encoding: add fast path of from/toutf8b() for ASCII strings See the previous patch for why. The added test seems not making much sense because ASCII strings should never contain "\xed" and be valid UTF-8. (with mercurial repo) $ export HGRCPATH=/dev/null HGPLAIN= $ hg log --time --config experimental.stabilization=all -Tjson > /dev/null (original) time: real 6.830 secs (user 6.740+0.000 sys 0.080+0.000) time: real 6.690 secs (user 6.650+0.000 sys 0.040+0.000) time: real 6.700 secs (user 6.640+0.000 sys 0.060+0.000) (fast jsonescape) time: real 5.630 secs (user 5.550+0.000 sys 0.070+0.000) time: real 5.700 secs (user 5.650+0.000 sys 0.050+0.000) time: real 5.690 secs (user 5.640+0.000 sys 0.050+0.000) (this patch) time: real 5.190 secs (user 5.120+0.000 sys 0.070+0.000) time: real 5.230 secs (user 5.170+0.000 sys 0.050+0.000) time: real 5.220 secs (user 5.150+0.000 sys 0.070+0.000)

     1

from __future__ import absolute_import

     2

     3

import unittest

     4

     5

from mercurial import (

     6

    encoding,

     7

)

     8

     9

class IsasciistrTest(unittest.TestCase):

    10

    asciistrs = [

    11

        b'a',

    12

        b'ab',

    13

        b'abc',

    14

        b'abcd',

    15

        b'abcde',

    16

        b'abcdefghi',

    17

        b'abcd\0fghi',

    18

    ]

    19

    20

    def testascii(self):

    21

        for s in self.asciistrs:

    22

            self.assertTrue(encoding.isasciistr(s))

    23

    24

    def testnonasciichar(self):

    25

        for s in self.asciistrs:

    26

            for i in range(len(s)):

    27

                t = bytearray(s)

    28

                t[i] |= 0x80

    29

                self.assertFalse(encoding.isasciistr(bytes(t)))

    30

    31

class LocalEncodingTest(unittest.TestCase):

    32

    def testasciifastpath(self):

    33

        s = b'\0' * 100

    34

        self.assertTrue(s is encoding.tolocal(s))

    35

        self.assertTrue(s is encoding.fromlocal(s))

    36

    37

class Utf8bEncodingTest(unittest.TestCase):

    38

    def testasciifastpath(self):

    39

        s = b'\0' * 100

    40

        self.assertTrue(s is encoding.toutf8b(s))

    41

        self.assertTrue(s is encoding.fromutf8b(s))

    42

    43

if __name__ == '__main__':

    44

    import silenttestrunner

    45

    silenttestrunner.main(__name__)