fuzz: tell manifest fuzzer about longer node hashes

Differential Revision: https://phab.mercurial-scm.org/D8374

contrib/fuzz/manifest.cc

@@ -1,67 +1,72 b''
 #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' * 20, 'x')
+  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.
 }
 }

contrib/fuzz/manifest_corpus.py

@@ -1,33 +1,38 b''
 from __future__ import absolute_import, print_function
 
 import argparse
 import zipfile
 
 ap = argparse.ArgumentParser()
 ap.add_argument("out", metavar="some.zip", type=str, nargs=1)
 args = ap.parse_args()
 
 with zipfile.ZipFile(args.out[0], "w", zipfile.ZIP_STORED) as zf:
     zf.writestr(
         "manifest_zero",
-        '''PKG-INFO\09b3ed8f2b81095a13064402e930565f083346e9a
+        '''\0PKG-INFO\09b3ed8f2b81095a13064402e930565f083346e9a
 README\080b6e76643dcb44d4bc729e932fc464b3e36dbe3
 hg\0b6444347c629cc058d478023905cfb83b7f5bb9d
 mercurial/__init__.py\0b80de5d138758541c5f05265ad144ab9fa86d1db
 mercurial/byterange.py\017f5a9fbd99622f31a392c33ac1e903925dc80ed
 mercurial/fancyopts.py\0b6f52e23e356748c5039313d8b639cda16bf67ba
 mercurial/hg.py\023cc12f225f1b42f32dc0d897a4f95a38ddc8f4a
 mercurial/mdiff.py\0a05f65c44bfbeec6a42336cd2ff0b30217899ca3
 mercurial/revlog.py\0217bc3fde6d82c0210cf56aeae11d05a03f35b2b
 mercurial/transaction.py\09d180df101dc14ce3dd582fd998b36c98b3e39aa
 notes.txt\0703afcec5edb749cf5cec67831f554d6da13f2fb
 setup.py\0ccf3f6daf0f13101ca73631f7a1769e328b472c9
 tkmerge\03c922edb43a9c143682f7bc7b00f98b3c756ebe7
 ''',
     )
-    zf.writestr("badmanifest_shorthashes", "narf\0aa\nnarf2\0aaa\n")
+    zf.writestr("badmanifest_shorthashes", "\0narf\0aa\nnarf2\0aaa\n")
     zf.writestr(
         "badmanifest_nonull",
-        "narf\0cccccccccccccccccccccccccccccccccccccccc\n"
+        "\0narf\0cccccccccccccccccccccccccccccccccccccccc\n"
         "narf2aaaaaaaaaaaaaaaaaaaa\n",
     )
+
+    zf.writestr(
+        "manifest_long_nodes",
+        "\1a\0ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff\n",
+    )