##// 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:

r34215:aa877860 default
r36870:290fc4c3 default
Show More
charencode.py
85 lines | 2.3 KiB | text/x-python | PythonLexer
# charencode.py - miscellaneous character encoding
#
# Copyright 2005-2009 Matt Mackall <mpm@selenic.com> and others
#
# 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 array
from .. import (
pycompat,
)
def isasciistr(s):
try:
s.decode('ascii')
return True
except UnicodeDecodeError:
return False
def asciilower(s):
'''convert a string to lowercase if ASCII
Raises UnicodeDecodeError if non-ASCII characters are found.'''
s.decode('ascii')
return s.lower()
def asciiupper(s):
'''convert a string to uppercase if ASCII
Raises UnicodeDecodeError if non-ASCII characters are found.'''
s.decode('ascii')
return s.upper()
_jsonmap = []
_jsonmap.extend("\\u%04x" % x for x in range(32))
_jsonmap.extend(pycompat.bytechr(x) for x in range(32, 127))
_jsonmap.append('\\u007f')
_jsonmap[0x09] = '\\t'
_jsonmap[0x0a] = '\\n'
_jsonmap[0x22] = '\\"'
_jsonmap[0x5c] = '\\\\'
_jsonmap[0x08] = '\\b'
_jsonmap[0x0c] = '\\f'
_jsonmap[0x0d] = '\\r'
_paranoidjsonmap = _jsonmap[:]
_paranoidjsonmap[0x3c] = '\\u003c' # '<' (e.g. escape "</script>")
_paranoidjsonmap[0x3e] = '\\u003e' # '>'
_jsonmap.extend(pycompat.bytechr(x) for x in range(128, 256))
def jsonescapeu8fast(u8chars, paranoid):
"""Convert a UTF-8 byte string to JSON-escaped form (fast path)
Raises ValueError if non-ASCII characters have to be escaped.
"""
if paranoid:
jm = _paranoidjsonmap
else:
jm = _jsonmap
try:
return ''.join(jm[x] for x in bytearray(u8chars))
except IndexError:
raise ValueError
if pycompat.ispy3:
_utf8strict = r'surrogatepass'
else:
_utf8strict = r'strict'
def jsonescapeu8fallback(u8chars, paranoid):
"""Convert a UTF-8 byte string to JSON-escaped form (slow path)
Escapes all non-ASCII characters no matter if paranoid is False.
"""
if paranoid:
jm = _paranoidjsonmap
else:
jm = _jsonmap
# non-BMP char is represented as UTF-16 surrogate pair
u16b = u8chars.decode('utf-8', _utf8strict).encode('utf-16', _utf8strict)
u16codes = array.array(r'H', u16b)
u16codes.pop(0) # drop BOM
return ''.join(jm[x] if x < 128 else '\\u%04x' % x for x in u16codes)