sobjects/parsers.py
author Sylvain Thénault <sylvain.thenault@logilab.fr>
Wed, 22 Jun 2011 18:53:38 +0200
changeset 7553 935423529f45
parent 7534 d58a9d96aad8
child 7689 a86fd3ec322e
permissions -rw-r--r--
[datafeed cw parser] refactor: split logic that was in the parser into: * an "item builder" component, turning an etree xml node into a specific python dictionnary representing an entity * "action" components, selected given an entity, a relation and its role in the relation, and responsible to link the entity to given related items (eg dictionnary) This changes make it easy to add new action or to override existing one's behaviour according to the entity, the relation, etc... Also refactor the xml view so one can also override what's included in the tag used to mark the entity as used by a relation, hopefully allowing to reduce the number of http requests needed for a full datafeed import.
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
6960
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
     1
# copyright 2010-2011 LOGILAB S.A. (Paris, FRANCE), all rights reserved.
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
     2
# contact http://www.logilab.fr/ -- mailto:contact@logilab.fr
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
     3
#
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
     4
# This file is part of CubicWeb.
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
     5
#
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
     6
# CubicWeb is free software: you can redistribute it and/or modify it under the
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
     7
# terms of the GNU Lesser General Public License as published by the Free
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
     8
# Software Foundation, either version 2.1 of the License, or (at your option)
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
     9
# any later version.
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    10
#
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    11
# CubicWeb is distributed in the hope that it will be useful, but WITHOUT
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    12
# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    13
# FOR A PARTICULAR PURPOSE.  See the GNU Lesser General Public License for more
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    14
# details.
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    15
#
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    16
# You should have received a copy of the GNU Lesser General Public License along
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    17
# with CubicWeb.  If not, see <http://www.gnu.org/licenses/>.
7354
f627ab500fda [parsers] various refactorings
Nicolas Chauvat <nicolas.chauvat@logilab.fr>
parents: 7351
diff changeset
    18
"""datafeed parser for xml generated by cubicweb
f627ab500fda [parsers] various refactorings
Nicolas Chauvat <nicolas.chauvat@logilab.fr>
parents: 7351
diff changeset
    19
f627ab500fda [parsers] various refactorings
Nicolas Chauvat <nicolas.chauvat@logilab.fr>
parents: 7351
diff changeset
    20
Example of mapping for CWEntityXMLParser::
f627ab500fda [parsers] various refactorings
Nicolas Chauvat <nicolas.chauvat@logilab.fr>
parents: 7351
diff changeset
    21
f627ab500fda [parsers] various refactorings
Nicolas Chauvat <nicolas.chauvat@logilab.fr>
parents: 7351
diff changeset
    22
  {u'CWUser': {                                        # EntityType
f627ab500fda [parsers] various refactorings
Nicolas Chauvat <nicolas.chauvat@logilab.fr>
parents: 7351
diff changeset
    23
      (u'in_group', u'subject', u'link'): [            # (rtype, role, action)
f627ab500fda [parsers] various refactorings
Nicolas Chauvat <nicolas.chauvat@logilab.fr>
parents: 7351
diff changeset
    24
          (u'CWGroup', {u'linkattr': u'name'})],       #   -> rules = [(EntityType, options), ...]
f627ab500fda [parsers] various refactorings
Nicolas Chauvat <nicolas.chauvat@logilab.fr>
parents: 7351
diff changeset
    25
      (u'tags', u'object', u'link-or-create'): [       # (...)
f627ab500fda [parsers] various refactorings
Nicolas Chauvat <nicolas.chauvat@logilab.fr>
parents: 7351
diff changeset
    26
          (u'Tag', {u'linkattr': u'name'})],           #   -> ...
f627ab500fda [parsers] various refactorings
Nicolas Chauvat <nicolas.chauvat@logilab.fr>
parents: 7351
diff changeset
    27
      (u'use_email', u'subject', u'copy'): [           # (...)
f627ab500fda [parsers] various refactorings
Nicolas Chauvat <nicolas.chauvat@logilab.fr>
parents: 7351
diff changeset
    28
          (u'EmailAddress', {})]                       #   -> ...
f627ab500fda [parsers] various refactorings
Nicolas Chauvat <nicolas.chauvat@logilab.fr>
parents: 7351
diff changeset
    29
      }
f627ab500fda [parsers] various refactorings
Nicolas Chauvat <nicolas.chauvat@logilab.fr>
parents: 7351
diff changeset
    30
   }
f627ab500fda [parsers] various refactorings
Nicolas Chauvat <nicolas.chauvat@logilab.fr>
parents: 7351
diff changeset
    31
f627ab500fda [parsers] various refactorings
Nicolas Chauvat <nicolas.chauvat@logilab.fr>
parents: 7351
diff changeset
    32
"""
6960
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    33
6963
5774d4ba4306 [datafeed] introduce a host mapping so dev instance may transparently redirect request to another host than the actual's one
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 6960
diff changeset
    34
import os.path as osp
6960
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    35
from datetime import datetime, timedelta
7531
e891ca479586 [datafeed, cwxml] parser now try to complete source's urls so one can add url such as <myinstance>/project. Closes #1759908
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7481
diff changeset
    36
from urllib import urlencode
7532
76914c7ba1b0 [python 2.5] compat fix
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7531
diff changeset
    37
from cgi import parse_qs # in urlparse with python >= 2.6
6960
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    38
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    39
from logilab.common.date import todate, totime
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    40
from logilab.common.textutils import splitstrip, text_to_dict
7553
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
    41
from logilab.common.decorators import classproperty
6960
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    42
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    43
from yams.constraints import BASE_CONVERTERS
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    44
from yams.schema import role_name as rn
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    45
7553
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
    46
from cubicweb import ValidationError, RegistryException, typed_eid
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
    47
from cubicweb.view import Component
6960
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    48
from cubicweb.server.sources import datafeed
7553
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
    49
from cubicweb.server.hook import match_rtype
6960
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    50
7354
f627ab500fda [parsers] various refactorings
Nicolas Chauvat <nicolas.chauvat@logilab.fr>
parents: 7351
diff changeset
    51
# XXX see cubicweb.cwvreg.YAMS_TO_PY
f627ab500fda [parsers] various refactorings
Nicolas Chauvat <nicolas.chauvat@logilab.fr>
parents: 7351
diff changeset
    52
# XXX see cubicweb.web.views.xmlrss.SERIALIZERS
6960
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    53
DEFAULT_CONVERTERS = BASE_CONVERTERS.copy()
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    54
DEFAULT_CONVERTERS['String'] = unicode
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    55
DEFAULT_CONVERTERS['Password'] = lambda x: x.encode('utf8')
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    56
def convert_date(ustr):
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    57
    return todate(datetime.strptime(ustr, '%Y-%m-%d'))
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    58
DEFAULT_CONVERTERS['Date'] = convert_date
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    59
def convert_datetime(ustr):
7002
29f085f6177b [sobjects/parsers] compatibility with xml view of cw <= 3.10
Nicolas Chauvat <nicolas.chauvat@logilab.fr>
parents: 7001
diff changeset
    60
    if '.' in ustr: # assume %Y-%m-%d %H:%M:%S.mmmmmm
29f085f6177b [sobjects/parsers] compatibility with xml view of cw <= 3.10
Nicolas Chauvat <nicolas.chauvat@logilab.fr>
parents: 7001
diff changeset
    61
        ustr = ustr.split('.',1)[0]
6960
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    62
    return datetime.strptime(ustr, '%Y-%m-%d %H:%M:%S')
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    63
DEFAULT_CONVERTERS['Datetime'] = convert_datetime
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    64
def convert_time(ustr):
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    65
    return totime(datetime.strptime(ustr, '%H:%M:%S'))
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    66
DEFAULT_CONVERTERS['Time'] = convert_time
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    67
def convert_interval(ustr):
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    68
    return time(seconds=int(ustr))
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    69
DEFAULT_CONVERTERS['Interval'] = convert_interval
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    70
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    71
def extract_typed_attrs(eschema, stringdict, converters=DEFAULT_CONVERTERS):
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    72
    typeddict = {}
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    73
    for rschema in eschema.subject_relations():
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    74
        if rschema.final and rschema in stringdict:
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    75
            if rschema == 'eid':
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    76
                continue
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    77
            attrtype = eschema.destination(rschema)
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    78
            typeddict[rschema.type] = converters[attrtype](stringdict[rschema])
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    79
    return typeddict
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    80
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    81
def rtype_role_rql(rtype, role):
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    82
    if role == 'object':
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    83
        return 'Y %s X WHERE X eid %%(x)s' % rtype
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    84
    else:
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    85
        return 'X %s Y WHERE X eid %%(x)s' % rtype
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    86
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    87
7553
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
    88
class CWEntityXMLParser(datafeed.DataFeedXMLParser):
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
    89
    """datafeed parser for the 'xml' entity view
6960
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    90
7553
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
    91
    Most of the logic is delegated to the following components:
6960
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    92
7553
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
    93
    * an "item builder" component, turning an etree xml node into a specific
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
    94
      python dictionnary representing an entity
6960
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    95
7553
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
    96
    * "action" components, selected given an entity, a relation and its role in
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
    97
      the relation, and responsible to link the entity to given related items
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
    98
      (eg dictionnary)
6960
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
    99
7553
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   100
    So the parser is only doing the gluing service and the connection to the
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   101
    source.
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   102
    """
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   103
    __regid__ = 'cw.entityxml'
6960
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   104
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   105
    def __init__(self, *args, **kwargs):
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   106
        super(CWEntityXMLParser, self).__init__(*args, **kwargs)
7474
7dc405ad7bf3 [datafeed cwxml parser] cache processed urls/entities to avoid unnecessary http requests and processing
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7470
diff changeset
   107
        self._parsed_urls = {}
7dc405ad7bf3 [datafeed cwxml parser] cache processed urls/entities to avoid unnecessary http requests and processing
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7470
diff changeset
   108
        self._processed_entities = set()
6960
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   109
7553
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   110
    def select_linker(self, action, rtype, role, entity=None):
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   111
        try:
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   112
            return self._cw.vreg['components'].select(
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   113
                'cw.entityxml.action.%s' % action, self._cw, entity=entity,
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   114
                rtype=rtype, role=role, parser=self)
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   115
        except RegistryException:
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   116
            raise RegistryException('Unknown action %s' % action)
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   117
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   118
    def list_actions(self):
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   119
        reg = self._cw.vreg['components']
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   120
        return sorted(clss[0].action for rid, clss in reg.iteritems()
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   121
                      if rid.startswith('cw.entityxml.action.'))
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   122
6960
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   123
    # mapping handling #########################################################
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   124
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   125
    def add_schema_config(self, schemacfg, checkonly=False):
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   126
        """added CWSourceSchemaConfig, modify mapping accordingly"""
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   127
        _ = self._cw._
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   128
        try:
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   129
            rtype = schemacfg.schema.rtype.name
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   130
        except AttributeError:
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   131
            msg = _("entity and relation types can't be mapped, only attributes "
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   132
                    "or relations")
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   133
            raise ValidationError(schemacfg.eid, {rn('cw_for_schema', 'subject'): msg})
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   134
        if schemacfg.options:
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   135
            options = text_to_dict(schemacfg.options)
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   136
        else:
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   137
            options = {}
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   138
        try:
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   139
            role = options.pop('role')
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   140
            if role not in ('subject', 'object'):
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   141
                raise KeyError
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   142
        except KeyError:
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   143
            msg = _('"role=subject" or "role=object" must be specified in options')
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   144
            raise ValidationError(schemacfg.eid, {rn('options', 'subject'): msg})
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   145
        try:
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   146
            action = options.pop('action')
7553
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   147
            linker = self.select_linker(action, rtype, role)
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   148
            linker.check_options(options, schemacfg.eid)
6960
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   149
        except KeyError:
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   150
            msg = _('"action" must be specified in options; allowed values are '
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   151
                    '%s') % ', '.join(self.action_methods)
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   152
            raise ValidationError(schemacfg.eid, {rn('options', 'subject'): msg})
7553
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   153
        except RegistryException:
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   154
            msg = _('allowed values for "action" are %s') % ', '.join(self.list_actions())
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   155
            raise ValidationError(schemacfg.eid, {rn('options', 'subject'): msg})
6960
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   156
        if not checkonly:
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   157
            if role == 'subject':
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   158
                etype = schemacfg.schema.stype.name
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   159
                ttype = schemacfg.schema.otype.name
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   160
            else:
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   161
                etype = schemacfg.schema.otype.name
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   162
                ttype = schemacfg.schema.stype.name
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   163
            etyperules = self.source.mapping.setdefault(etype, {})
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   164
            etyperules.setdefault((rtype, role, action), []).append(
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   165
                (ttype, options) )
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   166
            self.source.mapping_idx[schemacfg.eid] = (
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   167
                etype, rtype, role, action, ttype)
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   168
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   169
    def del_schema_config(self, schemacfg, checkonly=False):
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   170
        """deleted CWSourceSchemaConfig, modify mapping accordingly"""
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   171
        etype, rtype, role, action, ttype = self.source.mapping_idx[schemacfg.eid]
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   172
        rules = self.source.mapping[etype][(rtype, role, action)]
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   173
        rules = [x for x in rules if not x[0] == ttype]
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   174
        if not rules:
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   175
            del self.source.mapping[etype][(rtype, role, action)]
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   176
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   177
    # import handling ##########################################################
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   178
7531
e891ca479586 [datafeed, cwxml] parser now try to complete source's urls so one can add url such as <myinstance>/project. Closes #1759908
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7481
diff changeset
   179
    def process(self, url, raise_on_error=False, partialcommit=True):
e891ca479586 [datafeed, cwxml] parser now try to complete source's urls so one can add url such as <myinstance>/project. Closes #1759908
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7481
diff changeset
   180
        """IDataFeedParser main entry point"""
e891ca479586 [datafeed, cwxml] parser now try to complete source's urls so one can add url such as <myinstance>/project. Closes #1759908
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7481
diff changeset
   181
        super(CWEntityXMLParser, self).process(self.complete_url(url),
e891ca479586 [datafeed, cwxml] parser now try to complete source's urls so one can add url such as <myinstance>/project. Closes #1759908
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7481
diff changeset
   182
                                               raise_on_error, partialcommit)
7553
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   183
    def parse_etree(self, parent):
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   184
        for node in list(parent):
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   185
            builder = self._cw.vreg['components'].select(
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   186
                'cw.entityxml.item-builder', self._cw, node=node,
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   187
                parser=self)
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   188
            yield builder.build_item()
6960
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   189
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   190
    def process_item(self, item, rels):
7354
f627ab500fda [parsers] various refactorings
Nicolas Chauvat <nicolas.chauvat@logilab.fr>
parents: 7351
diff changeset
   191
        entity = self.extid2entity(str(item.pop('cwuri')),  item.pop('cwtype'),
7534
d58a9d96aad8 [datafeed, cw.xml] xml now carry entity's source information, interpreted at the other end so that for instance when an entity from elo is seen when importing cwo, it's properly marked as coming from elo source if one exists
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7532
diff changeset
   192
                                   cwsource=item.pop('cwsource'), item=item)
7399
972ed1843bd8 [multi-sources] support for moving an entity from an external source (closes #343818)
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7378
diff changeset
   193
        if entity is None:
972ed1843bd8 [multi-sources] support for moving an entity from an external source (closes #343818)
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7378
diff changeset
   194
            return None
7474
7dc405ad7bf3 [datafeed cwxml parser] cache processed urls/entities to avoid unnecessary http requests and processing
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7470
diff changeset
   195
        if entity.eid in self._processed_entities:
7dc405ad7bf3 [datafeed cwxml parser] cache processed urls/entities to avoid unnecessary http requests and processing
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7470
diff changeset
   196
            return entity
7dc405ad7bf3 [datafeed cwxml parser] cache processed urls/entities to avoid unnecessary http requests and processing
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7470
diff changeset
   197
        self._processed_entities.add(entity.eid)
7354
f627ab500fda [parsers] various refactorings
Nicolas Chauvat <nicolas.chauvat@logilab.fr>
parents: 7351
diff changeset
   198
        if not (self.created_during_pull(entity) or self.updated_during_pull(entity)):
6960
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   199
            self.notify_updated(entity)
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   200
            item.pop('eid')
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   201
            # XXX check modification date
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   202
            attrs = extract_typed_attrs(entity.e_schema, item)
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   203
            entity.set_attributes(**attrs)
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   204
        for (rtype, role, action), rules in self.source.mapping.get(entity.__regid__, {}).iteritems():
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   205
            try:
7354
f627ab500fda [parsers] various refactorings
Nicolas Chauvat <nicolas.chauvat@logilab.fr>
parents: 7351
diff changeset
   206
                related_items = rels[role][rtype]
6960
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   207
            except KeyError:
7354
f627ab500fda [parsers] various refactorings
Nicolas Chauvat <nicolas.chauvat@logilab.fr>
parents: 7351
diff changeset
   208
                self.source.error('relation %s-%s not found in xml export of %s',
6960
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   209
                                  rtype, role, entity.__regid__)
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   210
                continue
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   211
            try:
7553
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   212
                linker = self.select_linker(action, rtype, role, entity)
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   213
            except RegistryException:
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   214
                self.source.error('no linker for action %s', action)
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   215
            else:
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   216
                linker.link_items(related_items, rules)
6960
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   217
        return entity
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   218
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   219
    def before_entity_copy(self, entity, sourceparams):
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   220
        """IDataFeedParser callback"""
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   221
        attrs = extract_typed_attrs(entity.e_schema, sourceparams['item'])
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   222
        entity.cw_edited.update(attrs)
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   223
7553
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   224
    def complete_url(self, url, etype=None, add_relations=True):
7531
e891ca479586 [datafeed, cwxml] parser now try to complete source's urls so one can add url such as <myinstance>/project. Closes #1759908
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7481
diff changeset
   225
        """append to the url's query string information about relation that should
e891ca479586 [datafeed, cwxml] parser now try to complete source's urls so one can add url such as <myinstance>/project. Closes #1759908
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7481
diff changeset
   226
        be included in the resulting xml, according to source mapping.
e891ca479586 [datafeed, cwxml] parser now try to complete source's urls so one can add url such as <myinstance>/project. Closes #1759908
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7481
diff changeset
   227
e891ca479586 [datafeed, cwxml] parser now try to complete source's urls so one can add url such as <myinstance>/project. Closes #1759908
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7481
diff changeset
   228
        If etype is not specified, try to guess it using the last path part of
e891ca479586 [datafeed, cwxml] parser now try to complete source's urls so one can add url such as <myinstance>/project. Closes #1759908
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7481
diff changeset
   229
        the url.
e891ca479586 [datafeed, cwxml] parser now try to complete source's urls so one can add url such as <myinstance>/project. Closes #1759908
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7481
diff changeset
   230
        """
e891ca479586 [datafeed, cwxml] parser now try to complete source's urls so one can add url such as <myinstance>/project. Closes #1759908
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7481
diff changeset
   231
        try:
e891ca479586 [datafeed, cwxml] parser now try to complete source's urls so one can add url such as <myinstance>/project. Closes #1759908
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7481
diff changeset
   232
            url, qs = url.split('?', 1)
e891ca479586 [datafeed, cwxml] parser now try to complete source's urls so one can add url such as <myinstance>/project. Closes #1759908
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7481
diff changeset
   233
        except ValueError:
e891ca479586 [datafeed, cwxml] parser now try to complete source's urls so one can add url such as <myinstance>/project. Closes #1759908
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7481
diff changeset
   234
            qs = ''
e891ca479586 [datafeed, cwxml] parser now try to complete source's urls so one can add url such as <myinstance>/project. Closes #1759908
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7481
diff changeset
   235
        if etype is None:
e891ca479586 [datafeed, cwxml] parser now try to complete source's urls so one can add url such as <myinstance>/project. Closes #1759908
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7481
diff changeset
   236
            try:
e891ca479586 [datafeed, cwxml] parser now try to complete source's urls so one can add url such as <myinstance>/project. Closes #1759908
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7481
diff changeset
   237
                etype = url.rsplit('/', 1)[1]
e891ca479586 [datafeed, cwxml] parser now try to complete source's urls so one can add url such as <myinstance>/project. Closes #1759908
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7481
diff changeset
   238
            except ValueError:
e891ca479586 [datafeed, cwxml] parser now try to complete source's urls so one can add url such as <myinstance>/project. Closes #1759908
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7481
diff changeset
   239
                return url
e891ca479586 [datafeed, cwxml] parser now try to complete source's urls so one can add url such as <myinstance>/project. Closes #1759908
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7481
diff changeset
   240
            try:
e891ca479586 [datafeed, cwxml] parser now try to complete source's urls so one can add url such as <myinstance>/project. Closes #1759908
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7481
diff changeset
   241
                etype = self._cw.vreg.case_insensitive_etypes[etype]
e891ca479586 [datafeed, cwxml] parser now try to complete source's urls so one can add url such as <myinstance>/project. Closes #1759908
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7481
diff changeset
   242
            except KeyError:
e891ca479586 [datafeed, cwxml] parser now try to complete source's urls so one can add url such as <myinstance>/project. Closes #1759908
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7481
diff changeset
   243
                return url
e891ca479586 [datafeed, cwxml] parser now try to complete source's urls so one can add url such as <myinstance>/project. Closes #1759908
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7481
diff changeset
   244
        params = parse_qs(qs)
e891ca479586 [datafeed, cwxml] parser now try to complete source's urls so one can add url such as <myinstance>/project. Closes #1759908
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7481
diff changeset
   245
        if not 'vid' in params:
e891ca479586 [datafeed, cwxml] parser now try to complete source's urls so one can add url such as <myinstance>/project. Closes #1759908
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7481
diff changeset
   246
            params['vid'] = ['xml']
7553
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   247
        if add_relations:
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   248
            relations = params.setdefault('relation', [])
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   249
            for rtype, role, _ in self.source.mapping.get(etype, ()):
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   250
                reldef = '%s-%s' % (rtype, role)
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   251
                if not reldef in relations:
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   252
                    relations.append(reldef)
7531
e891ca479586 [datafeed, cwxml] parser now try to complete source's urls so one can add url such as <myinstance>/project. Closes #1759908
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7481
diff changeset
   253
        return url + '?' + self._cw.build_url_params(**params)
e891ca479586 [datafeed, cwxml] parser now try to complete source's urls so one can add url such as <myinstance>/project. Closes #1759908
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7481
diff changeset
   254
7553
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   255
    def complete_item(self, item, add_relations=True):
7474
7dc405ad7bf3 [datafeed cwxml parser] cache processed urls/entities to avoid unnecessary http requests and processing
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7470
diff changeset
   256
        try:
7dc405ad7bf3 [datafeed cwxml parser] cache processed urls/entities to avoid unnecessary http requests and processing
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7470
diff changeset
   257
            return self._parsed_urls[(item['cwuri'], add_relations)]
7dc405ad7bf3 [datafeed cwxml parser] cache processed urls/entities to avoid unnecessary http requests and processing
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7470
diff changeset
   258
        except KeyError:
7553
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   259
            itemurl = self.complete_url(item['cwuri'], item['cwtype'],
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   260
                                        add_relations)
7474
7dc405ad7bf3 [datafeed cwxml parser] cache processed urls/entities to avoid unnecessary http requests and processing
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7470
diff changeset
   261
            item_rels = list(self.parse(itemurl))
7dc405ad7bf3 [datafeed cwxml parser] cache processed urls/entities to avoid unnecessary http requests and processing
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7470
diff changeset
   262
            assert len(item_rels) == 1, 'url %s expected to bring back one '\
7dc405ad7bf3 [datafeed cwxml parser] cache processed urls/entities to avoid unnecessary http requests and processing
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7470
diff changeset
   263
                   'and only one entity, got %s' % (itemurl, len(item_rels))
7dc405ad7bf3 [datafeed cwxml parser] cache processed urls/entities to avoid unnecessary http requests and processing
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7470
diff changeset
   264
            self._parsed_urls[(item['cwuri'], add_relations)] = item_rels[0]
7dc405ad7bf3 [datafeed cwxml parser] cache processed urls/entities to avoid unnecessary http requests and processing
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7470
diff changeset
   265
            return item_rels[0]
6960
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   266
7553
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   267
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   268
class CWEntityXMLItemBuilder(Component):
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   269
    __regid__ = 'cw.entityxml.item-builder'
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   270
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   271
    def __init__(self, _cw, parser, node, **kwargs):
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   272
        super(CWEntityXMLItemBuilder, self).__init__(_cw, **kwargs)
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   273
        self.parser = parser
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   274
        self.node = node
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   275
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   276
    def build_item(self):
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   277
        node = self.node
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   278
        item = dict(node.attrib.items())
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   279
        item['cwtype'] = unicode(node.tag)
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   280
        item.setdefault('cwsource', None)
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   281
        try:
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   282
            item['eid'] = typed_eid(item['eid'])
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   283
        except KeyError:
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   284
            # cw < 3.11 compat mode XXX
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   285
            item['eid'] = typed_eid(node.find('eid').text)
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   286
            item['cwuri'] = node.find('cwuri').text
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   287
        rels = {}
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   288
        for child in node:
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   289
            role = child.get('role')
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   290
            if role:
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   291
                # relation
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   292
                related = rels.setdefault(role, {}).setdefault(child.tag, [])
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   293
                related += [ritem for ritem, _ in self.parser.parse_etree(child)]
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   294
            else:
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   295
                # attribute
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   296
                item[child.tag] = unicode(child.text)
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   297
        return item, rels
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   298
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   299
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   300
class CWEntityXMLActionCopy(Component):
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   301
    """implementation of cubicweb entity xml parser's'copy' action
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   302
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   303
    Takes no option.
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   304
    """
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   305
    __regid__ = 'cw.entityxml.action.copy'
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   306
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   307
    def __init__(self, _cw, parser, rtype, role, entity=None, **kwargs):
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   308
        super(CWEntityXMLActionCopy, self).__init__(_cw, **kwargs)
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   309
        self.parser = parser
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   310
        self.rtype = rtype
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   311
        self.role = role
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   312
        self.entity = entity
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   313
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   314
    @classproperty
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   315
    def action(cls):
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   316
        return cls.__regid__.rsplit('.', 1)[-1]
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   317
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   318
    def check_options(self, options, eid):
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   319
        self._check_no_options(options, eid)
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   320
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   321
    def _check_no_options(self, options, eid, msg=None):
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   322
        if options:
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   323
            if msg is None:
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   324
                msg = self._cw._("'%s' action doesn't take any options") % self.action
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   325
            raise ValidationError(eid, {rn('options', 'subject'): msg})
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   326
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   327
    def link_items(self, others, rules):
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   328
        assert not any(x[1] for x in rules), "'copy' action takes no option"
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   329
        ttypes = frozenset([x[0] for x in rules])
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   330
        eids = [] # local eids
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   331
        for item in others:
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   332
            if item['cwtype'] in ttypes:
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   333
                item = self.parser.complete_item(item)[0]
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   334
                other_entity = self.parser.process_item(item, [])
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   335
                if other_entity is not None:
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   336
                    eids.append(other_entity.eid)
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   337
        if eids:
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   338
            self._set_relation(eids)
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   339
        else:
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   340
            self._clear_relation(ttypes)
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   341
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   342
    def _clear_relation(self, ttypes):
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   343
        if not self.parser.created_during_pull(self.entity):
6960
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   344
            if len(ttypes) > 1:
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   345
                typerestr = ', Y is IN(%s)' % ','.join(ttypes)
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   346
            else:
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   347
                typerestr = ', Y is %s' % ','.join(ttypes)
7553
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   348
            self._cw.execute('DELETE ' + rtype_role_rql(self.rtype, self.role) + typerestr,
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   349
                             {'x': self.entity.eid})
6960
822f2530570d [datafeed] add parser to import cubicweb xml
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents:
diff changeset
   350
7553
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   351
    def _set_relation(self, eids):
7399
972ed1843bd8 [multi-sources] support for moving an entity from an external source (closes #343818)
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7378
diff changeset
   352
        assert eids
7553
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   353
        rtype = self.rtype
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   354
        rqlbase = rtype_role_rql(rtype, self.role)
7399
972ed1843bd8 [multi-sources] support for moving an entity from an external source (closes #343818)
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7378
diff changeset
   355
        eidstr = ','.join(str(eid) for eid in eids)
972ed1843bd8 [multi-sources] support for moving an entity from an external source (closes #343818)
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7378
diff changeset
   356
        self._cw.execute('DELETE %s, NOT Y eid IN (%s)' % (rqlbase, eidstr),
7553
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   357
                         {'x': self.entity.eid})
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   358
        if self.role == 'object':
7399
972ed1843bd8 [multi-sources] support for moving an entity from an external source (closes #343818)
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7378
diff changeset
   359
            rql = 'SET %s, Y eid IN (%s), NOT Y %s X' % (rqlbase, eidstr, rtype)
972ed1843bd8 [multi-sources] support for moving an entity from an external source (closes #343818)
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7378
diff changeset
   360
        else:
972ed1843bd8 [multi-sources] support for moving an entity from an external source (closes #343818)
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7378
diff changeset
   361
            rql = 'SET %s, Y eid IN (%s), NOT X %s Y' % (rqlbase, eidstr, rtype)
7553
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   362
        self._cw.execute(rql, {'x': self.entity.eid})
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   363
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   364
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   365
class CWEntityXMLActionLink(CWEntityXMLActionCopy):
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   366
    """implementation of cubicweb entity xml parser's'link' action
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   367
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   368
    requires a 'linkattr' option to control search of the linked entity.
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   369
    """
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   370
    __regid__ = 'cw.entityxml.action.link'
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   371
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   372
    def check_options(self, options, eid):
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   373
        if not 'linkattr' in options:
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   374
            msg = self._cw._("'%s' action requires 'linkattr' option") % self.action
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   375
            raise ValidationError(eid, {rn('options', 'subject'): msg})
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   376
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   377
    create_when_not_found = False
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   378
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   379
    def link_items(self, others, rules):
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   380
        for ttype, options in rules:
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   381
            searchattrs = splitstrip(options.get('linkattr', ''))
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   382
            self._related_link(ttype, others, searchattrs)
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   383
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   384
    def _related_link(self, ttype, others, searchattrs):
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   385
        def issubset(x,y):
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   386
            return all(z in y for z in x)
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   387
        eids = [] # local eids
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   388
        source = self.parser.source
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   389
        for item in others:
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   390
            if item['cwtype'] != ttype:
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   391
                continue
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   392
            if not issubset(searchattrs, item):
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   393
                item = self.parser.complete_item(item, False)[0]
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   394
                if not issubset(searchattrs, item):
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   395
                    source.error('missing attribute, got %s expected keys %s',
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   396
                                 item, searchattrs)
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   397
                    continue
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   398
            # XXX str() needed with python < 2.6
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   399
            kwargs = dict((str(attr), item[attr]) for attr in searchattrs)
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   400
            targets = self._find_entities(item, kwargs)
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   401
            if len(targets) > 1:
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   402
                source.error('ambiguous link: found %s entity %s with attributes %s',
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   403
                             len(targets), item['cwtype'], kwargs)
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   404
            elif len(targets) == 1:
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   405
                eids.append(targets[0].eid)
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   406
            elif self.create_when_not_found:
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   407
                eids.append(self._cw.create_entity(item['cwtype'], **kwargs).eid)
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   408
            else:
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   409
                source.error('can not find %s entity with attributes %s',
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   410
                             item['cwtype'], kwargs)
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   411
        if eids:
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   412
            self._set_relation(eids)
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   413
        else:
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   414
            self._clear_relation((ttype,))
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   415
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   416
    def _find_entities(self, item, kwargs):
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   417
        return tuple(self._cw.find_entities(item['cwtype'], **kwargs))
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   418
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   419
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   420
class CWEntityXMLActionLinkInState(CWEntityXMLActionLink):
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   421
    """custom implementation of cubicweb entity xml parser's'link' action for
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   422
    in_state relation
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   423
    """
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   424
    __select__ = match_rtype('in_state')
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   425
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   426
    def check_options(self, options, eid):
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   427
        super(CWEntityXMLActionLinkInState, self).check_options(options, eid)
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   428
        if not 'name' in options['linkattr']:
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   429
            msg = self._cw._("'%s' action for in_state relation should at least have 'linkattr=name' option") % self.action
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   430
            raise ValidationError(eid, {rn('options', 'subject'): msg})
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   431
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   432
    def _find_entities(self, item, kwargs):
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   433
        assert 'name' in item # XXX else, complete_item
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   434
        state_name = item['name']
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   435
        wf = self.entity.cw_adapt_to('IWorkflowable').current_workflow
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   436
        state = wf.state_by_name(state_name)
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   437
        if state is None:
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   438
            return ()
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   439
        return (state,)
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   440
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   441
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   442
class CWEntityXMLActionLinkOrCreate(CWEntityXMLActionLink):
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   443
    """implementation of cubicweb entity xml parser's'link-or-create' action
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   444
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   445
    requires a 'linkattr' option to control search of the linked entity.
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   446
    """
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   447
    __regid__ = 'cw.entityxml.action.link-or-create'
935423529f45 [datafeed cw parser] refactor: split logic that was in the parser
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7534
diff changeset
   448
    create_when_not_found = True
6963
5774d4ba4306 [datafeed] introduce a host mapping so dev instance may transparently redirect request to another host than the actual's one
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 6960
diff changeset
   449
7531
e891ca479586 [datafeed, cwxml] parser now try to complete source's urls so one can add url such as <myinstance>/project. Closes #1759908
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 7481
diff changeset
   450
6963
5774d4ba4306 [datafeed] introduce a host mapping so dev instance may transparently redirect request to another host than the actual's one
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 6960
diff changeset
   451
def registration_callback(vreg):
6970
a6ccbfbacf3d [parser host mapping] take care to cases where apphome is None (c-c i18ncube command for instance)
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 6963
diff changeset
   452
    vreg.register_all(globals().values(), __name__)
6963
5774d4ba4306 [datafeed] introduce a host mapping so dev instance may transparently redirect request to another host than the actual's one
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 6960
diff changeset
   453
    global HOST_MAPPING
6970
a6ccbfbacf3d [parser host mapping] take care to cases where apphome is None (c-c i18ncube command for instance)
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 6963
diff changeset
   454
    HOST_MAPPING = {}
a6ccbfbacf3d [parser host mapping] take care to cases where apphome is None (c-c i18ncube command for instance)
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 6963
diff changeset
   455
    if vreg.config.apphome:
a6ccbfbacf3d [parser host mapping] take care to cases where apphome is None (c-c i18ncube command for instance)
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 6963
diff changeset
   456
        host_mapping_file = osp.join(vreg.config.apphome, 'hostmapping.py')
a6ccbfbacf3d [parser host mapping] take care to cases where apphome is None (c-c i18ncube command for instance)
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 6963
diff changeset
   457
        if osp.exists(host_mapping_file):
a6ccbfbacf3d [parser host mapping] take care to cases where apphome is None (c-c i18ncube command for instance)
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 6963
diff changeset
   458
            HOST_MAPPING = eval(file(host_mapping_file).read())
a6ccbfbacf3d [parser host mapping] take care to cases where apphome is None (c-c i18ncube command for instance)
Sylvain Thénault <sylvain.thenault@logilab.fr>
parents: 6963
diff changeset
   459
            vreg.info('using host mapping %s from %s', HOST_MAPPING, host_mapping_file)