Inspired by our FieldStorage work with file uploads, I also made some
implementation changes to Field and StringField in util.py. In essense,
that will make things like using form['key'] multiple times much more
efficient. Also, FieldStorage will return the same object if called twice.
I'd like some feedback from the group on these changes, and also some
directions on what I'd need to do to get them integrated in the
mod_python beta. I have no experience whatsoever in contributing to open
source projects.
Major change is the Field and FieldStorage implementation:
class Field:
filename = None
headers = {}
def __init__(self, name):
self.name = name
def __repr__(self):
"""Return printable representation."""
return "Field(%s, %s)" % (`self.name`, `self.value`)
def __getattr__(self, name):
if name != 'value':
raise AttributeError, name
if self.file:
self.file.seek(0)
self.value = self.file.read()
self.file.seek(0)
else:
self.value = None
return self.value
def __del__(self):
self.file.close()
class StringField(str):
""" This class is basically a string with
added attributes for compatibility with std lib cgi.py. Basically, this
works the opposite of Field, as it stores its data in a string, but
creates
a file on demand. Field creates a value on demand and stores data
in a file.
"""
filename = None
headers = {}
ctype = "text/plain"
type_options = {}
disposition = None
disp_options = None
# I wanted __init__(name, value) but that does not work
(apparently, you
# cannot subclass str with a constructor that takes >1 argument)
def __init__(self, value):
'''Create StringField instance. You'll have to set name
yourself.'''
str.__init__(self, value)
self.value = value
def __getattr__(self, name):
if name != 'file':
raise AttributeError, name
self.file = cStringIO.StringIO(self.value)
return self.file
I've attached a working util.py (based on 3.1.4, so there are also the
changes to allow large uploads in the file).
#
# Copyright 2004 Apache Software Foundation
#
# Licensed under the Apache License, Version 2.0 (the "License"); you
# may not use this file except in compliance with the License. You
# may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
# implied. See the License for the specific language governing
# permissions and limitations under the License.
#
# Originally developed by Gregory Trubetskoy.
#
# $Id: util.py 102649 2004-02-16 19:47:28Z grisha $
import _apache
from mod_python import apache
import cStringIO
import tempfile
from types import *
from exceptions import *
parse_qs = _apache.parse_qs
parse_qsl = _apache.parse_qsl
""" The classes below are a (almost) a drop-in replacement for the
standard cgi.py FieldStorage class. They should have pretty much the
same functionality.
These classes differ in that unlike cgi.FieldStorage, they are not
recursive. The class FieldStorage contains a list of instances of
Field class. Field class is incapable of storing anything in it.
These objects should be considerably faster than the ones in cgi.py
because they do not expect CGI environment, and are
optimized specifically for Apache and mod_python.
"""
class Field:
filename = None
headers = {}
def __init__(self, name):
self.name = name
def __repr__(self):
"""Return printable representation."""
return "Field(%s, %s)" % (`self.name`, `self.value`)
def __getattr__(self, name):
if name != 'value':
raise AttributeError, name
if self.file:
self.file.seek(0)
self.value = self.file.read()
self.file.seek(0)
else:
self.value = None
return self.value
def __del__(self):
self.file.close()
class StringField(str):
""" This class is basically a string with
added attributes for compatibility with std lib cgi.py. Basically, this
works the opposite of Field, as it stores its data in a string, but creates
a file on demand. Field creates a value on demand and stores data in a file.
"""
filename = None
headers = {}
ctype = "text/plain"
type_options = {}
disposition = None
disp_options = None
# I wanted __init__(name, value) but that does not work (apparently, you
# cannot subclass str with a constructor that takes >1 argument)
def __init__(self, value):
'''Create StringField instance. You'll have to set name yourself.'''
str.__init__(self, value)
self.value = value
def __getattr__(self, name):
if name != 'file':
raise AttributeError, name
self.file = cStringIO.StringIO(self.value)
return self.file
class FieldStorage:
def __init__(self, req, keep_blank_values=0, strict_parsing=0):
self.list = []
# always process GET-style parameters
if req.args:
pairs = parse_qsl(req.args, keep_blank_values)
for pair in pairs:
self.add_field(pair[0], pair[1])
if req.method == "POST":
try:
clen = int(req.headers_in["content-length"])
except (KeyError, ValueError):
# absent content-length is not acceptable
raise apache.SERVER_RETURN, apache.HTTP_LENGTH_REQUIRED
if not req.headers_in.has_key("content-type"):
ctype = "application/x-www-form-urlencoded"
else:
ctype = req.headers_in["content-type"]
if ctype == "application/x-www-form-urlencoded":
pairs = parse_qsl(req.read(clen), keep_blank_values)
for pair in pairs:
self.add_field(pair[0], pair[1])
elif ctype[:10] == "multipart/":
# figure out boundary
try:
i = ctype.lower().rindex("boundary=")
boundary = ctype[i+9:]
if len(boundary) >= 2 and boundary[0] == boundary[-1] == '"':
boundary = boundary[1:-1]
boundary = "--" + boundary
except ValueError:
raise apache.SERVER_RETURN, apache.HTTP_BAD_REQUEST
#read until boundary
# ML: req.readline without any limit seems to let my
# apache 2.0.55 comsume the whole request at once, and
# may fail with a memory error
line = req.readline(10240)
while line and not line.startswith(boundary):
line = req.readline(10240)
while 1:
## parse headers
ctype, type_options = "text/plain", {}
disp, disp_options = None, {}
headers = apache.make_table()
line = req.readline(10240)
if len(line) == 10240:
raise "Too big", "bad header in multipart post?"
sline = line.strip()
if not line or sline == (boundary + "--"):
break
while line and line not in ["\n", "\r\n"]:
h, v = line.split(":", 1)
headers.add(h, v)
h = h.lower()
if h == "content-disposition":
disp, disp_options = parse_header(v)
elif h == "content-type":
ctype, type_options = parse_header(v)
line = req.readline(10240)
if len(line) == 10240:
raise "Too big", "bad header in multipart post?"
sline = line.strip()
if disp_options.has_key("name"):
name = disp_options["name"]
else:
name = None
# create a file object
file = self.make_file(disp_options)
# read it in
self.read_to_boundary(req, boundary, file)
file.seek(0)
# make a Field
if disp_options.has_key("filename"):
field = Field(name)
field.filename = disp_options["filename"]
else:
field = StringField(file.read())
field.name = name
field.file = file
field.type = ctype
field.type_options = type_options
field.disposition = disp
field.disposition_options = disp_options
field.headers = headers
self.list.append(field)
else:
# we don't understand this content-type
raise apache.SERVER_RETURN, apache.HTTP_NOT_IMPLEMENTED
def add_field(self, key, value):
"""Insert a field as key/value pair"""
item = StringField(value)
item.name = key
self.list.append(item)
def make_file(self, disp_options):
"""Create a file obejct for the given disp_options. You can override
this method to avoid temp file creation and stream directly. The
returned file must at least support write(data) and seek(0)."""
if disp_options.has_key("filename"):
return tempfile.TemporaryFile("w+b")
else:
return cStringIO.StringIO()
def skip_to_boundary(self, req, boundary):
line = req.readline(10240)
while line and not line.startswith(boundary):
line = req.readline(10240)
## def read_to_boundary_org(self, req, boundary, file, readBlockSize=10240):
## delim = ""
## line = req.readline(readBlockSize)
## while line and not line.startswith(boundary):
## odelim = delim
## if line[-2:] == "\r\n":
## delim = "\r\n"
## line = line[:-2]
## elif line[-1:] == "\n":
## delim = "\n"
## line = line[:-1]
## else:
## delim = ""
## file.write(odelim + line)
## line = req.readline(readBlockSize)
def read_to_boundary(self, req, boundary, file, readBlockSize=65536):
prevline = ""
while 1:
line = req.readline(readBlockSize)
if not line or line.startswith(boundary):
if prevline.endswith('\r\n'):
file.write(prevline[:-2])
elif prevline.endswith('\n'):
file.write(prevline[:-1])
break
file.write(prevline)
prevline = line
def __getitem__(self, key):
"""Dictionary style indexing."""
if self.list is None:
raise TypeError, "not indexable"
found = []
for item in self.list:
if item.name == key:
found.append(item)
if not found:
raise KeyError, key
if len(found) == 1:
return found[0]
else:
return found
def get(self, key, default):
try:
return self.__getitem__(key)
except KeyError:
return default
def keys(self):
"""Dictionary style keys() method."""
if self.list is None:
raise TypeError, "not indexable"
keys = []
for item in self.list:
if item.name not in keys: keys.append(item.name)
return keys
def has_key(self, key):
"""Dictionary style has_key() method."""
if self.list is None:
raise TypeError, "not indexable"
for item in self.list:
if item.name == key: return 1
return 0
__contains__ = has_key
def __len__(self):
"""Dictionary style len(x) support."""
return len(self.keys())
def getfirst(self, key, default=None):
""" return the first value received """
for item in self.list:
if item.name == key:
return item
return default
def getlist(self, key):
""" return a list of received values """
if self.list is None:
raise TypeError, "not indexable"
found = []
for item in self.list:
if item.name == key:
found.append(item)
return found
def parse_header(line):
"""Parse a Content-type like header.
Return the main content-type and a dictionary of options.
"""
plist = map(lambda a: a.strip(), line.split(';'))
key = plist[0].lower()
del plist[0]
pdict = {}
for p in plist:
i = p.find('=')
if i >= 0:
name = p[:i].strip().lower()
value = p[i+1:].strip()
if len(value) >= 2 and value[0] == value[-1] == '"':
value = value[1:-1]
pdict[name] = value
return key, pdict
def apply_fs_data(object, fs, **args):
"""
Apply FieldStorage data to an object - the object must be
callable. Examine the args, and match then with fs data,
then call the object, return the result.
"""
# add form data to args
for field in fs.list:
if field.filename:
val = field
else:
val = field.value
args.setdefault(field.name, []).append(val)
# replace lists with single values
for arg in args:
if ((type(args[arg]) is ListType) and
(len(args[arg]) == 1)):
args[arg] = args[arg][0]
# we need to weed out unexpected keyword arguments
# and for that we need to get a list of them. There
# are a few options for callable objects here:
if type(object) is InstanceType:
# instances are callable when they have __call__()
object = object.__call__
expected = []
if hasattr(object, "func_code"):
# function
fc = object.func_code
expected = fc.co_varnames[0:fc.co_argcount]
elif hasattr(object, 'im_func'):
# method
fc = object.im_func.func_code
expected = fc.co_varnames[1:fc.co_argcount]
elif type(object) is ClassType:
# class
fc = object.__init__.im_func.func_code
expected = fc.co_varnames[1:fc.co_argcount]
# remove unexpected args unless co_flags & 0x08,
# meaning function accepts **kw syntax
if not (fc.co_flags & 0x08):
for name in args.keys():
if name not in expected:
del args[name]
return object(**args)
def redirect(req, location, permanent=0, text=None):
"""
A convenience function to provide redirection
"""
if req.sent_bodyct:
raise IOError, "Cannot redirect after headers have already been sent."
req.err_headers_out["Location"] = location
if permanent:
req.status = apache.HTTP_MOVED_PERMANENTLY
else:
req.status = apache.HTTP_MOVED_TEMPORARILY
if text is None:
req.write('<p>The document has moved'
' <a href="%s">here</a></p>\n'
% location)
else:
req.write(text)
raise apache.SERVER_RETURN, apache.OK
