##// END OF EJS Templates
manifest: proxy to revlog instance instead of inheriting...
manifest: proxy to revlog instance instead of inheriting Previously, manifestrevlog inherited revlog.revlog and therefore exposed all its APIs. This inevitably resulted in consumers calling low-level revlog APIs. As part of abstracting storage, we want to formalize the interface for manifest storage. The revlog API is much too large to define as the interface. Like we did for filelog, this commit divorces the manifest class from revlog so that we can standardize on a smaller API surface. The way I went about this commit was I broke the inheritance, ran tests, and added proxies until all tests passed. Like filelog, there are a handful of attributes that don't belong on the interface. And like filelog, we'll tease these out in the future. As part of this, we formalize an interface for manifest storage and add checks that manifestrevlog conforms to the interface. Adding proxies will introduce some overhead due to extra attribute lookups and function calls. On the mozilla-unified repository: $ hg verify before: real 627.220 secs (user 525.870+0.000 sys 18.800+0.000) after: real 628.930 secs (user 532.050+0.000 sys 18.320+0.000) $ hg serve (for a clone) before: user 223.580+0.000 sys 14.270+0.000 after: user 227.720+0.000 sys 13.920+0.000 $ hg clone before: user 506.390+0.000 sys 29.720+0.000 after: user 513.080+0.000 sys 28.280+0.000 There appears to be some overhead here. But it appears to be 1-2%. I think that is an appropriate price to pay for storage abstraction, which will eventually let us have much nicer things. If the overhead is noticed in other operations (whose CPU time isn't likely dwarfed by fulltext resolution) or if we want to cut down on the overhead, we could dynamically build up a type whose methods are effectively aliased to a revlog instance's. I'm inclined to punt on that problem for now. We may have to do it for the changelog. At which point it could be implemented in a generic way and ported to filelog and manifestrevlog easily enough I would think. .. api:: manifest.manifestrevlog no longer inherits from revlog The manifestrevlog class now wraps a revlog instance instead of inheriting from revlog. Various attributes and methods on instances are no longer available. Differential Revision: https://phab.mercurial-scm.org/D4386

File last commit:

r37752:a1110db1 default
r39350:7f5e6d3e default
Show More
common.py
261 lines | 8.7 KiB | text/x-python | PythonLexer
# hgweb/common.py - Utility functions needed by hgweb_mod and hgwebdir_mod
#
# 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.
from __future__ import absolute_import
import base64
import errno
import mimetypes
import os
import stat
from .. import (
encoding,
pycompat,
util,
)
httpserver = util.httpserver
HTTP_OK = 200
HTTP_CREATED = 201
HTTP_NOT_MODIFIED = 304
HTTP_BAD_REQUEST = 400
HTTP_UNAUTHORIZED = 401
HTTP_FORBIDDEN = 403
HTTP_NOT_FOUND = 404
HTTP_METHOD_NOT_ALLOWED = 405
HTTP_NOT_ACCEPTABLE = 406
HTTP_UNSUPPORTED_MEDIA_TYPE = 415
HTTP_SERVER_ERROR = 500
def ismember(ui, username, userlist):
"""Check if username is a member of userlist.
If userlist has a single '*' member, all users are considered members.
Can be overridden by extensions to provide more complex authorization
schemes.
"""
return userlist == ['*'] or username in userlist
def checkauthz(hgweb, req, op):
'''Check permission for operation based on request data (including
authentication info). Return if op allowed, else raise an ErrorResponse
exception.'''
user = req.remoteuser
deny_read = hgweb.configlist('web', 'deny_read')
if deny_read and (not user or ismember(hgweb.repo.ui, user, deny_read)):
raise ErrorResponse(HTTP_UNAUTHORIZED, 'read not authorized')
allow_read = hgweb.configlist('web', 'allow_read')
if allow_read and (not ismember(hgweb.repo.ui, user, allow_read)):
raise ErrorResponse(HTTP_UNAUTHORIZED, 'read not authorized')
if op == 'pull' and not hgweb.allowpull:
raise ErrorResponse(HTTP_UNAUTHORIZED, 'pull not authorized')
elif op == 'pull' or op is None: # op is None for interface requests
return
# Allow LFS uploading via PUT requests
if op == 'upload':
if req.method != 'PUT':
msg = 'upload requires PUT request'
raise ErrorResponse(HTTP_METHOD_NOT_ALLOWED, msg)
# enforce that you can only push using POST requests
elif req.method != 'POST':
msg = 'push requires POST request'
raise ErrorResponse(HTTP_METHOD_NOT_ALLOWED, msg)
# require ssl by default for pushing, auth info cannot be sniffed
# and replayed
if hgweb.configbool('web', 'push_ssl') and req.urlscheme != 'https':
raise ErrorResponse(HTTP_FORBIDDEN, 'ssl required')
deny = hgweb.configlist('web', 'deny_push')
if deny and (not user or ismember(hgweb.repo.ui, user, deny)):
raise ErrorResponse(HTTP_UNAUTHORIZED, 'push not authorized')
allow = hgweb.configlist('web', 'allow-push')
if not (allow and ismember(hgweb.repo.ui, user, allow)):
raise ErrorResponse(HTTP_UNAUTHORIZED, 'push not authorized')
# Hooks for hgweb permission checks; extensions can add hooks here.
# Each hook is invoked like this: hook(hgweb, request, operation),
# where operation is either read, pull, push or upload. Hooks should either
# raise an ErrorResponse exception, or just return.
#
# It is possible to do both authentication and authorization through
# this.
permhooks = [checkauthz]
class ErrorResponse(Exception):
def __init__(self, code, message=None, headers=None):
if message is None:
message = _statusmessage(code)
Exception.__init__(self, pycompat.sysstr(message))
self.code = code
if headers is None:
headers = []
self.headers = headers
class continuereader(object):
"""File object wrapper to handle HTTP 100-continue.
This is used by servers so they automatically handle Expect: 100-continue
request headers. On first read of the request body, the 100 Continue
response is sent. This should trigger the client into actually sending
the request body.
"""
def __init__(self, f, write):
self.f = f
self._write = write
self.continued = False
def read(self, amt=-1):
if not self.continued:
self.continued = True
self._write('HTTP/1.1 100 Continue\r\n\r\n')
return self.f.read(amt)
def __getattr__(self, attr):
if attr in ('close', 'readline', 'readlines', '__iter__'):
return getattr(self.f, attr)
raise AttributeError
def _statusmessage(code):
responses = httpserver.basehttprequesthandler.responses
return pycompat.bytesurl(
responses.get(code, (r'Error', r'Unknown error'))[0])
def statusmessage(code, message=None):
return '%d %s' % (code, message or _statusmessage(code))
def get_stat(spath, fn):
"""stat fn if it exists, spath otherwise"""
cl_path = os.path.join(spath, fn)
if os.path.exists(cl_path):
return os.stat(cl_path)
else:
return os.stat(spath)
def get_mtime(spath):
return get_stat(spath, "00changelog.i")[stat.ST_MTIME]
def ispathsafe(path):
"""Determine if a path is safe to use for filesystem access."""
parts = path.split('/')
for part in parts:
if (part in ('', pycompat.oscurdir, pycompat.ospardir) or
pycompat.ossep in part or
pycompat.osaltsep is not None and pycompat.osaltsep in part):
return False
return True
def staticfile(directory, fname, res):
"""return a file inside directory with guessed Content-Type header
fname always uses '/' as directory separator and isn't allowed to
contain unusual path components.
Content-Type is guessed using the mimetypes module.
Return an empty string if fname is illegal or file not found.
"""
if not ispathsafe(fname):
return
fpath = os.path.join(*fname.split('/'))
if isinstance(directory, str):
directory = [directory]
for d in directory:
path = os.path.join(d, fpath)
if os.path.exists(path):
break
try:
os.stat(path)
ct = mimetypes.guess_type(pycompat.fsdecode(path))[0] or "text/plain"
with open(path, 'rb') as fh:
data = fh.read()
res.headers['Content-Type'] = ct
res.setbodybytes(data)
return res
except TypeError:
raise ErrorResponse(HTTP_SERVER_ERROR, 'illegal filename')
except OSError as err:
if err.errno == errno.ENOENT:
raise ErrorResponse(HTTP_NOT_FOUND)
else:
raise ErrorResponse(HTTP_SERVER_ERROR,
encoding.strtolocal(err.strerror))
def paritygen(stripecount, offset=0):
"""count parity of horizontal stripes for easier reading"""
if stripecount and offset:
# account for offset, e.g. due to building the list in reverse
count = (stripecount + offset) % stripecount
parity = (stripecount + offset) // stripecount & 1
else:
count = 0
parity = 0
while True:
yield parity
count += 1
if stripecount and count >= stripecount:
parity = 1 - parity
count = 0
def get_contact(config):
"""Return repo contact information or empty string.
web.contact is the primary source, but if that is not set, try
ui.username or $EMAIL as a fallback to display something useful.
"""
return (config("web", "contact") or
config("ui", "username") or
encoding.environ.get("EMAIL") or "")
def cspvalues(ui):
"""Obtain the Content-Security-Policy header and nonce value.
Returns a 2-tuple of the CSP header value and the nonce value.
First value is ``None`` if CSP isn't enabled. Second value is ``None``
if CSP isn't enabled or if the CSP header doesn't need a nonce.
"""
# Without demandimport, "import uuid" could have an immediate side-effect
# running "ldconfig" on Linux trying to find libuuid.
# With Python <= 2.7.12, that "ldconfig" is run via a shell and the shell
# may pollute the terminal with:
#
# shell-init: error retrieving current directory: getcwd: cannot access
# parent directories: No such file or directory
#
# Python >= 2.7.13 has fixed it by running "ldconfig" directly without a
# shell (hg changeset a09ae70f3489).
#
# Moved "import uuid" from here so it's executed after we know we have
# a sane cwd (i.e. after dispatch.py cwd check).
#
# We can move it back once we no longer need Python <= 2.7.12 support.
import uuid
# Don't allow untrusted CSP setting since it be disable protections
# from a trusted/global source.
csp = ui.config('web', 'csp', untrusted=False)
nonce = None
if csp and '%nonce%' in csp:
nonce = base64.urlsafe_b64encode(uuid.uuid4().bytes).rstrip('=')
csp = csp.replace('%nonce%', nonce)
return csp, nonce