fuzz: new fuzzer for fncache-related functions

fuzz: new fuzzer for fncache-related functions

Not all of these are strictly fncache-related, but they all have th
same signature and similar-enough behavior that we may as well fuzz
them together. No obvious bugs for once, but these felt like they were
just complicated enough to cover.

Differential Revision: https://phab.mercurial-scm.org/D7033

--- a/contrib/fuzz/Makefile	Wed Oct 09 20:49:23 2019 -0700
+++ b/contrib/fuzz/Makefile	Wed Oct 09 20:49:39 2019 -0700
@@ -113,6 +113,14 @@
 	  -lFuzzingEngine `$$OUT/sanpy/bin/python-config --ldflags` \
 	  -o $$OUT/dirs_fuzzer
 
+fncache_fuzzer: fncache.cc manifest.o charencode.o parsers.o dirs.o pathencode.o revlog.o pyutil.o
+	$(CXX) $(CXXFLAGS) `$$OUT/sanpy/bin/python-config --cflags` \
+	  -Wno-register -Wno-macro-redefined \
+	  -I../../mercurial fncache.cc \
+	  manifest.o charencode.o parsers.o dirs.o pathencode.o revlog.o pyutil.o \
+	  -lFuzzingEngine `$$OUT/sanpy/bin/python-config --ldflags` \
+	  -o $$OUT/fncache_fuzzer
+
 manifest_corpus.zip:
 	python manifest_corpus.py $$OUT/manifest_fuzzer_seed_corpus.zip
 
@@ -163,6 +171,6 @@
 	  mpatch \
 	  xdiff
 
-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
+oss-fuzz: bdiff_fuzzer mpatch_fuzzer mpatch_corpus.zip xdiff_fuzzer dirs_fuzzer fncache_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/fncache.cc	Wed Oct 09 20:49:39 2019 -0700
@@ -0,0 +1,78 @@
+#include <Python.h>
+#include <assert.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+#include "pyutil.h"
+
+#include <iostream>
+#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 (
+    isasciistr,
+    asciilower,
+    asciiupper,
+    encodedir,
+    pathencode,
+    lowerencode,
+)
+
+try:
+    for fn in (
+        isasciistr,
+        asciilower,
+        asciiupper,
+        encodedir,
+        pathencode,
+        lowerencode,
+    ):
+        try:
+            fn(data)
+        except UnicodeDecodeError:
+            pass  # some functions emit this exception
+        except AttributeError:
+            # pathencode needs hashlib, which fails to import because the time
+            # module fails to import. We should try and fix that some day, but
+            # for now we at least get coverage on non-hashencoded codepaths.
+            if fn != pathencode:
+                raise
+        # uncomment this for debugging exceptions
+        # except Exception as e:
+        #     raise Exception('%r: %r' % (fn, e))
+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);
+	if (!code) {
+		std::cerr << "failed to compile Python code!" << std::endl;
+	}
+	return 0;
+}
+
+int LLVMFuzzerTestOneInput(const uint8_t *Data, size_t Size)
+{
+	PyObject *mtext =
+	    PyBytes_FromStringAndSize((const char *)Data, (Py_ssize_t)Size);
+	PyObject *locals = PyDict_New();
+	PyDict_SetItemString(locals, "data", 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.
+}
+}