##// END OF EJS Templates
diff: do not concatenate immutable bytes while building a/b bodies (issue6445)...
diff: do not concatenate immutable bytes while building a/b bodies (issue6445) Use bytearray instead. I don't know what's changed since Python 2, but bytes concatenation is 100x slow on Python 3. % python2.7 -m timeit -s "s = b''" "for i in range(10000): s += b'line'" 1000 loops, best of 3: 321 usec per loop % python3.9 -m timeit -s "s = b''" "for i in range(10000): s += b'line'" 5 loops, best of 5: 39.2 msec per loop Benchmark using tailwind.css (measuring the fast path, a is empty): % HGRCPATH=/dev/null python2.7 ./hg log -R /tmp/issue6445 -p --time \ --color=always --config diff.word-diff=true >/dev/null (prev) time: real 1.580 secs (user 1.560+0.000 sys 0.020+0.000) (this) time: real 1.610 secs (user 1.570+0.000 sys 0.030+0.000) % HGRCPATH=/dev/null python3.9 ./hg log -R /tmp/issue6445 -p --time \ --color=always --config diff.word-diff=true >/dev/null (prev) time: real 114.500 secs (user 114.460+0.000 sys 0.030+0.000) (this) time: real 2.180 secs (user 2.140+0.000 sys 0.040+0.000) Benchmark using random tabular text data (not the fast path): % dd if=/dev/urandom bs=1k count=1000 | hexdump -v -e '16/1 "%3u," "\n"' > ttf % hg ci -ma % dd if=/dev/urandom bs=1k count=1000 | hexdump -v -e '16/1 "%3u," "\n"' > ttf % hg ci -mb % HGRCPATH=/dev/null python2.7 ./hg log -R /tmp/issue6445 -p --time \ --color=always --config diff.word-diff=true >/dev/null (prev) time: real 3.240 secs (user 3.040+0.000 sys 0.200+0.000 (this) time: real 3.230 secs (user 3.070+0.000 sys 0.160+0.000) % HGRCPATH=/dev/null python3.9 ./hg log -R /tmp/issue6445 -p --time \ --color=always --config diff.word-diff=true >/dev/null (prev) time: real 44.130 secs (user 43.850+0.000 sys 0.270+0.000) (this) time: real 4.170 secs (user 3.850+0.000 sys 0.310+0.000)

File last commit:

r44445:873d0fec default
r46624:210f9b8d stable
Show More
wsgicgi.py
94 lines | 3.0 KiB | text/x-python | PythonLexer
# hgweb/wsgicgi.py - CGI->WSGI translator
#
# Copyright 2006 Eric Hopper <hopper@omnifarious.org>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
#
# This was originally copied from the public domain code at
# http://www.python.org/dev/peps/pep-0333/#the-server-gateway-side
from __future__ import absolute_import
import os
from ..pycompat import getattr
from .. import pycompat
from ..utils import procutil
from . import common
def launch(application):
procutil.setbinary(procutil.stdin)
procutil.setbinary(procutil.stdout)
environ = dict(pycompat.iteritems(os.environ)) # re-exports
environ.setdefault('PATH_INFO', b'')
if environ.get('SERVER_SOFTWARE', '').startswith('Microsoft-IIS'):
# IIS includes script_name in PATH_INFO
scriptname = environ['SCRIPT_NAME']
if environ['PATH_INFO'].startswith(scriptname):
environ['PATH_INFO'] = environ['PATH_INFO'][len(scriptname) :]
stdin = procutil.stdin
if environ.get('HTTP_EXPECT', '').lower() == '100-continue':
stdin = common.continuereader(stdin, procutil.stdout.write)
environ['wsgi.input'] = stdin
environ['wsgi.errors'] = procutil.stderr
environ['wsgi.version'] = (1, 0)
environ['wsgi.multithread'] = False
environ['wsgi.multiprocess'] = True
environ['wsgi.run_once'] = True
if environ.get('HTTPS', 'off').lower() in ('on', '1', 'yes'):
environ['wsgi.url_scheme'] = 'https'
else:
environ['wsgi.url_scheme'] = 'http'
headers_set = []
headers_sent = []
out = procutil.stdout
def write(data):
if not headers_set:
raise AssertionError(b"write() before start_response()")
elif not headers_sent:
# Before the first output, send the stored headers
status, response_headers = headers_sent[:] = headers_set
out.write(b'Status: %s\r\n' % pycompat.bytesurl(status))
for hk, hv in response_headers:
out.write(
b'%s: %s\r\n'
% (pycompat.bytesurl(hk), pycompat.bytesurl(hv))
)
out.write(b'\r\n')
out.write(data)
out.flush()
def start_response(status, response_headers, exc_info=None):
if exc_info:
try:
if headers_sent:
# Re-raise original exception if headers sent
raise exc_info[0](exc_info[1], exc_info[2])
finally:
del exc_info # avoid dangling circular ref
elif headers_set:
raise AssertionError(b"Headers already set!")
headers_set[:] = [status, response_headers]
return write
content = application(environ, start_response)
try:
for chunk in content:
write(chunk)
if not headers_sent:
write(b'') # send headers now if body was empty
finally:
getattr(content, 'close', lambda: None)()