view mercurial/hgweb/wsgicgi.py @ 35616:706aa203b396

fileset: add a lightweight file filtering language

This patch was inspired by one that Jun Wu authored for the fb-experimental
repo, to avoid using matcher for efficiency[1].  We want a way to specify what
files will be converted to LFS at commit time.  And per discussion, we also want
to specify what files to skip, text diff, or merge in another config option.
The current `lfs.threshold` config option could not satisfy complex needs.  I'm
putting it in a core package because Augie floated the idea of also using it for
narrow and sparse.

Yuya suggested farming out to fileset.parse(), which added support for more
symbols.  The only fileset element not supported here is 'negate'.  (List isn't
supported by filesets either.)  I also changed the 'always' token to the 'all()'
predicate for consistency, and introduced 'none()' to improve readability in a
future tracked file based config.  The extension operator was changed from '.'
to '**', to match how recursive path globs are specified.  Finally, I changed
the path matcher from '/' to 'path:' at Yuya's suggestion, for consistency with
matcher.  Unfortunately, ':' is currently reserved in filesets, so this has to
be quoted to be processed as a string instead of a symbol[2].  We should
probably revisit that, because it's seriously ugly.  But it's only used by an
experimental extension, and I think using a file based config for LFS may drive
some more tweaks, so I'm settling for this for now.

I reserved all of the glob characters in fileset except '.' and '_' for the
extension test because those are likely valid extension characters.

Sample filter settings:

  all()                        # everything
  size(">20MB")                # larger than 20MB
  !**.txt                      # except for .txt files
  **.zip | **.tar.gz | **.7z   # some types of compressed files
  "path:bin"                   # files under "bin" in the project root

[1] https://www.mercurial-scm.org/pipermail/mercurial-devel/2017-December/109387.html
[2] https://www.mercurial-scm.org/pipermail/mercurial-devel/2018-January/109729.html

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

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