mercurial/hgweb/wsgicgi.py

strip: calculate list of extra nodes to save and pass it to changegroupsubset

When we remove revision N from the repository, all revisions >= N are
affected: either it's a descendant from N and will also be removed, or
it's not a descendant of N and will be renumbered.

As a consequence, we have to (at least temporarily) remove all filelog
and manifest revisions that have a linkrev >= N, readding some of them
later.

Unfortunately, it's possible to have a revlog with two revisions
r1 and r2 such that r1 < r2, but linkrev(r1) > linkrev(r2).  If we try
to strip revision linkrev(r1) from the repository, we'll also lose
revision r2 when we truncate this revlog.

We already use changegroupsubset to create a temporary changegroup
containing the revisions that have to be restored, but that function is
unable to detect that we also wanted to save the r2 in the case above.

So we manually calculate these extra nodes and pass it to changegroupsubset.

This should fix issue764.

# 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.stdin)
    util.set_binary(sys.stdout)

    environ = dict(os.environ.items())
    environ.setdefault('PATH_INFO', '')
    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').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

    application(environ, start_response)