contrib/fuzz/revlog.cc

posix: always seek to EOF when opening a file in append mode

Python 3 already does this, so skip it there.

Consider the program:

   #include <stdio.h>

   int main() {
     FILE *f = fopen("narf", "w");
     fprintf(f, "narf\n");
     fclose(f);

     f = fopen("narf", "a");
     printf("%ld\n", ftell(f));
     fprintf(f, "troz\n");
     printf("%ld\n", ftell(f));

     return 0;
   }

on macOS, FreeBSD, and Linux with glibc, this program prints

   5
   10

but on musl libc (Alpine Linux and probably others) this prints

   0
   10

By my reading of
https://pubs.opengroup.org/onlinepubs/009695399/functions/fopen.html
this is technically correct, specifically:

> Opening a file with append mode (a as the first character in the
> mode argument) shall cause all subsequent writes to the file to be
> forced to the then current end-of-file, regardless of intervening
> calls to fseek().

in other words, the file position doesn't really matter in append-mode
files, and we can't depend on it being at all meaningful unless we
perform a seek() before tell() after open(..., 'a'). Experimentally
after a .write() we can do a .tell() and it'll always be reasonable,
but I'm unclear from reading the specification if that's a smart thing
to rely on. This matches what we do on Windows and what Python 3 does
for free, so let's just be consistent. Thanks to Yuya for the idea.

#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 parse_index2
for inline in (True, False):
    try:
        index, cache = parse_index2(data, inline)
        index.slicechunktodensity(list(range(len(index))), 0.5, 262144)
        for rev in range(len(index)):
            node = index[rev][7]
            partial = index.shortest(node)
            index.partialmatch(node[:partial])
    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 60k, since we'll just bog
	// down and not accomplish much.
	if (Size > 60000) {
		return 0;
	}
	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.
}
}