root/trunk/RBFoundation/RBFoundation/URIparser.py

#!/usr/bin/env python
##~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
##~ License 
##~ 
##- The RuneBlade Foundation library is intended to ease some 
##- aspects of writing intricate Jabber, XML, and User Interface (wxPython, etc.) 
##- applications, while providing the flexibility to modularly change the 
##- architecture. Enjoy.
##~ 
##~ Copyright (C) 2002  TechGame Networks, LLC.
##~ 
##~ This library is free software; you can redistribute it and/or
##~ modify it under the terms of the BSD style License as found in the 
##~ LICENSE file included with this distribution.
##~ 
##~ TechGame Networks, LLC can be reached at:
##~ 3578 E. Hartsel Drive #211
##~ Colorado Springs, Colorado, USA, 80920
##~
##~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#~ Imports 
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

import re

#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#~ Definitions 
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

class URIPathDefault(object):
    """
    From RFC 2396 at <http://www.ietf.org/rfc/rfc2396.txt>
    ...
    B. Parsing a URI Reference with a Regular Expression

       As described in Section 4.3, the generic URI syntax is not sufficient
       to disambiguate the components of some forms of URI.  Since the
       "greedy algorithm" described in that section is identical to the
       disambiguation method used by POSIX regular expressions, it is
       natural and commonplace to use a regular expression for parsing the
       potential four components and fragment identifier of a URI reference.

       The following line is the regular expression for breaking-down a URI
       reference into its components.

          ^(([^:/?#]+):)?(//([^/?#]*))?([^?#]*)(\?([^#]*))?(#(.*))?
           12            3  4          5       6  7        8 9

       The numbers in the second line above are only to assist readability;
       they indicate the reference points for each subexpression (i.e., each
       paired parenthesis).  We refer to the value matched for subexpression
       <n> as $<n>.  For example, matching the above expression to

          http://www.ics.uci.edu/pub/ietf/uri/#Related

       results in the following subexpression matches:

          $1 = http:
          $2 = http
          $3 = //www.ics.uci.edu
          $4 = www.ics.uci.edu
          $5 = /pub/ietf/uri/
          $6 = <undefined>
          $7 = <undefined>
          $8 = #Related
          $9 = Related

       where <undefined> indicates that the component is not present, as is
       the case for the query component in the above example.  Therefore, we
       can determine the value of the four components and fragment as

          scheme    = $2
          authority = $4
          path      = $5
          query     = $7
          fragment  = $9

       and, going in the opposite direction, we can recreate a URI reference
       from its components using the algorithm in step 7 of Section 5.2.

    """

    #~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    #~ Constants / Variables / Etc. 
    #~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

    reURItype = '^(([^:/?#@]+)(:))?'
    reURIauthority = '((//)([^/?#]*))?'
    reURIpath = '([^?#]*)'
    reURIquery = '((\?)([^#]*))?'
    reURIfragment = '((#)(.*))?'

    reURI = reURItype + reURIauthority + reURIpath + reURIquery + reURIfragment
    _repattern = re.compile(reURI)

    reURIindices = {
        'scheme': 1, 'authority': 5, 'path': 6, 'query': 9, 'fragment': 12,
        'schemesep': 2, 'authoritysep': 4, 'querysep': 8, 'fragmentsep': 11}

    # Default values
    scheme = authority = path = query = fragment = None
    schemesep = ':'
    authoritysep = '//'
    querysep = '?'
    fragmentsep = '#'

    #~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    #~ Special 
    #~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

    def __init__(self, uri=None, **kw):
        if isinstance(uri, (str,unicode)):
            self.seturi(uri)
        elif uri is None:
            pass
        else: raise ValueError, 'Expected string, but received %r' % type(uri)

    def __repr__(self):
        return repr(self.geturi())

    def __str__(self):
        return self.geturi()

    def __cmp__(self, other):
        return cmp(str(self), str(other))

    def __hash__(self):
        return hash(str(self))

    def geturi(self):
        """
        Pseudocode from RFC 2396 at http://www.ietf.org/rfc/rfc2396.txt 
        Section 5.2, step 7 to recreate a URI reference from its components.
        """
        result = []
        if self.scheme is not None:
            result.append(self.scheme)
            if self.schemesep is not None:
                result.append(self.schemesep)
        if self.authority is not None:
            if self.authoritysep is not None:
                result.append(self.authoritysep)
            result.append(self.authority)
        if self.path is not None:
            result.append(self.path)
        if self.query is not None:
            if self.querysep is not None:
                result.append(self.querysep)
            result.append(self.query)
        if self.fragment is not None:
            if self.fragmentsep is not None:
                result.append(self.fragmentsep)
            result.append(self.fragment)
        return ''.join(result)

    def seturi(self, uri, **kw):
        match = self._repattern.match(uri)
        groups = match.groups()
        for key, groupskey in self.reURIindices.iteritems():
            setattr(self, key, groups[groupskey])

        # Copy the explicitly set items from kw
        for key, value in kw.items():
            # but only if they are in known names
            if key in self.reURIindices:
                setattr(self, key, value)
                del kw[key]

    uri = property(geturi, seturi)

#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

class URIAuthorityDefault(URIPathDefault):
    #~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    #~ Constants / Variables / Etc. 
    #~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

    reURItype = '^(([^:/?#@]+)(:))?'
    reURIauthority = '(//)?([^/?#]*)'
    reURIpath = '(/[^?#]*)?'
    reURIquery = '((\?)([^#]*))?'
    reURIfragment = '((#)(.*))?'

    reURI = reURItype + reURIauthority + reURIpath + reURIquery + reURIfragment
    _repattern = re.compile(reURI)

    reURIindices = {
        'scheme': 1, 'authority': 4, 'path': 5, 'query': 8, 'fragment': 11,
        'schemesep': 2, 'authoritysep': 3, 'querysep': 7, 'fragmentsep': 10}

#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#~ Class Aliases
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

RFC2396URI = URIPathDefault
URIPath = URIPathDefault
URI = URIPathDefault

URIAuthDefault = URIAuthorityDefault
URIAuthority = URIAuthorityDefault
URIAuth = URIAuthorityDefault
URIHost = URIAuthorityDefault