mercurial/hgweb/request.py

demandimport: delay loading for "from a import b" with absolute_import

Before this patch, "from a import b" doesn't delay loading module "b",
if absolute_import is enabled, even though "from . import b" does.

For example:

  - it is assumed that extension X has "from P import M" for module M
    under package P with absolute_import feature

  - if importing module M is already delayed before loading extension
    X, loading module M in extension X is delayed until actually
    referring

    util, cmdutil, scmutil or so of Mercurial itself should be
    imported by "from . import M" style before loading extension X

  - otherwise, module M is loaded immediately at loading extension X,
    even if extension X itself isn't used at that "hg" command invocation

    Some minor modules (e.g. filemerge or so) of Mercurial itself
    aren't imported by "from . import M" style before loading
    extension X. And of course, external libraries aren't, too.

This might cause startup performance problem of hg command, because
many bundled extensions already enable absolute_import feature.

To delay loading module for "from a import b" with absolute_import
feature, this patch does below in "from a (or .a) import b" with
absolute_import case:

  1. import root module of "name" by system built-in __import__
     (referred as _origimport)

  2. recurse down the module chain for hierarchical "name"

     This logic can be shared with non absolute_import
     case. Therefore, this patch also centralizes it into chainmodules().

  3. and fall through to process elements in "fromlist" for the leaf
     module of "name"

     Processing elements in "fromlist" is executed in the code path
     after "if _pypy: .... else: ..." clause. Therefore, this patch
     replaces "if _pypy:" with "elif _pypy:" to share it.

At 4f1144c3c72b introducing original "work around" for "from a import
b" case, elements in "fromlist" were imported with "level=level". But
"level" might be grater than 1 (e.g. level=2 in "from .. import b"
case) at demandimport() invocation, and importing direct sub-module in
"fromlist" with level grater than 1 causes unexpected result.

IMHO, this seems main reason of "errors for unknown reason" described
in 4f1144c3c72b, and we don't have to worry about it, because this
issue was already fixed by 78d05778907b.

This is reason why this patch removes "errors for unknown reasons"
comment.

# hgweb/request.py - An http request from either CGI or the standalone server.
#
# Copyright 21 May 2005 - (c) 2005 Jake Edge <[e-mail]>
# Copyright 2005, 2006 Matt Mackall <[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.

from __future__ import absolute_import

import cgi
import errno
import socket

from .common import (
    ErrorResponse,
    HTTP_NOT_MODIFIED,
    statusmessage,
)

from .. import (
    util,
)

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.rpartition('/')[-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