mercurial/hgweb/wsgicgi.py

wireprotov2: define and use stream encoders

Now that we have basic support for defining stream encoding, it is
time to start doing something with it.

We define various classes implementing stream encoders/decoders for
the defined encoding profiles. This is relatively straightforward.

We teach the inputstream and outputstream classes how to encode,
decode, and flush data.

We then teach the clientreactor how to filter received data through
the inputstream decoder.

One of the features of the framing format is that streams can span
requests. This is a differentiating feature from say HTTP/2, which
associates streams with requests. By allowing streams to span requests,
we can reuse compression context data across requests/responses. But
in order to do this, we need a mechanism to "flush" the encoder at
logical boundaries so that receivers receive all data where it is
expected. And a "flush" event is distinct from a "finish" event from
the perspective of certain compressors because a "flush" will retain
compression context state whereas a "finish" operation will not. This
is why encoders have both a flush() and a finish() and each uses
specific flushing semantics on the underlying compressor.

The added tests verify various behavior of decoders via clientreactor.
These tests do test some compression behavior via use of outputstream.
But for all intents and purposes, server reactor support for encoding
is not yet implemented.

Differential Revision: https://phab.mercurial-scm.org/D4921

# 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 .. import (
    pycompat,
)

from ..utils import (
    procutil,
)

from . import (
    common,
)

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

    environ = dict(os.environ.iteritems()) # re-exports
    environ.setdefault(r'PATH_INFO', '')
    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("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('Status: %s\r\n' % pycompat.bytesurl(status))
            for hk, hv in response_headers:
                out.write('%s: %s\r\n' % (pycompat.bytesurl(hk),
                                          pycompat.bytesurl(hv)))
            out.write('\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("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('')   # send headers now if body was empty
    finally:
        getattr(content, 'close', lambda: None)()