fuzz: new fuzzer for dirs.c

fuzz: new fuzzer for dirs.c

This found a six-year-old bug immediately, and then I put it through a
few CPU-days of time before sending it.

Differential Revision: https://phab.mercurial-scm.org/D7031

--- a/contrib/fuzz/Makefile	Tue Oct 08 16:18:15 2019 -0400
+++ b/contrib/fuzz/Makefile	Wed Oct 09 20:48:12 2019 -0700
@@ -105,6 +105,17 @@
 	  -I../../mercurial \
 	  -c -o revlog.o ../../mercurial/cext/revlog.c
 
+dirs_fuzzer: dirs.cc manifest.o charencode.o parsers.o dirs.o pathencode.o revlog.o pyutil.o
+	$(CXX) $(CXXFLAGS) `$$OUT/sanpy/bin/python-config --cflags` \
+	  -Wno-register -Wno-macro-redefined \
+	  -I../../mercurial dirs.cc \
+	  manifest.o charencode.o parsers.o dirs.o pathencode.o revlog.o pyutil.o \
+	  -lFuzzingEngine `$$OUT/sanpy/bin/python-config --ldflags` \
+	  -o $$OUT/dirs_fuzzer
+
+manifest_corpus.zip:
+	python manifest_corpus.py $$OUT/manifest_fuzzer_seed_corpus.zip
+
 manifest_fuzzer: manifest.cc manifest.o charencode.o parsers.o dirs.o pathencode.o revlog.o pyutil.o
 	$(CXX) $(CXXFLAGS) `$$OUT/sanpy/bin/python-config --cflags` \
 	  -Wno-register -Wno-macro-redefined \
@@ -113,9 +124,6 @@
 	  -lFuzzingEngine `$$OUT/sanpy/bin/python-config --ldflags` \
 	  -o $$OUT/manifest_fuzzer
 
-manifest_corpus.zip:
-	python manifest_corpus.py $$OUT/manifest_fuzzer_seed_corpus.zip
-
 revlog_fuzzer: revlog.cc manifest.o charencode.o parsers.o dirs.o pathencode.o revlog.o pyutil.o
 	$(CXX) $(CXXFLAGS) `$$OUT/sanpy/bin/python-config --cflags` \
 	  -Wno-register -Wno-macro-redefined \
@@ -155,6 +163,6 @@
 	  mpatch \
 	  xdiff
 
-oss-fuzz: bdiff_fuzzer mpatch_fuzzer mpatch_corpus.zip xdiff_fuzzer manifest_fuzzer manifest_corpus.zip revlog_fuzzer revlog_corpus.zip dirstate_fuzzer dirstate_corpus.zip fm1readmarkers_fuzzer fm1readmarkers_corpus.zip
+oss-fuzz: bdiff_fuzzer mpatch_fuzzer mpatch_corpus.zip xdiff_fuzzer dirs_fuzzer manifest_fuzzer manifest_corpus.zip revlog_fuzzer revlog_corpus.zip dirstate_fuzzer dirstate_corpus.zip fm1readmarkers_fuzzer fm1readmarkers_corpus.zip
 
 .PHONY: all clean oss-fuzz

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/contrib/fuzz/dirs.cc	Wed Oct 09 20:48:12 2019 -0700
@@ -0,0 +1,56 @@
+#include <Python.h>
+#include <assert.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+#include "pyutil.h"
+
+#include <string>
+
+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 dirs
+try:
+  files = mdata.split('\n')
+  d = dirs(files)
+  list(d)
+  'a' in d
+  if files:
+    files[0] in d
+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;
+	}
+	PyObject *mtext =
+	    PyBytes_FromStringAndSize((const char *)Data, (Py_ssize_t)Size);
+	PyObject *locals = PyDict_New();
+	PyDict_SetItemString(locals, "mdata", mtext);
+	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.
+}
+}