tags-cache: directly perform a monimal walk for hgtagsfnodescache warming
We do something narrower than the path retrieving data. So lets use dedicated
code instead.
This provides further useful speedup:
### data-env-vars.name = mozilla-try-2023-03-22-zstd-sparse-revlog
# benchmark.name = hg.debug.debug-update-cache
# bin-env-vars.hg.flavor = default
# bin-env-vars.hg.py-re2-module = default
# benchmark.variants.pre-state = warm
before-this-series: 19.947581
skip-fnode-filter: 18.916804 (-5.17%, -1.03)
use-rev-num: 17.493725 (-12.30%, -2.45)
this-changesets: 15.919466 (-20.19%, -4.03)
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__)