[Zope-Checkins] CVS: Zope2 - PathIndex.py:1.1.4.1

andreas@digicool.com andreas@digicool.com
Wed, 9 May 2001 09:18:35 -0400 (EDT)


Update of /cvs-repository/Zope2/lib/python/SearchIndex
In directory korak:/tmp/cvs-serv8183/lib/python/SearchIndex

Added Files:
      Tag: ajung-dropin-registry
	PathIndex.py 
Log Message:
added from ajung-pathindex branch



--- Added File PathIndex.py in package Zope2 ---
##############################################################################
# 
# Zope Public License (ZPL) Version 1.0
# -------------------------------------
# 
# Copyright (c) Digital Creations.  All rights reserved.
# 
# This license has been certified as Open Source(tm).
# 
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are
# met:
# 
# 1. Redistributions in source code must retain the above copyright
#    notice, this list of conditions, and the following disclaimer.
# 
# 2. Redistributions in binary form must reproduce the above copyright
#    notice, this list of conditions, and the following disclaimer in
#    the documentation and/or other materials provided with the
#    distribution.
# 
# 3. Digital Creations requests that attribution be given to Zope
#    in any manner possible. Zope includes a "Powered by Zope"
#    button that is installed by default. While it is not a license
#    violation to remove this button, it is requested that the
#    attribution remain. A significant investment has been put
#    into Zope, and this effort will continue if the Zope community
#    continues to grow. This is one way to assure that growth.
# 
# 4. All advertising materials and documentation mentioning
#    features derived from or use of this software must display
#    the following acknowledgement:
# 
#      "This product includes software developed by Digital Creations
#      for use in the Z Object Publishing Environment
#      (http://www.zope.org/)."
# 
#    In the event that the product being advertised includes an
#    intact Zope distribution (with copyright and license included)
#    then this clause is waived.
# 
# 5. Names associated with Zope or Digital Creations must not be used to
#    endorse or promote products derived from this software without
#    prior written permission from Digital Creations.
# 
# 6. Modified redistributions of any form whatsoever must retain
#    the following acknowledgment:
# 
#      "This product includes software developed by Digital Creations
#      for use in the Z Object Publishing Environment
#      (http://www.zope.org/)."
# 
#    Intact (re-)distributions of any official Zope release do not
#    require an external acknowledgement.
# 
# 7. Modifications are encouraged but must be packaged separately as
#    patches to official Zope releases.  Distributions that do not
#    clearly separate the patches from the original work must be clearly
#    labeled as unofficial distributions.  Modifications which do not
#    carry the name Zope may be packaged in any form, as long as they
#    conform to all of the clauses above.
# 
# 
# Disclaimer
# 
#   THIS SOFTWARE IS PROVIDED BY DIGITAL CREATIONS ``AS IS'' AND ANY
#   EXPRESSED OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
#   IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
#   PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL DIGITAL CREATIONS OR ITS
#   CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
#   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
#   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
#   USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
#   ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
#   OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
#   OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
#   SUCH DAMAGE.
# 
# 
# This software consists of contributions made by Digital Creations and
# many individuals on behalf of Digital Creations.  Specific
# attributions are listed in the accompanying credits file.
# 
##############################################################################

from BTrees.IOBTree import IOBTree
from BTrees.OOBTree import OOBTree
from BTrees.IIBTree import IISet,difference,intersection
from Persistence import Persistent
from Acquisition import Implicit
from types import StringType

import re,string

class PathIndex(Persistent,Implicit):
    """ A path index stores all path components of the physical 
    path of an object: 

    """

    meta_type = 'Path Index'

    def __init__(self,id):
        self.id = id
        self.clear()


    def clear(self):
        """ clear everything """

        self._index   = OOBTree()
        self._unindex = IOBTree()


    def insertEntry(self,comp,id,level):
        """ 
        k is a path component (generated by splitPath() )
        v is the documentId
        level is the level of the component inside the path
        """

        if self._index.has_key(comp)==0:
            self._index[comp] = {}

        if self._index[comp].has_key(level)==0:
            self._index[comp][level] = IISet()

        self._index[comp][level].insert(id)

        # reverse index
        if not self._unindex.has_key(id):
            self._unindex[id] = {}
        self._unindex[id][comp] = level
            

    def index_object(self, documentId, obj ,threshold):
        """ hook for (Z)Catalog """

        try:
            path = obj.getPhysicalPath()
        except:
            return 0

        path = '/'+ '/'.join(path[1:])
        comps = self.splitPath(path,obj)

        if obj.meta_type != 'Folder':
            comps = comps[:-1]

        for i in range(len(comps)):
            self.insertEntry( comps[i],documentId,i)

        return 1
    

    def unindex_object(self,id):
        """ hook for (Z)Catalog """

        for path,level in self._unindex[id].items():
            self._index[path][level].remove(id)

            if len(self._index[path][level])==0:
                del self._index[path][level]

        del self._unindex[id]


    def splitPath(self,path,obj=None):
        """ split physical path of object. If the object has
        as function splitPath() we use this user-defined function
        to split the path
        """

        if hasattr(obj,"splitPath"):
            comps = obj.splitPath(path)
        else:
            comps = filter(lambda x: x , re.split("/",path))

        return comps


    def search(self,path,level=0):
        """
        path is a list of path components to be searched
        level>=0  starts searching at the given level
        level<0   not defined yet
        """       

        comps = self.splitPath(path)

        if level >=0:

            results = []
            for i in range(len(comps)):
                
                comp = comps[i]

                if not self._index.has_key(comp): return []
                if not self._index[comp].has_key(level+i): return []

                results.append( self._index[comp][level+i] )

            res = results[0]

            for i in range(1,len(results)):
                res = intersection(res,results[i])

            return res

        else:
            pass
 
        return res


    def __len__(self):
        return len(self._index)


    def keys(self):   
        """ return list of all path components """
        keys = []
        for k in self._index.keys(): keys.append(k)
        return keys


    def values(self):   
        values = []
        for k in self._index.values(): values.append(k)
        return values


    def items(self):   
        """ mapping path components : documentIds """

        items = []
        for k in self._index.items(): items.append(k)
        return items


    def _apply_index(self, request, cid=''): 
        """ hook for (Z)Catalog
        request   mapping type (usually {"path": "..." }
                  additionaly a parameter "path_level" might be passed
                  to specify the level (see search())

        cid      ???
        """
           
        if request.has_key(self.id):
            keys = request[self.id]
        else:
            return None

        level = request.get("path_level",-1)

        if type(keys) is StringType:
            if not keys or not string.strip(keys):
                return None
            keys = [keys]

        res = IISet()

        for k in keys:

            if k[0]=="/": level = 0

            rows = self.search(k,level)

            for r in rows:
                res.insert(r)
   
        return res, (self.id,)