view tests/test-encoding-func.py @ 40053:8c692a6b5ad1

fuzz: new fuzzer for cext/manifest.c

This is a bit messy, because lazymanifest is tightly coupled to the
cpython API for performance reasons. As a result, we have to build a
whole Python without pymalloc (so ASAN can help us out) and link
against that. Then we have to use an embedded Python interpreter. We
could manually drive the lazymanifest in C from that point, but
experimentally just using PyEval_EvalCode isn't really any slower so
we may as well do that and write the innermost guts of the fuzzer in
Python.

Leak detection is currently disabled for this fuzzer because there are
a few global-lifetime things in our extensions that we more or less
intentionally leak and I didn't want to take the detour to work around
that for now.

This should not be pushed to our repo until
https://github.com/google/oss-fuzz/pull/1853 is merged, as this
depends on having the Python tarball around.

Differential Revision: https://phab.mercurial-scm.org/D4879

from __future__ import absolute_import

import unittest

from mercurial import (
    encoding,
)

class IsasciistrTest(unittest.TestCase):
    asciistrs = [
        b'a',
        b'ab',
        b'abc',
        b'abcd',
        b'abcde',
        b'abcdefghi',
        b'abcd\0fghi',
    ]

    def testascii(self):
        for s in self.asciistrs:
            self.assertTrue(encoding.isasciistr(s))

    def testnonasciichar(self):
        for s in self.asciistrs:
            for i in range(len(s)):
                t = bytearray(s)
                t[i] |= 0x80
                self.assertFalse(encoding.isasciistr(bytes(t)))

class LocalEncodingTest(unittest.TestCase):
    def testasciifastpath(self):
        s = b'\0' * 100
        self.assertTrue(s is encoding.tolocal(s))
        self.assertTrue(s is encoding.fromlocal(s))

class Utf8bEncodingTest(unittest.TestCase):
    def setUp(self):
        self.origencoding = encoding.encoding

    def tearDown(self):
        encoding.encoding = self.origencoding

    def testasciifastpath(self):
        s = b'\0' * 100
        self.assertTrue(s is encoding.toutf8b(s))
        self.assertTrue(s is encoding.fromutf8b(s))

    def testlossylatin(self):
        encoding.encoding = b'ascii'
        s = u'\xc0'.encode('utf-8')
        l = encoding.tolocal(s)
        self.assertEqual(l, b'?')  # lossy
        self.assertEqual(s, encoding.toutf8b(l))  # utf8 sequence preserved

    def testlosslesslatin(self):
        encoding.encoding = b'latin-1'
        s = u'\xc0'.encode('utf-8')
        l = encoding.tolocal(s)
        self.assertEqual(l, b'\xc0')  # lossless
        self.assertEqual(s, encoding.toutf8b(l))  # convert back to utf-8

    def testlossy0xed(self):
        encoding.encoding = b'euc-kr'  # U+Dxxx Hangul
        s = u'\ud1bc\xc0'.encode('utf-8')
        l = encoding.tolocal(s)
        self.assertIn(b'\xed', l)
        self.assertTrue(l.endswith(b'?'))  # lossy
        self.assertEqual(s, encoding.toutf8b(l))  # utf8 sequence preserved

    def testlossless0xed(self):
        encoding.encoding = b'euc-kr'  # U+Dxxx Hangul
        s = u'\ud1bc'.encode('utf-8')
        l = encoding.tolocal(s)
        self.assertEqual(l, b'\xc5\xed')  # lossless
        self.assertEqual(s, encoding.toutf8b(l))  # convert back to utf-8

if __name__ == '__main__':
    import silenttestrunner
    silenttestrunner.main(__name__)