root/oss/amplee/amplee/examples/miror/miror.py

# -*- coding: utf-8 -*-

## Redistribution and use in source and binary forms, with or without modification, 
## are permitted provided that the following conditions are met:
## 
##      * Redistributions of source code must retain the above copyright notice, 
##        this list of conditions and the following disclaimer.
##      * 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.
##      * Neither the name of Sylvain Hellegouarch nor the names of his contributors 
##        may be used to endorse or promote products derived from this software 
##        without specific prior written permission.
##
## THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND 
## ANY EXPRESS 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 THE COPYRIGHT OWNER OR 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.

__doc__ = """
This module demonstrates how you can use amplee to miror an existing AtomPub service to your local machine as well as index each entry while importing.

Basically just run the module as-is after changing the service document URI and username and password if required.

This will go and fetch the service document, lookup for each collection defined and import each member.

This module is not full proof, it may break if the service document or the atom entries are doing something funny but it might be a good starting point for anyone.

Once the import is done, you'll have a new directory called 'repository' and its sub-directories are reflecting each collection found in the service document.

You will also have a file named 'index.p' representing the indexed atom entries. You can then do something such as, from a python interpreter:

>>> from miror import setup_index
>>> i = setup_index()
>>> from datetime import datetime
>>> ui = i.retrieve('ui')
>>> r0 = ui.between(datetime(2007, 10, 24, 19, 50), datetime(2007, 10, 24, 20, 10))
>>> ci = i.retrieve('ci')
>>> r1 = ci.lookup(term='test')
>>> ai = i.retrieve('ai')
>>> r2 = ai.lookup('some name')
>>> r0 & r1 | r2
"""

__author__ = ['Sylvain Hellegouarch']
__license__ = 'BSD'
__version__ = '0.1.0'

from urlparse import urlparse
import os

base_dir = os.getcwd()

import httplib2
import amara
from amplee.loader import AtomPubLoader
from amplee.atompub.member import MemberResource
from amplee.utils import extract_url_trail
from amplee.indexer import *

class ResourceWrapper(MemberResource):
    def generate_resource_id(self, entry=None, slug=None, info=None):
        links = entry.xml_xpath('atom:link[@rel="edit"]')
        return extract_url_trail(links[0].href) + '.atom'
    
def run(service_uri, username=None, password=None):
    h = httplib2.Http(os.path.join(base_dir, '.cache'))
    if username:
        h.add_credentials(username, password)

    index = setup_index()
    service, xmldoc = load_service_document(h, service_uri)
    import_members(h, service, index)

    print "Saving service document as service.xml"
    f = file(os.path.join(base_dir, 'service.xml'), 'w')
    f.write(service.to_service().xml(indent=True))
    f.close()

def setup_index():
    index = Indexer()
    container = ShelveContainer(os.path.join(base_dir, 'index.p'))
    index.register(PublishedIndex('pi', container=container, granularity=DateIndex.day))
    index.register(UpdatedIndex('ui', container=container, granularity=DateIndex.minute))
    index.register(EditedIndex('ei', container=container, granularity=DateIndex.minute))
    index.register(AuthorIndex('ai', container=container, index_email=True, index_uri=True))
    index.register(CategoryIndex('ci', container=container))

    return index
    
def load_service_document(h, service_uri):
    r, c = h.request(service_uri)
    if r['status'] in ['200', '304']:
        apl = AtomPubLoader(base_dir)
        return apl.load(os.path.join(base_dir, 'config.xml'), c)

    raise StandardError("Could not retrieve '%s'" % service_uri)

def import_members(h, service, index):
    for collection in service.get_collections():
        # This will allow automatic indexing of
        # each entry
        collection.add_indexer(index)
        
        uri = collection.get_base_edit_uri()
        r, c = h.request(uri)
        
        if r['status'] in ['200', '304'] and \
               r['content-type'] in ['application/atom+xml',
                                     'application/atom+xml;type=feed']:

            print "Loading: %s" % uri

            # This creates the directory structure that will
            # contain the resources in the storage
            path_info = urlparse(uri)[2].strip('/')
            collection.name_or_id = path_info
            collection.store.storage.create_container(path_info)

            # Load the collection feed
            doc = amara.parse(c)
            doc.xmlns_prefixes['app'] = "http://www.w3.org/2007/app"
            doc.xmlns_prefixes['atom'] = "http://www.w3.org/2005/Atom"

            # Extract all the link[@rel='edit'] elements
            entries = doc.feed.xml_xpath('//atom:link[@rel="edit"]')

            # Import each member
            for entry in entries:
                # Instead of using the entry as it appears in the collection
                # feed, we load the most up-to-date representation
                r, c = h.request(unicode(entry.href))
                content_type = r['content-type'].lower().replace(' ', '')
                if r['status'] in ['200', '304'] and \
                     content_type in ['application/atom+xml',
                                      'application/atom+xml;type=entry']:
                    
                    print "  Entry: %s" % unicode(entry.href)

                    doc = amara.parse(c)
                    doc.xmlns_prefixes['atom'] = "http://www.w3.org/2005/Atom"

                    media_content = None
                    media = doc.entry.xml_xpath('//atom:link[@rel="edit-media"]')
                    if media:
                        r, c = h.request(unicode(media[0].href))
                        if r['status'] in ['200', '304']:
                            media_content = c

                    member = ResourceWrapper(collection, 'application/atom+xml;type=entry')
                    member.from_entry(doc.entry)
                    collection.attach(member, member_content=member.atom.xml(),
                                      media_content=media_content)
                    collection.store.commit(message='Adding %s' % member.member_id)

if __name__ == "__main__": 
   run('http://snellspace.dyndns.org:9080/weblogs/services/atom', 'test', 'test')