETYPE *)Py_CompileString(R"py(
try:
    dmap = {}
    copymap = {}
    p = parsers.parse_dirstate(dmap, copymap, data)
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)
{
	PyObject *text =
	    PyBytes_FromStringAndSize((const char *)Data, (Py_ssize_t)Size);
	PyObject *locals = PyDict_New();
	PyDict_SetItemString(locals, "data", text);
	PyObject *res = PyEval_EvalCode(code, contrib::pyglobals(), locals);
	if (!res) {
		PyErr_Print();
	}
	Py_XDECREF(res);
	Py_DECREF(locals);
	Py_DECREF(text);
	return 0; // Non-zero return values are reserved for future use.
}
}