view mercurial/hgweb/request.py @ 26375:3686fa2b8eee

windows: insert file positioning call between reads and writes fopen() and fdopen() have a unique-to-Windows requirement that transitions between read and write operations in files opened in modes r+, w+, and a+ perform a file positioning call (fsetpos, fseek, or rewind) in between. While the MSDN docs don't say what will happen if this is not done, observations reveal that Python raises an IOError with errno 0. Furthermore, I /think/ this behavior isn't deterministic. But I can reproduce it reliably with subsequent patches applied that open revlogs in a+ mode and perform both reads and writes. This patch introduces a proxy class for file handles opened in r+, w+, and a+ mode on Windows. The class intercepts calls and audits whether a file positioning function has been called between read and write operations. If not, a dummy, no-op seek to the current file position is performed. This appears to be sufficient to "trick" Windows into allowing transitions between read and writes without raising errors.
author Gregory Szorc <gregory.szorc@gmail.com>
date Sun, 27 Sep 2015 18:46:53 -0700
parents 461e7b700fdf
children 7c1b4840c2cd
line wrap: on
line source

# hgweb/request.py - An http request from either CGI or the standalone server.
#
# Copyright 21 May 2005 - (c) 2005 Jake Edge <jake@edge2.net>
# Copyright 2005, 2006 Matt Mackall <mpm@selenic.com>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

import socket, cgi, errno
from mercurial import util
from common import ErrorResponse, statusmessage, HTTP_NOT_MODIFIED

shortcuts = {
    'cl': [('cmd', ['changelog']), ('rev', None)],
    'sl': [('cmd', ['shortlog']), ('rev', None)],
    'cs': [('cmd', ['changeset']), ('node', None)],
    'f': [('cmd', ['file']), ('filenode', None)],
    'fl': [('cmd', ['filelog']), ('filenode', None)],
    'fd': [('cmd', ['filediff']), ('node', None)],
    'fa': [('cmd', ['annotate']), ('filenode', None)],
    'mf': [('cmd', ['manifest']), ('manifest', None)],
    'ca': [('cmd', ['archive']), ('node', None)],
    'tags': [('cmd', ['tags'])],
    'tip': [('cmd', ['changeset']), ('node', ['tip'])],
    'static': [('cmd', ['static']), ('file', None)]
}

def normalize(form):
    # first expand the shortcuts
    for k in shortcuts.iterkeys():
        if k in form:
            for name, value in shortcuts[k]:
                if value is None:
                    value = form[k]
                form[name] = value
            del form[k]
    # And strip the values
    for k, v in form.iteritems():
        form[k] = [i.strip() for i in v]
    return form

class wsgirequest(object):
    """Higher-level API for a WSGI request.

    WSGI applications are invoked with 2 arguments. They are used to
    instantiate instances of this class, which provides higher-level APIs
    for obtaining request parameters, writing HTTP output, etc.
    """
    def __init__(self, wsgienv, start_response):
        version = wsgienv['wsgi.version']
        if (version < (1, 0)) or (version >= (2, 0)):
            raise RuntimeError("Unknown and unsupported WSGI version %d.%d"
                               % version)
        self.inp = wsgienv['wsgi.input']
        self.err = wsgienv['wsgi.errors']
        self.threaded = wsgienv['wsgi.multithread']
        self.multiprocess = wsgienv['wsgi.multiprocess']
        self.run_once = wsgienv['wsgi.run_once']
        self.env = wsgienv
        self.form = normalize(cgi.parse(self.inp,
                                        self.env,
                                        keep_blank_values=1))
        self._start_response = start_response
        self.server_write = None
        self.headers = []

    def __iter__(self):
        return iter([])

    def read(self, count=-1):
        return self.inp.read(count)

    def drain(self):
        '''need to read all data from request, httplib is half-duplex'''
        length = int(self.env.get('CONTENT_LENGTH') or 0)
        for s in util.filechunkiter(self.inp, limit=length):
            pass

    def respond(self, status, type, filename=None, body=None):
        if self._start_response is not None:
            self.headers.append(('Content-Type', type))
            if filename:
                filename = (filename.split('/')[-1]
                            .replace('\\', '\\\\').replace('"', '\\"'))
                self.headers.append(('Content-Disposition',
                                     'inline; filename="%s"' % filename))
            if body is not None:
                self.headers.append(('Content-Length', str(len(body))))

            for k, v in self.headers:
                if not isinstance(v, str):
                    raise TypeError('header value must be string: %r' % (v,))

            if isinstance(status, ErrorResponse):
                self.headers.extend(status.headers)
                if status.code == HTTP_NOT_MODIFIED:
                    # RFC 2616 Section 10.3.5: 304 Not Modified has cases where
                    # it MUST NOT include any headers other than these and no
                    # body
                    self.headers = [(k, v) for (k, v) in self.headers if
                                    k in ('Date', 'ETag', 'Expires',
                                          'Cache-Control', 'Vary')]
                status = statusmessage(status.code, str(status))
            elif status == 200:
                status = '200 Script output follows'
            elif isinstance(status, int):
                status = statusmessage(status)

            self.server_write = self._start_response(status, self.headers)
            self._start_response = None
            self.headers = []
        if body is not None:
            self.write(body)
            self.server_write = None

    def write(self, thing):
        if thing:
            try:
                self.server_write(thing)
            except socket.error as inst:
                if inst[0] != errno.ECONNRESET:
                    raise

    def writelines(self, lines):
        for line in lines:
            self.write(line)

    def flush(self):
        return None

    def close(self):
        return None

def wsgiapplication(app_maker):
    '''For compatibility with old CGI scripts. A plain hgweb() or hgwebdir()
    can and should now be used as a WSGI application.'''
    application = app_maker()
    def run_wsgi(env, respond):
        return application(env, respond)
    return run_wsgi