mercurial/hgweb/wsgicgi.py

phases: invalidate the phases set less often on retract boundary

We already have the information to update the phase set, so we do so directly
instead of invalidating the cache.

This show a sizeable speedup in our `perf::unbundle` benchmark on the
many-draft mozilla-try repository.

### data-env-vars.name            = mozilla-try-2023-03-22-zstd-sparse-revlog
  # benchmark.name                = hg.perf.perf-unbundle
  # bin-env-vars.hg.flavor        = no-rust
  # bin-env-vars.hg.py-re2-module = default
  # benchmark.variants.issue6528  = disabled

  # benchmark.variants.revs = last-10
before: 2.055259 seconds
after:  1.887064 seconds (-8.18%)
  # benchmark.variants.revs = last-100
before: 2.409239 seconds
after:  2.222429 seconds (-7.75%)
  # benchmark.variants.revs = last-1000
before: 3.945648 seconds
after:  3.762480 seconds (-4.64%)

# 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 .. import encoding, pycompat

from ..utils import procutil

from . import common


def launch(application):
    procutil.setbinary(procutil.stdin)
    procutil.setbinary(procutil.stdout)

    environ = {
        k.decode('iso8859-1'): v.decode('iso8859-1')
        for k, v in encoding.environ.items()
    }  # re-exports
    environ.setdefault('PATH_INFO', '')
    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)()