view contrib/fuzz/fm1readmarkers.cc @ 43231:30570a056fa8

sidedatacopies: only store an entry if it has values

This will make for a shorter storage and help use to write faster code in simple
case. This change already provided a speed boost for copy tracing.

For example here is combined time of running copies tracing on a 6989 pairs of
revision on the pypy repos:

before: 771s
after:  631s - 18%

This also has a very positive impact on changelog size. For example here are the
number for the `00changelog.d` file of pypy.

before: 30449712 Bytes
after:  24973718 Bytes - 18%

This give an overall quite acceptable overhead for storing copies into the
changelog:

filelog-only: 23370586
sidedata:     24973718 Bytes + 7%

Differential Revision: https://phab.mercurial-scm.org/D7068

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

#include <string>

#include "pyutil.h"

extern "C" {

static PyCodeObject *code;

extern "C" int LLVMFuzzerInitialize(int *argc, char ***argv)
{
	contrib::initpy(*argv[0]);
	code = (PyCodeObject *)Py_CompileString(R"py(
from parsers import fm1readmarkers
def maybeint(s, default):
    try:
        return int(s)
    except ValueError:
        return default
try:
    parts = data.split('\0', 2)
    if len(parts) == 3:
        offset, stop, data = parts
    elif len(parts) == 2:
        stop, data = parts
        offset = 0
    else:
        offset = stop = 0
    offset, stop = maybeint(offset, 0), maybeint(stop, len(data))
    fm1readmarkers(data, offset, stop)
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.
}
}