mercurial/hgweb/wsgicgi.py

sidedatacopies: only store an entry if it has values

This will make for a shorter storage and help use to write faster code in simple
case. This change already provided a speed boost for copy tracing.

For example here is combined time of running copies tracing on a 6989 pairs of
revision on the pypy repos:

before: 771s
after:  631s - 18%

This also has a very positive impact on changelog size. For example here are the
number for the `00changelog.d` file of pypy.

before: 30449712 Bytes
after:  24973718 Bytes - 18%

This give an overall quite acceptable overhead for storing copies into the
changelog:

filelog-only: 23370586
sidedata:     24973718 Bytes + 7%

Differential Revision: https://phab.mercurial-scm.org/D7068

# hgweb/wsgicgi.py - CGI->WSGI translator
#
# Copyright 2006 Eric Hopper <[e-mail]>
#
# 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(r'PATH_INFO', b'')
    if environ.get(r'SERVER_SOFTWARE', r'').startswith(r'Microsoft-IIS'):
        # IIS includes script_name in PATH_INFO
        scriptname = environ[r'SCRIPT_NAME']
        if environ[r'PATH_INFO'].startswith(scriptname):
            environ[r'PATH_INFO'] = environ[r'PATH_INFO'][len(scriptname) :]

    stdin = procutil.stdin
    if environ.get(r'HTTP_EXPECT', r'').lower() == r'100-continue':
        stdin = common.continuereader(stdin, procutil.stdout.write)

    environ[r'wsgi.input'] = stdin
    environ[r'wsgi.errors'] = procutil.stderr
    environ[r'wsgi.version'] = (1, 0)
    environ[r'wsgi.multithread'] = False
    environ[r'wsgi.multiprocess'] = True
    environ[r'wsgi.run_once'] = True

    if environ.get(r'HTTPS', r'off').lower() in (r'on', r'1', r'yes'):
        environ[r'wsgi.url_scheme'] = r'https'
    else:
        environ[r'wsgi.url_scheme'] = r'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:
                exc_info = None  # 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)()