mercurial/hgweb/wsgicgi.py

changelog: rework the delayupdate mechanism

The current way we use the 'delayupdate' mechanism is wrong. We call
'delayupdate' right after the transaction retrieval, then we call 'finalize'
right before calling 'tr.close()'. The 'finalize' call will -always- result in a
flush to disk, making the data available to all readers. But the 'tr.close()' may
be a no-op if the transaction is nested. This would result in data:

1) exposed to reader too early,
2) rolled back by other part of the transaction after such exposure

So we need to end up in a situation where we call 'finalize' a single time when
the transaction actually closes. For this purpose we need to be able to call
'delayupdate' and '_writepending' multiple times and 'finalize' once. This was
not possible with the previous state of the code.

This changeset refactors the code to makes this possible. We buffer data in memory
as much as possible and fall-back to writing to a ".a" file after the first call
to '_writepending'.

# 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

import os, sys
from mercurial import util
from mercurial.hgweb import common

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

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

    environ['wsgi.input'] = stdin
    environ['wsgi.errors'] = sys.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 = sys.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)()