mercurial/hgweb/wsgicgi.py

util._matcher: speed up regexp matching.

In 4babaa52badf, Benoit made a change that substantially slows matching
when a big .hgignore file is in play, because it calls into the regexp
matching engine potentially hundreds of times per file to be matched.

I've partly rolled back his change, so that we only call into the matcher
once per file, but preserved the ability to report a meaningful error
message if there's a syntax error in the regexp.

# 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, incorporated herein by reference.
#
# 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

def launch(application):
    util.set_binary(sys.stdout)

    environ = dict(os.environ.items())
    environ['wsgi.input'] = sys.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') in ('on','1'):
        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

    result = application(environ, start_response)
    try:
        for data in result:
            if data:    # don't send headers until body appears
                write(data)
        if not headers_sent:
            write('')   # send headers now if body was empty
    finally:
        if hasattr(result,'close'):
            result.close()