changeset 33928:6c119dbfd0c0

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)
author Yuya Nishihara <yuya@tcha.org>
date Sun, 23 Apr 2017 13:08:58 +0900
parents 853574db5b12
children 5d2ce90c71f1
files mercurial/encoding.py tests/test-encoding-func.py
diffstat 2 files changed, 10 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- a/mercurial/encoding.py	Sun Apr 23 13:06:23 2017 +0900
+++ b/mercurial/encoding.py	Sun Apr 23 13:08:58 2017 +0900
@@ -494,6 +494,8 @@
     internal surrogate encoding as a UTF-8 string.)
     '''
 
+    if not isinstance(s, localstr) and isasciistr(s):
+        return s
     if "\xed" not in s:
         if isinstance(s, localstr):
             return s._utf8
@@ -544,6 +546,8 @@
     True
     '''
 
+    if isasciistr(s):
+        return s
     # fast path - look for uDxxx prefixes in s
     if "\xed" not in s:
         return s
--- a/tests/test-encoding-func.py	Sun Apr 23 13:06:23 2017 +0900
+++ b/tests/test-encoding-func.py	Sun Apr 23 13:08:58 2017 +0900
@@ -34,6 +34,12 @@
         self.assertTrue(s is encoding.tolocal(s))
         self.assertTrue(s is encoding.fromlocal(s))
 
+class Utf8bEncodingTest(unittest.TestCase):
+    def testasciifastpath(self):
+        s = b'\0' * 100
+        self.assertTrue(s is encoding.toutf8b(s))
+        self.assertTrue(s is encoding.fromutf8b(s))
+
 if __name__ == '__main__':
     import silenttestrunner
     silenttestrunner.main(__name__)