cgi.py

mallet是自然语言处理、机器学习领域的一个开源项目。

#! /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
# =======

import sys
import os
import urllib
import mimetools
import rfc822
import UserDict
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
    apply(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 not fp:
        fp = sys.stdin
    if not environ.has_key('REQUEST_METHOD'):
        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 environ.has_key('QUERY_STRING'):
            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 environ.has_key('QUERY_STRING'):
        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 dict.has_key(name):
            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:
        nv = name_value.split('=', 1)
        if len(nv) != 2:
            if strict_parsing:
                raise ValueError, "bad query field: %s" % `name_value`
            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 conten-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.

    """
    boundary = ""
    if pdict.has_key('boundary'):
        boundary = pdict['boundary']
    if not valid_boundary(boundary):
        raise ValueError,  ('Invalid boundary in multipart form: %s'
                            % `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 params.has_key('name'):
            name = params['name']
        else:
            continue
        if partdict.has_key(name):
            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 = map(lambda x: x.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


# Classes for field storage
# =========================

class MiniFieldStorage:

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

    # Dummy attributes