#! /usr/local/bin/python

# NOTE: the above "/usr/local/bin/python" is NOT a mistake.  It is

# intentionally NOT "/usr/bin/env python".  On many systems

# (e.g. Solaris), /usr/local/bin is not in $PATH as passed to CGI

# scripts, and /usr/local/bin is the default directory where Python is

# installed, so /usr/bin/env would be unable to find python.  Granted,

# binary installations by Linux vendors often install Python in

# /usr/bin.  So let those vendors patch cgi.py to match their choice

# of installation.

"""Support module for CGI (Common Gateway Interface) scripts.

This module defines a number of utilities for use by CGI scripts

written in Python.

"""

# XXX Perhaps there should be a slimmed version that doesn't contain

# all those backwards compatible and debugging classes and functions?

# History

# -------

#

# Michael McLay started this module.  Steve Majewski changed the

# interface to SvFormContentDict and FormContentDict.  The multipart

# parsing was inspired by code submitted by Andreas Paepcke.  Guido van

# Rossum rewrote, reformatted and documented the module and is currently

# responsible for its maintenance.

#

__version__ = "2.6"

# Imports

# =======

from operator import attrgetter

import sys

import os

import urllib

import mimetools

import rfc822

import UserDict

try:

    from cStringIO import StringIO

except ImportError:

    from StringIO import StringIO

__all__ = ["MiniFieldStorage", "FieldStorage", "FormContentDict",

           "SvFormContentDict", "InterpFormContentDict", "FormContent",

           "parse", "parse_qs", "parse_qsl", "parse_multipart",

           "parse_header", "print_exception", "print_environ",

           "print_form", "print_directory", "print_arguments",

           "print_environ_usage", "escape"]

# Logging support

# ===============

logfile = ""            # Filename to log to, if not empty

logfp = None            # File object to log to, if not None

def initlog(*allargs):

    """Write a log message, if there is a log file.

    Even though this function is called initlog(), you should always

    use log(); log is a variable that is set either to initlog

    (initially), to dolog (once the log file has been opened), or to

    nolog (when logging is disabled).

    The first argument is a format string; the remaining arguments (if

    any) are arguments to the % operator, so e.g.

        log("%s: %s", "a", "b")

    will write "a: b" to the log file, followed by a newline.

    If the global logfp is not None, it should be a file object to

    which log data is written.

    If the global logfp is None, the global logfile may be a string

    giving a filename to open, in append mode.  This file should be

    world writable!!!  If the file can't be opened, logging is

    silently disabled (since there is no safe place where we could

    send an error message).

    """

    global logfp, log

    if logfile and not logfp:

        try:

            logfp = open(logfile, "a")

        except IOError:

            pass

    if not logfp:

        log = nolog

    else:

        log = dolog

    log(*allargs)

def dolog(fmt, *args):

    """Write a log message to the log file.  See initlog() for docs."""

    logfp.write(fmt%args + "\n")

def nolog(*allargs):

    """Dummy function, assigned to log when logging is disabled."""

    pass

log = initlog           # The current logging function

# Parsing functions

# =================

# Maximum input we will accept when REQUEST_METHOD is POST

# 0 ==> unlimited input

maxlen = 0

def parse(fp=None, environ=os.environ, keep_blank_values=0, strict_parsing=0):

    """Parse a query in the environment or from a file (default stdin)

        Arguments, all optional:

        fp              : file pointer; default: sys.stdin

        environ         : environment dictionary; default: os.environ

        keep_blank_values: flag indicating whether blank values in

            URL encoded forms should be treated as blank strings.

            A true value indicates that blanks should be retained as

            blank strings.  The default false value indicates that

            blank values are to be ignored and treated as if they were

            not included.

        strict_parsing: flag indicating what to do with parsing errors.

            If false (the default), errors are silently ignored.

            If true, errors raise a ValueError exception.

    """

    if fp is None:

        fp = sys.stdin

    if not 'REQUEST_METHOD' in environ:

        environ['REQUEST_METHOD'] = 'GET'       # For testing stand-alone

    if environ['REQUEST_METHOD'] == 'POST':

        ctype, pdict = parse_header(environ['CONTENT_TYPE'])

        if ctype == 'multipart/form-data':

            return parse_multipart(fp, pdict)

        elif ctype == 'application/x-www-form-urlencoded':

            clength = int(environ['CONTENT_LENGTH'])

            if maxlen and clength > maxlen:

                raise ValueError, 'Maximum content length exceeded'

            qs = fp.read(clength)

        else:

            qs = ''                     # Unknown content-type

        if 'QUERY_STRING' in environ:

            if qs: qs = qs + '&'

            qs = qs + environ['QUERY_STRING']

        elif sys.argv[1:]:

            if qs: qs = qs + '&'

            qs = qs + sys.argv[1]

        environ['QUERY_STRING'] = qs    # XXX Shouldn't, really

    elif 'QUERY_STRING' in environ:

        qs = environ['QUERY_STRING']

    else:

        if sys.argv[1:]:

            qs = sys.argv[1]

        else:

            qs = ""

        environ['QUERY_STRING'] = qs    # XXX Shouldn't, really

    return parse_qs(qs, keep_blank_values, strict_parsing)

def parse_qs(qs, keep_blank_values=0, strict_parsing=0):

    """Parse a query given as a string argument.

        Arguments:

        qs: URL-encoded query string to be parsed

        keep_blank_values: flag indicating whether blank values in

            URL encoded queries should be treated as blank strings.

            A true value indicates that blanks should be retained as

            blank strings.  The default false value indicates that

            blank values are to be ignored and treated as if they were

            not included.

        strict_parsing: flag indicating what to do with parsing errors.

            If false (the default), errors are silently ignored.

            If true, errors raise a ValueError exception.

    """

    dict = {}

    for name, value in parse_qsl(qs, keep_blank_values, strict_parsing):

        if name in dict:

            dict[name].append(value)

        else:

            dict[name] = [value]

    return dict

def parse_qsl(qs, keep_blank_values=0, strict_parsing=0):

    """Parse a query given as a string argument.

    Arguments:

    qs: URL-encoded query string to be parsed

    keep_blank_values: flag indicating whether blank values in

        URL encoded queries should be treated as blank strings.  A

        true value indicates that blanks should be retained as blank

        strings.  The default false value indicates that blank values

        are to be ignored and treated as if they were  not included.

    strict_parsing: flag indicating what to do with parsing errors. If

        false (the default), errors are silently ignored. If true,

        errors raise a ValueError exception.

    Returns a list, as G-d intended.

    """

    pairs = [s2 for s1 in qs.split('&') for s2 in s1.split(';')]

    r = []

    for name_value in pairs:

        if not name_value and not strict_parsing:

            continue

        nv = name_value.split('=', 1)

        if len(nv) != 2:

            if strict_parsing:

                raise ValueError, "bad query field: %r" % (name_value,)

            # Handle case of a control-name with no equal sign

            if keep_blank_values:

                nv.append('')

            else:

                continue

        if len(nv[1]) or keep_blank_values:

            name = urllib.unquote(nv[0].replace('+', ' '))

            value = urllib.unquote(nv[1].replace('+', ' '))

            r.append((name, value))

    return r

def parse_multipart(fp, pdict):

    """Parse multipart input.

    Arguments:

    fp   : input file

    pdict: dictionary containing other parameters of content-type header

    Returns a dictionary just like parse_qs(): keys are the field names, each

    value is a list of values for that field.  This is easy to use but not

    much good if you are expecting megabytes to be uploaded -- in that case,

    use the FieldStorage class instead which is much more flexible.  Note

    that content-type is the raw, unparsed contents of the content-type

    header.

    XXX This does not parse nested multipart parts -- use FieldStorage for

    that.

    XXX This should really be subsumed by FieldStorage altogether -- no

    point in having two implementations of the same parsing algorithm.

    Also, FieldStorage protects itself better against certain DoS attacks

    by limiting the size of the data read in one chunk.  The API here

    does not support that kind of protection.  This also affects parse()

    since it can call parse_multipart().

    """

    boundary = ""

    if 'boundary' in pdict:

        boundary = pdict['boundary']

    if not valid_boundary(boundary):

        raise ValueError,  ('Invalid boundary in multipart form: %r'

                            % (boundary,))

    nextpart = "--" + boundary

    lastpart = "--" + boundary + "--"

    partdict = {}

    terminator = ""

    while terminator != lastpart:

        bytes = -1

        data = None

        if terminator:

            # At start of next part.  Read headers first.

            headers = mimetools.Message(fp)

            clength = headers.getheader('content-length')

            if clength:

                try:

                    bytes = int(clength)

                except ValueError:

                    pass

            if bytes > 0:

                if maxlen and bytes > maxlen:

                    raise ValueError, 'Maximum content length exceeded'

                data = fp.read(bytes)

            else:

                data = ""

        # Read lines until end of part.

        lines = []

        while 1:

            line = fp.readline()

            if not line:

                terminator = lastpart # End outer loop

                break

            if line[:2] == "--":

                terminator = line.strip()

                if terminator in (nextpart, lastpart):

                    break

            lines.append(line)

        # Done with part.

        if data is None:

            continue

        if bytes < 0:

            if lines:

                # Strip final line terminator

                line = lines[-1]

                if line[-2:] == "\r\n":

                    line = line[:-2]

                elif line[-1:] == "\n":

                    line = line[:-1]

                lines[-1] = line

                data = "".join(lines)

        line = headers['content-disposition']

        if not line:

            continue

        key, params = parse_header(line)

        if key != 'form-data':

            continue

        if 'name' in params:

            name = params['name']

        else:

            continue

        if name in partdict:

            partdict[name].append(data)

        else:

            partdict[name] = [data]

    return partdict

def parse_header(line):

    """Parse a Content-type like header.

    Return the main content-type and a dictionary of options.

    """

    plist = [x.strip() for x in line.split(';')]

    key = plist.pop(0).lower()

    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]

                value = value.replace('\\\\', '\\').replace('\\"', '"')

            pdict[name] = value

    return key, pdict

# Classes for field storage

# =========================

class MiniFieldStorage:

    """Like FieldStorage, for use when no file uploads are possible."""

    # Dummy attributes

    filename = None

    list = None

    type = None

    file = None

    type_options = {}

    disposition = None

    disposition_options = {}

    headers = {}

    def __init__(self, name, value):

        """Constructor from field name and value."""

        self.name = name

        self.value = value

        # self.file = StringIO(value)

    def __repr__(self):

        """Return printable representation."""

        return "MiniFieldStorage(%r, %r)" % (self.name, self.value)

class FieldStorage:

    """Store a sequence of fields, reading multipart/form-data.

    This class provides naming, typing, files stored on disk, and

    more.  At the top level, it is accessible like a dictionary, whose

    keys are the field names.  (Note: None can occur as a field name.)

    The items are either a Python list (if there's multiple values) or

    another FieldStorage or MiniFieldStorage object.  If it's a single

    object, it has the following attributes:

    name: the field name, if specified; otherwise None

    filename: the filename, if specified; otherwise None; this is the

        client side filename, *not* the file name on which it is

        stored (that's a temporary file you don't deal with)

    value: the value as a *string*; for file uploads, this

        transparently reads the file every time you request the value

    file: the file(-like) object from which you can read the data;

        None if the data is stored a simple string

    type: the content-type, or None if not specified

    type_options: dictionary of options specified on the content-type

        line

    disposition: content-disposition, or None if not specified

    disposition_options: dictionary of corresponding options

    headers: a dictionary(-like) object (sometimes rfc822.Message or a

        subclass thereof) containing *all* headers

    The class is subclassable, mostly for the purpose of overriding

    the make_file() method, which is called internally to come up with

    a file open for reading and writing.  This makes it possible to

    override the default choice of storing all files in a temporary

    directory and unlinking them as soon as they have been opened.

    """

    def __init__(self, fp=None, headers=None, outerboundary="",

                 environ=os.environ, keep_blank_values=0, strict_parsing=0):

        """Constructor.  Read multipart/* until last part.

        Arguments, all optional:

        fp              : file pointer; default: sys.stdin

            (not used when the request method is GET)

        headers         : header dictionary-like object; default:

            taken from environ as per CGI spec

        outerboundary   : terminating multipart boundary

            (for internal use only)

        environ         : environment dictionary; default: os.environ

        keep_blank_values: flag indicating whether blank values in

            URL encoded forms should be treated as blank strings.

            A true value indicates that blanks should be retained as

            blank strings.  The default false value indicates that

            blank values are to be ignored and treated as if they were

            not included.

        strict_parsing: flag indicating what to do with parsing errors.

            If false (the default), errors are silently ignored.

            If true, errors raise a ValueError exception.

        """

        method = 'GET'

        self.keep_blank_values = keep_blank_values

        self.strict_parsing = strict_parsing

        if 'REQUEST_METHOD' in environ:

            method = environ['REQUEST_METHOD'].upper()

        if method == 'GET' or method == 'HEAD':

            if 'QUERY_STRING' in environ:

                qs = environ['QUERY_STRING']

            elif sys.argv[1:]:

                qs = sys.argv[1]

            else:

                qs = ""

            fp = StringIO(qs)

            if headers is None:

                headers = {'content-type':

                           "application/x-www-form-urlencoded"}

        if headers is None:

            headers = {}

            if method == 'POST':

                # Set default content-type for POST to what's traditional

                headers['content-type'] = "application/x-www-form-urlencoded"

            if 'CONTENT_TYPE' in environ:

                headers['content-type'] = environ['CONTENT_TYPE']

            if 'CONTENT_LENGTH' in environ:

                headers['content-length'] = environ['CONTENT_LENGTH']

        self.fp = fp or sys.stdin

        self.headers = headers

        self.outerboundary = outerboundary

        # Process content-disposition header

        cdisp, pdict = "", {}

        if 'content-disposition' in self.headers:

            cdisp, pdict = parse_header(self.headers['content-disposition'])

        self.disposition = cdisp

        self.disposition_options = pdict

        self.name = None

        if 'name' in pdict:

            self.name = pdict['name']

        self.filename = None

        if 'filename' in pdict:

            self.filename = pdict['filename']

        # Process content-type header

        #

        # Honor any existing content-type header.  But if there is no

        # content-type header, use some sensible defaults.  Assume

        # outerboundary is "" at the outer level, but something non-false

        # inside a multi-part.  The default for an inner part is text/plain,

        # but for an outer part it should be urlencoded.  This should catch

        # bogus clients which erroneously forget to include a content-type

        # header.

        #

        # See below for what we do if there does exist a content-type header,

        # but it happens to be something we don't understand.

        if 'content-type' in self.headers:

            ctype, pdict = parse_header(self.headers['content-type'])

        elif self.outerboundary or method != 'POST':

            ctype, pdict = "text/plain", {}

        else:

            ctype, pdict = 'application/x-www-form-urlencoded', {}

        self.type = ctype

        self.type_options = pdict

        self.innerboundary = ""

        if 'boundary' in pdict:

            self.innerboundary = pdict['boundary']

        clen = -1

        if 'content-length' in self.headers:

            try:

                clen = int(self.headers['content-length'])

            except ValueError:

                pass

            if maxlen and clen > maxlen:

                raise ValueError, 'Maximum content length exceeded'

        self.length = clen