comparison mercurial/hgweb/request.py @ 43076:2372284d9457

formatting: blacken the codebase

This is using my patch to black
(https://github.com/psf/black/pull/826) so we don't un-wrap collection
literals.

Done with:

  hg files 'set:**.py - mercurial/thirdparty/** - "contrib/python-zstandard/**"' | xargs black -S

# skip-blame mass-reformatting only

# no-check-commit reformats foo_bar functions

Differential Revision: https://phab.mercurial-scm.org/D6971

43075:57875cf423c9

# 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 wsgiref.validate

from ..thirdparty import (
    attr,
)
from .. import (
    error,
    pycompat,
    util,
)

class multidict(object):
    """A dict like object that can store multiple values for a key.

    Used to store parsed request parameters.

    This is inspired by WebOb's class of the same name.
    """
    def __init__(self):
        self._items = {}

    def __getitem__(self, key):
        """Returns the last set value for a key."""

        return vals[0]

    def asdictoflists(self):
        return {k: list(v) for k, v in self._items.iteritems()}

@attr.s(frozen=True)
class parsedrequest(object):
    """Represents a parsed WSGI request.

    # Request body input stream.
    bodyfh = attr.ib()
    # WSGI environment dict, unmodified.
    rawenv = attr.ib()

def parserequestfromenv(env, reponame=None, altbaseurl=None, bodyfh=None):
    """Parse URL components from environment variables.

    WSGI defines request attributes via environment variables. This function
    parses the environment variables into a data structure.

    # PEP 3333 defines the WSGI spec and is a useful reference for this code.

    # We first validate that the incoming object conforms with the WSGI spec.
    # We only want to be dealing with spec-conforming WSGI implementations.
    # TODO enable this once we fix internal violations.
    #wsgiref.validate.check_environ(env)

    # PEP-0333 states that environment keys and values are native strings
    # (bytes on Python 2 and str on Python 3). The code points for the Unicode
    # strings on Python 3 must be between \00000-\000FF. We deal with bytes
    # in Mercurial, so mass convert string keys and values to bytes.
    if pycompat.ispy3:
        env = {k.encode('latin-1'): v for k, v in env.iteritems()}
        env = {k: v.encode('latin-1') if isinstance(v, str) else v
               for k, v in env.iteritems()}

    # Some hosting solutions are emulating hgwebdir, and dispatching directly
    # to an hgweb instance using this environment variable.  This was always
    # checked prior to d7fd203e36cc; keep doing so to avoid breaking them.
    if not reponame:

        if not env.get('PATH_INFO'):
            raise error.ProgrammingError('reponame requires PATH_INFO')

        if not env['PATH_INFO'].startswith(repoprefix):
            raise error.ProgrammingError('PATH_INFO does not begin with repo '
                                         'name: %s (%s)' % (env['PATH_INFO'],
                                                            reponame))

        dispatchpath = env['PATH_INFO'][len(repoprefix):]

        if dispatchpath and not dispatchpath.startswith('/'):
            raise error.ProgrammingError('reponame prefix of PATH_INFO does '
                                         'not end at path delimiter: %s (%s)' %
                                         (env['PATH_INFO'], reponame))

        apppath = apppath.rstrip('/') + repoprefix
        dispatchparts = dispatchpath.strip('/').split('/')
        dispatchpath = '/'.join(dispatchparts)

    # perform case normalization for us. We just rewrite underscore to dash
    # so keys match what likely went over the wire.
    headers = []
    for k, v in env.iteritems():
        if k.startswith('HTTP_'):
            headers.append((k[len('HTTP_'):].replace('_', '-'), v))

    from . import wsgiheaders # avoid cycle
    headers = wsgiheaders.Headers(headers)

    # This is kind of a lie because the HTTP header wasn't explicitly
    # sent. But for all intents and purposes it should be OK to lie about
    # this, since a consumer will either either value to determine how many

        headers['Content-Type'] = env['CONTENT_TYPE']

    if bodyfh is None:
        bodyfh = env['wsgi.input']
        if 'Content-Length' in headers:
            bodyfh = util.cappedreader(bodyfh,
                                       int(headers['Content-Length'] or '0'))

    return parsedrequest(method=env['REQUEST_METHOD'],
                         url=fullurl, baseurl=baseurl,
                         advertisedurl=advertisedfullurl,
                         advertisedbaseurl=advertisedbaseurl,
                         urlscheme=env['wsgi.url_scheme'],
                         remoteuser=env.get('REMOTE_USER'),
                         remotehost=env.get('REMOTE_HOST'),
                         apppath=apppath,
                         dispatchparts=dispatchparts, dispatchpath=dispatchpath,
                         reponame=reponame,
                         querystring=querystring,
                         qsparams=qsparams,
                         headers=headers,
                         bodyfh=bodyfh,
                         rawenv=env)

class offsettrackingwriter(object):
    """A file object like object that is append only and tracks write count.

    Instances are bound to a callable. This callable is called with data

    The intent of this class is to wrap the ``write()`` function returned by
    a WSGI ``start_response()`` function. Since ``write()`` is a callable and
    not a file object, it doesn't implement other file object methods.
    """
    def __init__(self, writefn):
        self._write = writefn
        self._offset = 0

    def write(self, s):

        pass

    def tell(self):
        return self._offset

class wsgiresponse(object):
    """Represents a response to a WSGI request.

    A response consists of a status line, headers, and a body.

        """
        self._req = req
        self._startresponse = startresponse

        self.status = None
        from . import wsgiheaders # avoid cycle
        self.headers = wsgiheaders.Headers([])

        self._bodybytes = None
        self._bodygen = None
        self._bodywillwrite = False
        self._started = False
        self._bodywritefn = None

    def _verifybody(self):
        if (self._bodybytes is not None or self._bodygen is not None
            or self._bodywillwrite):
            raise error.ProgrammingError('cannot define body multiple times')

    def setbodybytes(self, b):
        """Define the response body as static bytes.

        self._started = True

        if not self.status:
            raise error.ProgrammingError('status line not defined')

        if (self._bodybytes is None and self._bodygen is None
            and not self._bodywillwrite):
            raise error.ProgrammingError('response body not defined')

        # RFC 7232 Section 4.1 states that a 304 MUST generate one of
        # {Cache-Control, Content-Location, Date, ETag, Expires, Vary}
        # and SHOULD NOT generate other headers unless they could be used

            if self.headers.get('Content-Length') == '0':
                del self.headers['Content-Length']

            # Strictly speaking, this is too strict. But until it causes
            # problems, let's be strict.
            badheaders = {k for k in self.headers.keys()
                          if k.lower() not in ('date', 'etag', 'expires',
                                               'cache-control',
                                               'content-location',
                                               'content-security-policy',
                                               'vary')}
            if badheaders:
                raise error.ProgrammingError(
                    'illegal header on 304 response: %s' %
                    ', '.join(sorted(badheaders)))

            if self._bodygen is not None or self._bodywillwrite:
                raise error.ProgrammingError("must use setbodybytes('') with "
                                             "304 responses")

        # Various HTTP clients (notably httplib) won't read the HTTP response
        # until the HTTP request has been sent in full. If servers (us) send a
        # response before the HTTP request has been fully sent, the connection
        # may deadlock because neither end is reading.

            while True:
                chunk = self._req.bodyfh.read(32768)
                if not chunk:
                    break

        strheaders = [(pycompat.strurl(k), pycompat.strurl(v)) for
                      k, v in self.headers.items()]
        write = self._startresponse(pycompat.sysstr(self.status),
                                    strheaders)

        if self._bodybytes:
            yield self._bodybytes
        elif self._bodygen:
            for chunk in self._bodygen:

        """
        if not self._bodywillwrite:
            raise error.ProgrammingError('must call setbodywillwrite() first')

        if not self._started:
            raise error.ProgrammingError('must call sendresponse() first; did '
                                         'you remember to consume it since it '
                                         'is a generator?')

        assert self._bodywritefn
        return offsettrackingwriter(self._bodywritefn)

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

43076:2372284d9457

# 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 wsgiref.validate

from ..thirdparty import attr
from .. import (
    error,
    pycompat,
    util,
)


class multidict(object):
    """A dict like object that can store multiple values for a key.

    Used to store parsed request parameters.

    This is inspired by WebOb's class of the same name.
    """

    def __init__(self):
        self._items = {}

    def __getitem__(self, key):
        """Returns the last set value for a key."""

        return vals[0]

    def asdictoflists(self):
        return {k: list(v) for k, v in self._items.iteritems()}


@attr.s(frozen=True)
class parsedrequest(object):
    """Represents a parsed WSGI request.

    # Request body input stream.
    bodyfh = attr.ib()
    # WSGI environment dict, unmodified.
    rawenv = attr.ib()


def parserequestfromenv(env, reponame=None, altbaseurl=None, bodyfh=None):
    """Parse URL components from environment variables.

    WSGI defines request attributes via environment variables. This function
    parses the environment variables into a data structure.

    # PEP 3333 defines the WSGI spec and is a useful reference for this code.

    # We first validate that the incoming object conforms with the WSGI spec.
    # We only want to be dealing with spec-conforming WSGI implementations.
    # TODO enable this once we fix internal violations.
    # wsgiref.validate.check_environ(env)

    # PEP-0333 states that environment keys and values are native strings
    # (bytes on Python 2 and str on Python 3). The code points for the Unicode
    # strings on Python 3 must be between \00000-\000FF. We deal with bytes
    # in Mercurial, so mass convert string keys and values to bytes.
    if pycompat.ispy3:
        env = {k.encode('latin-1'): v for k, v in env.iteritems()}
        env = {
            k: v.encode('latin-1') if isinstance(v, str) else v
            for k, v in env.iteritems()
        }

    # Some hosting solutions are emulating hgwebdir, and dispatching directly
    # to an hgweb instance using this environment variable.  This was always
    # checked prior to d7fd203e36cc; keep doing so to avoid breaking them.
    if not reponame:

        if not env.get('PATH_INFO'):
            raise error.ProgrammingError('reponame requires PATH_INFO')

        if not env['PATH_INFO'].startswith(repoprefix):
            raise error.ProgrammingError(
                'PATH_INFO does not begin with repo '
                'name: %s (%s)' % (env['PATH_INFO'], reponame)
            )

        dispatchpath = env['PATH_INFO'][len(repoprefix) :]

        if dispatchpath and not dispatchpath.startswith('/'):
            raise error.ProgrammingError(
                'reponame prefix of PATH_INFO does '
                'not end at path delimiter: %s (%s)'
                % (env['PATH_INFO'], reponame)
            )

        apppath = apppath.rstrip('/') + repoprefix
        dispatchparts = dispatchpath.strip('/').split('/')
        dispatchpath = '/'.join(dispatchparts)

    # perform case normalization for us. We just rewrite underscore to dash
    # so keys match what likely went over the wire.
    headers = []
    for k, v in env.iteritems():
        if k.startswith('HTTP_'):
            headers.append((k[len('HTTP_') :].replace('_', '-'), v))

    from . import wsgiheaders  # avoid cycle

    headers = wsgiheaders.Headers(headers)

    # This is kind of a lie because the HTTP header wasn't explicitly
    # sent. But for all intents and purposes it should be OK to lie about
    # this, since a consumer will either either value to determine how many

        headers['Content-Type'] = env['CONTENT_TYPE']

    if bodyfh is None:
        bodyfh = env['wsgi.input']
        if 'Content-Length' in headers:
            bodyfh = util.cappedreader(
                bodyfh, int(headers['Content-Length'] or '0')
            )

    return parsedrequest(
        method=env['REQUEST_METHOD'],
        url=fullurl,
        baseurl=baseurl,
        advertisedurl=advertisedfullurl,
        advertisedbaseurl=advertisedbaseurl,
        urlscheme=env['wsgi.url_scheme'],
        remoteuser=env.get('REMOTE_USER'),
        remotehost=env.get('REMOTE_HOST'),
        apppath=apppath,
        dispatchparts=dispatchparts,
        dispatchpath=dispatchpath,
        reponame=reponame,
        querystring=querystring,
        qsparams=qsparams,
        headers=headers,
        bodyfh=bodyfh,
        rawenv=env,
    )


class offsettrackingwriter(object):
    """A file object like object that is append only and tracks write count.

    Instances are bound to a callable. This callable is called with data

    The intent of this class is to wrap the ``write()`` function returned by
    a WSGI ``start_response()`` function. Since ``write()`` is a callable and
    not a file object, it doesn't implement other file object methods.
    """

    def __init__(self, writefn):
        self._write = writefn
        self._offset = 0

    def write(self, s):

        pass

    def tell(self):
        return self._offset


class wsgiresponse(object):
    """Represents a response to a WSGI request.

    A response consists of a status line, headers, and a body.

        """
        self._req = req
        self._startresponse = startresponse

        self.status = None
        from . import wsgiheaders  # avoid cycle

        self.headers = wsgiheaders.Headers([])

        self._bodybytes = None
        self._bodygen = None
        self._bodywillwrite = False
        self._started = False
        self._bodywritefn = None

    def _verifybody(self):
        if (
            self._bodybytes is not None
            or self._bodygen is not None
            or self._bodywillwrite
        ):
            raise error.ProgrammingError('cannot define body multiple times')

    def setbodybytes(self, b):
        """Define the response body as static bytes.

        self._started = True

        if not self.status:
            raise error.ProgrammingError('status line not defined')

        if (
            self._bodybytes is None
            and self._bodygen is None
            and not self._bodywillwrite
        ):
            raise error.ProgrammingError('response body not defined')

        # RFC 7232 Section 4.1 states that a 304 MUST generate one of
        # {Cache-Control, Content-Location, Date, ETag, Expires, Vary}
        # and SHOULD NOT generate other headers unless they could be used

            if self.headers.get('Content-Length') == '0':
                del self.headers['Content-Length']

            # Strictly speaking, this is too strict. But until it causes
            # problems, let's be strict.
            badheaders = {
                k
                for k in self.headers.keys()
                if k.lower()
                not in (
                    'date',
                    'etag',
                    'expires',
                    'cache-control',
                    'content-location',
                    'content-security-policy',
                    'vary',
                )
            }
            if badheaders:
                raise error.ProgrammingError(
                    'illegal header on 304 response: %s'
                    % ', '.join(sorted(badheaders))
                )

            if self._bodygen is not None or self._bodywillwrite:
                raise error.ProgrammingError(
                    "must use setbodybytes('') with " "304 responses"
                )

        # Various HTTP clients (notably httplib) won't read the HTTP response
        # until the HTTP request has been sent in full. If servers (us) send a
        # response before the HTTP request has been fully sent, the connection
        # may deadlock because neither end is reading.

            while True:
                chunk = self._req.bodyfh.read(32768)
                if not chunk:
                    break

        strheaders = [
            (pycompat.strurl(k), pycompat.strurl(v))
            for k, v in self.headers.items()
        ]
        write = self._startresponse(pycompat.sysstr(self.status), strheaders)

        if self._bodybytes:
            yield self._bodybytes
        elif self._bodygen:
            for chunk in self._bodygen:

        """
        if not self._bodywillwrite:
            raise error.ProgrammingError('must call setbodywillwrite() first')

        if not self._started:
            raise error.ProgrammingError(
                'must call sendresponse() first; did '
                'you remember to consume it since it '
                'is a generator?'
            )

        assert self._bodywritefn
        return offsettrackingwriter(self._bodywritefn)


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