cgi.py

mallet是自然语言处理、机器学习领域的一个开源项目。

            if not line:
                self.done = -1
                break
            if line[:2] == "--":
                strippedline = line.strip()
                if strippedline == next:
                    break
                if strippedline == last:
                    self.done = 1
                    break
            odelim = delim
            if line[-2:] == "\r\n":
                delim = "\r\n"
                line = line[:-2]
            elif line[-1] == "\n":
                delim = "\n"
                line = line[:-1]
            else:
                delim = ""
            self.__write(odelim + line)

    def skip_lines(self):
        """Internal: skip lines until outer boundary if defined."""
        if not self.outerboundary or self.done:
            return
        next = "--" + self.outerboundary
        last = next + "--"
        while 1:
            line = self.fp.readline()
            if not line:
                self.done = -1
                break
            if line[:2] == "--":
                strippedline = line.strip()
                if strippedline == next:
                    break
                if strippedline == last:
                    self.done = 1
                    break

    def make_file(self, binary=None):
        """Overridable: return a readable & writable file.

        The file will be used as follows:
        - data is written to it
        - seek(0)
        - data is read from it

        The 'binary' argument is unused -- the file is always opened
        in binary mode.

        This version opens a temporary file for reading and writing,
        and immediately deletes (unlinks) it.  The trick (on Unix!) is
        that the file can still be used, but it can't be opened by
        another process, and it will automatically be deleted when it
        is closed or when the current process terminates.

        If you want a more permanent file, you derive a class which
        overrides this method.  If you want a visible temporary file
        that is nevertheless automatically deleted when the script
        terminates, try defining a __del__ method in a derived class
        which unlinks the temporary files you have created.

        """
        import tempfile
        return tempfile.TemporaryFile("w+b")



# Backwards Compatibility Classes
# ===============================

class FormContentDict(UserDict.UserDict):
    """Form content as dictionary with a list of values per field.

    form = FormContentDict()

    form[key] -> [value, value, ...]
    form.has_key(key) -> Boolean
    form.keys() -> [key, key, ...]
    form.values() -> [[val, val, ...], [val, val, ...], ...]
    form.items() ->  [(key, [val, val, ...]), (key, [val, val, ...]), ...]
    form.dict == {key: [val, val, ...], ...}

    """
    def __init__(self, environ=os.environ):
        self.dict = self.data = parse(environ=environ)
        self.query_string = environ['QUERY_STRING']


class SvFormContentDict(FormContentDict):
    """Form content as dictionary expecting a single value per field.

    If you only expect a single value for each field, then form[key]
    will return that single value.  It will raise an IndexError if
    that expectation is not true.  If you expect a field to have
    possible multiple values, than you can use form.getlist(key) to
    get all of the values.  values() and items() are a compromise:
    they return single strings where there is a single value, and
    lists of strings otherwise.

    """
    def __getitem__(self, key):
        if len(self.dict[key]) > 1:
            raise IndexError, 'expecting a single value'
        return self.dict[key][0]
    def getlist(self, key):
        return self.dict[key]
    def values(self):
        result = []
        for value in self.dict.values():
            if len(value) == 1:
                result.append(value[0])
            else: result.append(value)
        return result
    def items(self):
        result = []
        for key, value in self.dict.items():
            if len(value) == 1:
                result.append((key, value[0]))
            else: result.append((key, value))
        return result


class InterpFormContentDict(SvFormContentDict):
    """This class is present for backwards compatibility only."""
    def __getitem__(self, key):
        v = SvFormContentDict.__getitem__(self, key)
        if v[0] in '0123456789+-.':
            try: return int(v)
            except ValueError:
                try: return float(v)
                except ValueError: pass
        return v.strip()
    def values(self):
        result = []
        for key in self.keys():
            try:
                result.append(self[key])
            except IndexError:
                result.append(self.dict[key])
        return result
    def items(self):
        result = []
        for key in self.keys():
            try:
                result.append((key, self[key]))
            except IndexError:
                result.append((key, self.dict[key]))
        return result


class FormContent(FormContentDict):
    """This class is present for backwards compatibility only."""
    def values(self, key):
        if self.dict.has_key(key) :return self.dict[key]
        else: return None
    def indexed_value(self, key, location):
        if self.dict.has_key(key):
            if len(self.dict[key]) > location:
                return self.dict[key][location]
            else: return None
        else: return None
    def value(self, key):
        if self.dict.has_key(key): return self.dict[key][0]
        else: return None
    def length(self, key):
        return len(self.dict[key])
    def stripped(self, key):
        if self.dict.has_key(key): return self.dict[key][0].strip()
        else: return None
    def pars(self):
        return self.dict


# Test/debug code
# ===============

def test(environ=os.environ):
    """Robust test CGI script, usable as main program.

    Write minimal HTTP headers and dump all information provided to
    the script in HTML form.

    """
    import traceback
    print "Content-type: text/html"
    print
    sys.stderr = sys.stdout
    try:
        form = FieldStorage()   # Replace with other classes to test those
        print_directory()
        print_arguments()
        print_form(form)
        print_environ(environ)
        print_environ_usage()
        def f():
            exec "testing print_exception() -- <I>italics?</I>"
        def g(f=f):
            f()
        print "<H3>What follows is a test, not an actual exception:</H3>"
        g()
    except:
        print_exception()

    print "<H1>Second try with a small maxlen...</H1>"

    global maxlen
    maxlen = 50
    try:
        form = FieldStorage()   # Replace with other classes to test those
        print_directory()
        print_arguments()
        print_form(form)
        print_environ(environ)
    except:
        print_exception()

def print_exception(type=None, value=None, tb=None, limit=None):
    if type is None:
        type, value, tb = sys.exc_info()
    import traceback
    print
    print "<H3>Traceback (most recent call last):</H3>"
    list = traceback.format_tb(tb, limit) + \
           traceback.format_exception_only(type, value)
    print "<PRE>%s<B>%s</B></PRE>" % (
        escape("".join(list[:-1])),
        escape(list[-1]),
        )
    del tb

def print_environ(environ=os.environ):
    """Dump the shell environment as HTML."""
    keys = environ.keys()
    keys.sort()
    print
    print "<H3>Shell Environment:</H3>"
    print "<DL>"
    for key in keys:
        print "<DT>", escape(key), "<DD>", escape(environ[key])
    print "</DL>"
    print

def print_form(form):
    """Dump the contents of a form as HTML."""
    keys = form.keys()
    keys.sort()
    print
    print "<H3>Form Contents:</H3>"
    if not keys:
        print "<P>No form fields."
    print "<DL>"
    for key in keys:
        print "<DT>" + escape(key) + ":",
        value = form[key]
        print "<i>" + escape(`type(value)`) + "</i>"
        print "<DD>" + escape(`value`)
    print "</DL>"
    print

def print_directory():
    """Dump the current directory as HTML."""
    print
    print "<H3>Current Working Directory:</H3>"
    try:
        pwd = os.getcwd()
    except os.error, msg:
        print "os.error:", escape(str(msg))
    else:
        print escape(pwd)
    print

def print_arguments():
    print
    print "<H3>Command Line Arguments:</H3>"
    print
    print sys.argv
    print

def print_environ_usage():
    """Dump a list of environment variables used by CGI as HTML."""
    print """
<H3>These environment variables could have been set:</H3>
<UL>
<LI>AUTH_TYPE
<LI>CONTENT_LENGTH
<LI>CONTENT_TYPE
<LI>DATE_GMT
<LI>DATE_LOCAL
<LI>DOCUMENT_NAME
<LI>DOCUMENT_ROOT
<LI>DOCUMENT_URI
<LI>GATEWAY_INTERFACE
<LI>LAST_MODIFIED
<LI>PATH
<LI>PATH_INFO
<LI>PATH_TRANSLATED
<LI>QUERY_STRING
<LI>REMOTE_ADDR
<LI>REMOTE_HOST
<LI>REMOTE_IDENT
<LI>REMOTE_USER
<LI>REQUEST_METHOD
<LI>SCRIPT_NAME
<LI>SERVER_NAME
<LI>SERVER_PORT
<LI>SERVER_PROTOCOL
<LI>SERVER_ROOT
<LI>SERVER_SOFTWARE
</UL>
In addition, HTTP headers sent by the server may be passed in the
environment as well.  Here are some common variable names:
<UL>
<LI>HTTP_ACCEPT
<LI>HTTP_CONNECTION
<LI>HTTP_HOST
<LI>HTTP_PRAGMA
<LI>HTTP_REFERER
<LI>HTTP_USER_AGENT
</UL>
"""


# Utilities
# =========

def escape(s, quote=None):
    """Replace special characters '&', '<' and '>' by SGML entities."""
    s = s.replace("&", "&amp;") # Must be done first!
    s = s.replace("<", "&lt;")
    s = s.replace(">", "&gt;")
    if quote:
        s = s.replace('"', "&quot;")
    return s

def valid_boundary(s, _vb_pattern="^[ -~]{0,200}[!-~]$"):
    import re
    return re.match(_vb_pattern, s)

# Invoke mainline
# ===============

# Call test() when this file is run as a script (not imported as a module)
if __name__ == '__main__':
    test()