annotate tests/test-encoding-func.py @ 33927:853574db5b12

encoding: add fast path of from/tolocal() for ASCII strings

This is micro optimization, but seems not bad since to/fromlocal() is called
lots of times and isasciistr() is cheap and simple.

We boldly assume that any non-ASCII characters have at least one 8-bit byte.
This isn't true for some email character sets (e.g. ISO-2022-JP and UTF-7),
but I believe no such encodings are used as a platform default. Shift_JIS,
a major crap, is okay as it should have a leading byte in 0x80-0xff range.

  (with mercurial repo)
  $ export HGRCPATH=/dev/null HGPLAIN=
  $ hg log --time --config experimental.stabilization=all > /dev/null

  (original)
  time: real 7.460 secs (user 7.420+0.000 sys 0.030+0.000)
  time: real 7.670 secs (user 7.590+0.000 sys 0.080+0.000)
  time: real 7.560 secs (user 7.510+0.000 sys 0.040+0.000)

  (this patch)
  time: real 7.340 secs (user 7.260+0.000 sys 0.060+0.000)
  time: real 7.260 secs (user 7.210+0.000 sys 0.030+0.000)
  time: real 7.310 secs (user 7.260+0.000 sys 0.060+0.000)

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))

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