##// END OF EJS Templates
hgweb: use a capped reader for WSGI input stream...
hgweb: use a capped reader for WSGI input stream Per PEP 3333, the input stream from WSGI should respect EOF and prevent reads past the end of the request body. However, not all WSGI servers guarantee this. Notably, our BaseHTTPServer based built-in HTTP server doesn't. Instead, it exposes the raw socket and you can read() from it all you want, getting the connection in a bad state by doing so. We have a "cappedreader" utility class that proxies a file object and prevents reading past a limit. This commit converts the WSGI input stream into a capped reader when the input length is advertised via Content-Length headers. "cappedreader" only exposes a read() method. PEP 3333 states that the input stream MUST also support readline(), readlines(hint), and __iter__(). However, since our WSGI application code only calls read() and since we're not manipulating the stream exposed by the WSGI server, we're not violating the spec here. Differential Revision: https://phab.mercurial-scm.org/D2768

File last commit:

r35818:d5288b96 stable
r36870:290fc4c3 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)