import json
import jsonschema
import requests
-from requests.utils import urlparse, urlunparse
import types
-from urlparse import urljoin
+from urlparse import urljoin, urlparse, urlunparse
LOGGER = logging.getLogger(__name__)
# provide common defaults.
None: {
# terms in multiple encoded objects
+ 'award': { '@type': '@id' },
+ 'dataset': {'@type': '@id'},
'description': 'rdf:description',
+ 'documents': { '@type': '@id' },
'experiment': {'@type': '@id'},
'href': { '@type': '@id' },
'lab': { '@type': '@id' },
'library': {'@type': '@id' },
'pi': { '@type': '@id' },
'platform': { '@type': '@id' },
+ 'replicates': { '@type': '@id' },
'submitted_by': { '@type': '@id' },
'url': { '@type': '@id' },
},
},
'experiment': {
"assay_term_id": { "@type": "@id" },
- },
- 'file': {
- 'dataset': {'@type': '@id'},
+ "files": { "@type": "@id" },
+ "original_files": { "@type": "@id"},
},
# I tried to use the JSON-LD mapping capabilities to convert the lab
# contact information into a vcard record, but the encoded model
# "state": "vcard:region",
# "country": "vcard:country"
#},
- 'human_donor': {
- 'award': { '@type': '@id' },
- },
'library': {
- 'award': { '@type': '@id' },
'nucleic_acid_term_id': { '@type': '@id' }
}
}
#FIXME: this needs to be initialized from rdfns
-_encoded_namespaces = {
+ENCODED_NAMESPACES = {
# JSON-LD lets you define namespaces so you can used the shorted url syntax.
# (instead of http://www.w3.org/2000/01/rdf-schema#label you can do
# rdfs:label)
# OBI: available from http://svn.code.sf.net/p/obi/code/releases/2012-07-01/merged/merged-obi-comments.owl
'SO': 'http://purl.obolibrary.org/obo/SO_', # Sequence ontology
# SO: available from http://www.berkeleybop.org/ontologies/so.owl
+ # NTR: New Term Request space for DCC to implement new ontology terms
}
-ENCODED_CONTEXT[None].update(_encoded_namespaces)
+
ENCODED_SCHEMA_ROOT='/profiles/'
class ENCODED:
'''Programatic access encoded, the software powering ENCODE3's submit site.
'''
- def __init__(self, server, context=None):
+ def __init__(self, server, contexts=None):
self.server = server
self.username = None
self.password = None
- self.context = context if context else ENCODED_CONTEXT
+ self.contexts = contexts if contexts else ENCODED_CONTEXT
self.schemas = {}
def get_auth(self):
self.username = authenticators[0]
self.password = authenticators[2]
- def add_jsonld_context(self, tree, contexts, base):
+ def add_jsonld_context(self, tree, default_base):
"""Add contexts to various objects in the tree.
tree is a json tree returned from the DCC's encoded database.
base, if supplied allows setting the base url that relative
urls will be resolved against.
"""
- tree['@context'] = contexts[None]
- tree['@context']['@base'] = base
- self.add_jsonld_child_context(tree, contexts)
+ self.add_jsonld_child_context(tree, default_base)
+ self.add_jsonld_namespaces(tree['@context'])
- def add_jsonld_child_context(self, obj, contexts):
+ def add_jsonld_child_context(self, obj, default_base):
'''Add JSON-LD context to the encoded JSON.
This is recursive because some of the IDs were relative URLs
if isinstance(obj, collections.Sequence):
# how should I update lists?
for v in obj:
- self.add_jsonld_child_context(v, contexts)
+ self.add_jsonld_child_context(v, default_base)
return
if isinstance(obj, collections.Mapping):
for v in obj.values():
- self.add_jsonld_child_context(v, contexts)
+ self.add_jsonld_child_context(v, default_base)
# we have an object. attach a context to it.
if self._is_encoded_object(obj):
- default_base = contexts[None]['@base']
- context = {'@base': urljoin(default_base, obj['@id']),
- '@vocab': self.get_schema_url(obj)}
- for t in obj['@type']:
- if t in contexts:
- context.update(contexts[t])
+ context = self.create_jsonld_context(obj, default_base)
if len(context) > 0:
obj.setdefault('@context', {}).update(context)
+ def add_jsonld_namespaces(self, context):
+ '''Add shortcut namespaces to a context
+
+ Only needs to be run on the top-most context
+ '''
+ context.update(ENCODED_NAMESPACES)
+
+ def create_jsonld_context(self, obj, default_base):
+ '''Synthesize the context for a encoded type
+
+ self.contexts[None] = default context attributes added to any type
+ self.contexts[type] = context attributes for this type.
+ '''
+ context = {'@base': urljoin(default_base, obj['@id']),
+ '@vocab': self.get_schema_url(obj)}
+ # add in defaults
+ context.update(self.contexts[None])
+ for t in obj['@type']:
+ if t in self.contexts:
+ context.update(self.contexts[t])
+ return context
+
def get_json(self, obj_id, **kwargs):
'''GET an ENCODE object as JSON and return as dict
'''
url = self.prepare_url(obj_id)
json = self.get_json(obj_id, **kwargs)
- self.add_jsonld_context(json, self.context, url)
+ self.add_jsonld_context(json, url)
return json
def get_object_type(self, obj):
def get_schema_url(self, obj):
obj_type = self.get_object_type(obj)
if obj_type:
- return self.prepare_url(ENCODED_SCHEMA_ROOT + obj_type + '.json')
+ return self.prepare_url(ENCODED_SCHEMA_ROOT + obj_type + '.json') + '#'
def _is_encoded_object(self, obj):
'''Test to see if an object is a JSON-LD object
# clean up potentially messy urls
url = urlparse(request_url)._asdict()
if not url['scheme']:
- url['scheme'] = 'http'
+ url['scheme'] = 'https'
if not url['netloc']:
url['netloc'] = self.server
url = urlunparse(url.values())
return url
+ def search_jsonld(self, term, **kwargs):
+ '''Send search request to ENCODED
+ '''
+ url = self.prepare_url('/search/')
+ result = self.get_json(url, searchTerm=term, **kwargs)
+ self.convert_search_to_jsonld(result)
+ return result
+
+ def convert_search_to_jsonld(self, result):
+ '''Add the context to search result
+
+ Also remove hard to handle nested attributes
+ e.g. remove object.term when we have no id
+ '''
+ graph = result['@graph']
+ for i, obj in enumerate(graph):
+ # suppress nested attributes
+ graph[i] = {k: v for k, v in obj.items() if '.' not in k}
+
+ self.add_jsonld_context(result, self.prepare_url(result['@id']))
+ return result
+
def validate(self, obj):
obj_type = self.get_object_type(obj)
schema_url = self.get_schema_url(obj)
projects / htsworkflow.git / blobdiff