changeset 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)
author Yuya Nishihara <yuya@tcha.org>
date Sun, 23 Apr 2017 13:06:23 +0900
parents f4433f2713d0
children 6c119dbfd0c0
files mercurial/encoding.py tests/test-encoding-func.py
diffstat 2 files changed, 11 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- a/mercurial/encoding.py	Sun Apr 23 12:59:42 2017 +0900
+++ b/mercurial/encoding.py	Sun Apr 23 13:06:23 2017 +0900
@@ -128,6 +128,9 @@
     'foo: \\xc3\\xa4'
     """
 
+    if isasciistr(s):
+        return s
+
     try:
         try:
             # make sure string is actually stored in UTF-8
@@ -170,6 +173,8 @@
     # can we do a lossless round-trip?
     if isinstance(s, localstr):
         return s._utf8
+    if isasciistr(s):
+        return s
 
     try:
         u = s.decode(_sysstr(encoding), _sysstr(encodingmode))
--- a/tests/test-encoding-func.py	Sun Apr 23 12:59:42 2017 +0900
+++ b/tests/test-encoding-func.py	Sun Apr 23 13:06:23 2017 +0900
@@ -28,6 +28,12 @@
                 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__)