##// END OF EJS Templates
hgweb: refactor the request draining code...
hgweb: refactor the request draining code The previous code for draining was only invoked in a few places in the wire protocol. Behavior wasn't consist. Furthermore, it was difficult to reason about. With us converting the input stream to a capped reader, it is now safe to always drain the input stream when its size is known because we can never overrun the input and read into the next HTTP request. The only question is "should we?" This commit changes the draining code so every request is examined. Draining now kicks in for a few requests where it wouldn't before. But I think the code is sufficiently restricted so the behavior is safe. Possibly the most dangerous part of this code is the issuing of Connection: close for POST and PUT requests that don't have a Content-Length. I don't think there are any such uses in our WSGI application, so this should be safe. In the near future, I plan to significantly refactor the WSGI response handling. I anticipate this code evolving a bit. So any minor regressions around draining or connection closing behavior might be fixed as a result of that work. All tests pass with this change. That scares me a bit because it means we are lacking low-level tests for the HTTP protocol. Differential Revision: https://phab.mercurial-scm.org/D2769

File last commit:

r35818:d5288b96 stable
r36871:2cdf47e1 default
Show More
minifileset.py
85 lines | 3.3 KiB | text/x-python | PythonLexer
# minifileset.py - a simple language to select files
#
# Copyright 2017 Facebook, Inc.
#
# 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
from .i18n import _
from . import (
error,
fileset,
)
def _compile(tree):
if not tree:
raise error.ParseError(_("missing argument"))
op = tree[0]
if op in {'symbol', 'string', 'kindpat'}:
name = fileset.getpattern(tree, {'path'}, _('invalid file pattern'))
if name.startswith('**'): # file extension test, ex. "**.tar.gz"
ext = name[2:]
for c in ext:
if c in '*{}[]?/\\':
raise error.ParseError(_('reserved character: %s') % c)
return lambda n, s: n.endswith(ext)
elif name.startswith('path:'): # directory or full path test
p = name[5:] # prefix
pl = len(p)
f = lambda n, s: n.startswith(p) and (len(n) == pl or n[pl] == '/')
return f
raise error.ParseError(_("unsupported file pattern: %s") % name,
hint=_('paths must be prefixed with "path:"'))
elif op == 'or':
func1 = _compile(tree[1])
func2 = _compile(tree[2])
return lambda n, s: func1(n, s) or func2(n, s)
elif op == 'and':
func1 = _compile(tree[1])
func2 = _compile(tree[2])
return lambda n, s: func1(n, s) and func2(n, s)
elif op == 'not':
return lambda n, s: not _compile(tree[1])(n, s)
elif op == 'group':
return _compile(tree[1])
elif op == 'func':
symbols = {
'all': lambda n, s: True,
'none': lambda n, s: False,
'size': lambda n, s: fileset.sizematcher(tree[2])(s),
}
name = fileset.getsymbol(tree[1])
if name in symbols:
return symbols[name]
raise error.UnknownIdentifier(name, symbols.keys())
elif op == 'minus': # equivalent to 'x and not y'
func1 = _compile(tree[1])
func2 = _compile(tree[2])
return lambda n, s: func1(n, s) and not func2(n, s)
elif op == 'negate':
raise error.ParseError(_("can't use negate operator in this context"))
elif op == 'list':
raise error.ParseError(_("can't use a list in this context"),
hint=_('see hg help "filesets.x or y"'))
raise error.ProgrammingError('illegal tree: %r' % (tree,))
def compile(text):
"""generate a function (path, size) -> bool from filter specification.
"text" could contain the operators defined by the fileset language for
common logic operations, and parenthesis for grouping. The supported path
tests are '**.extname' for file extension test, and '"path:dir/subdir"'
for prefix test. The ``size()`` predicate is borrowed from filesets to test
file size. The predicates ``all()`` and ``none()`` are also supported.
'(**.php & size(">10MB")) | **.zip | (path:bin & !path:bin/README)' for
example, will catch all php files whose size is greater than 10 MB, all
files whose name ends with ".zip", and all files under "bin" in the repo
root except for "bin/README".
"""
tree = fileset.parse(text)
return _compile(tree)