view mercurial/hgweb/wsgicgi.py @ 33766:4c706037adef

wireproto: overhaul iterating batcher code (API)

The remote batching code is difficult to read. Let's improve it.

As part of the refactor, the future returned by method calls on
batchiter() instances is now populated. However, you still need to
consume the results() generator for the future to be set.  But at
least now we can stuff the future somewhere and not have to worry
about aligning method call order with result order since you can
use a future to hold the result.

Also as part of the change, we now verify that @batchable generators
yield exactly 2 values. In other words, we enforce their API.

The non-iter batcher has been unused since b6e71f8af5b8. And to my
surprise we had no explicit unit test coverage of it! test-batching.py
has been overhauled to use the iterating batcher.

Since the iterating batcher doesn't allow non-batchable method
calls nor local calls, tests have been updated to reflect reality.
The iterating batcher has been used for multiple releases apparently
without major issue. So this shouldn't cause alarm.

.. api::

   @peer.batchable functions must now yield exactly 2 values

Differential Revision: https://phab.mercurial-scm.org/D319

# 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

from .. import (
    encoding,
    util,
)

from . import (
    common,
)

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

    environ = dict(encoding.environ.iteritems())
    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 = util.stdin
    if environ.get('HTTP_EXPECT', '').lower() == '100-continue':
        stdin = common.continuereader(stdin, util.stdout.write)

    environ['wsgi.input'] = stdin
    environ['wsgi.errors'] = util.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 = util.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' % status)
            for header in response_headers:
                out.write('%s: %s\r\n' % header)
            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)()