def similar(entity_id):
enable_cache()
entity = get_index_entity(entity_id, request.authz.READ)
tag_request(collection_id=entity.get('collection_id'))
entity = model.get_proxy(entity)
result = MatchQuery.handle(request, entity=entity)
return EntitySerializer.jsonify_result(result)
def entities_index(entityset_id):
"""Search entities in the entity set with id `entityset_id`.
---
get:
summary: Search entities in the entity set with id `entityset_id`
description: >
Supports all query filters and arguments present in the normal
entity search API, but all resulting entities will be members of
the set.
parameters:
- description: The entityset id.
in: path
name: entityset_id
required: true
schema:
type: string
example: 3a0d91ece2dce88ad3259594c7b642485235a048
responses:
'200':
description: Resturns a list of entities in result
content:
application/json:
schema:
$ref: '#/components/schemas/EntitiesResponse'
tags:
- EntitySet
"""
entityset = get_entityset(entityset_id, request.authz.READ)
parser = SearchQueryParser(request.args, request.authz)
tag_request(query=parser.text, prefix=parser.prefix)
result = EntitySetItemsQuery.handle(request,
parser=parser,
entityset=entityset)
return EntitySerializer.jsonify_result(result)
def similar(entity_id):
enable_cache()
entity = get_index_entity(entity_id, request.authz.READ)
entity = model.get_proxy(entity)
record_audit(Audit.ACT_ENTITY, id=entity_id)
result = MatchQuery.handle(request, entity=entity)
return EntitySerializer.jsonify_result(result)
def similar(entity_id):
enable_cache()
entity = get_index_entity(entity_id, request.authz.READ)
tag_request(collection_id=entity.get('collection_id'))
entity = model.get_proxy(entity)
record_audit(Audit.ACT_ENTITY, id=entity_id)
result = MatchQuery.handle(request, entity=entity)
return EntitySerializer.jsonify_result(result)
def match():
entity = parse_request(EntityUpdateSchema)
entity = model.get_proxy(entity)
tag_request(schema=entity.schema.name, caption=entity.caption)
collection_ids = request.args.getlist('collection_ids')
result = MatchQuery.handle(request, entity=entity,
collection_ids=collection_ids)
return EntitySerializer.jsonify_result(result)
def match():
entity = parse_request(EntityUpdateSchema)
record_audit(Audit.ACT_MATCH, entity=entity)
entity = model.get_proxy(entity)
collection_ids = request.args.getlist('collection_ids')
result = MatchQuery.handle(request, entity=entity,
collection_ids=collection_ids)
return EntitySerializer.jsonify_result(result)
def match():
entity = parse_request(EntityUpdateSchema)
record_audit(Audit.ACT_MATCH, entity=entity)
entity = model.get_proxy(entity)
tag_request(schema=entity.schema.name, caption=entity.caption)
collection_ids = request.args.getlist('collection_ids')
result = MatchQuery.handle(request, entity=entity,
collection_ids=collection_ids)
return EntitySerializer.jsonify_result(result)
def index():
# enable_cache(vary_user=True)
parser = SearchQueryParser(request.args, request.authz)
result = EntitiesQuery.handle(request, parser=parser)
links = {}
if request.authz.logged_in and result.total <= EXPORT_MAX:
query = list(request.args.items(multi=True))
links['export'] = url_for('entities_api.export',
format='excel',
_authorize=True,
_query=query)
return EntitySerializer.jsonify_result(result, extra={'links': links})
def index():
# enable_cache(vary_user=True)
parser = SearchQueryParser(request.args, request.authz)
tag_request(query=parser.text, prefix=parser.prefix)
result = EntitiesQuery.handle(request, parser=parser)
links = {}
if request.authz.logged_in and result.total <= EXPORT_MAX:
query = list(request.args.items(multi=True))
links['export'] = url_for('entities_api.export',
format='excel',
_authorize=True,
_query=query)
return EntitySerializer.jsonify_result(result, extra={'links': links})
def index():
# enable_cache(vary_user=True)
parser = SearchQueryParser(request.args, request.authz)
if parser.text:
QueryLog.save(request.authz.id, request._session_id, parser.text)
db.session.commit()
tag_request(query=parser.text, prefix=parser.prefix)
result = EntitiesQuery.handle(request, parser=parser)
links = {}
if request.authz.logged_in and result.total <= MAX_PAGE:
query = list(request.args.items(multi=True))
links['export'] = url_for('entities_api.export',
_authorize=True,
_query=query)
return EntitySerializer.jsonify_result(result, extra={'links': links})
def similar(entity_id):
"""
---
get:
summary: Get similar entities
description: >
Get a list of similar entities to the entity with id `entity_id`
parameters:
- in: path
name: entity_id
required: true
schema:
type: string
- in: query
name: 'filter:schema'
schema:
items:
type: string
type: array
- in: query
name: 'filter:schemata'
schema:
items:
type: string
type: array
responses:
'200':
description: Returns a list of entities
content:
application/json:
schema:
$ref: '#/components/schemas/EntitiesResponse'
tags:
- Entity
"""
enable_cache()
entity = get_index_entity(entity_id, request.authz.READ)
tag_request(collection_id=entity.get('collection_id'))
entity = model.get_proxy(entity)
result = MatchQuery.handle(request, entity=entity)
return EntitySerializer.jsonify_result(result)
def match():
"""
---
post:
summary: Query for similar entities
description: >-
Query for similar entities matching a given entity inside a given list
of collections.
parameters:
- in: query
name: collection_ids
schema:
type: array
items:
type: string
responses:
'200':
description: Returns a list of entities in result
content:
application/json:
schema:
$ref: '#/components/schemas/EntitiesResponse'
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/EntityUpdate'
tags:
- Entity
"""
entity = parse_request("EntityUpdate")
entity = model.get_proxy(entity, cleaned=False)
tag_request(schema=entity.schema.name, caption=entity.caption)
collection_ids = request.args.getlist("collection_ids")
result = MatchQuery.handle(request,
entity=entity,
collection_ids=collection_ids)
return EntitySerializer.jsonify_result(result)
def index():
"""
---
get:
summary: Search entities
description: >
Returns a list of entities matching the given search criteria.
A filter can be applied to show only results from a particular
collection: `?filter:collection_id={collection_id}`.
If you know you only want to search documents (unstructured, ingested
data) or entities (structured data which may have been extracted from
a dataset, or entered by a human) you can use these arguments with the
`/documents` or `/entities` endpoints.
parameters:
- description: >-
A query string in ElasticSearch query syntax. Can include field
searches, such as `title:penguin`
in: query
name: q
schema:
type: string
- description: >-
Return facet values for the given metadata field, such as
`languages`, `countries`, `mime_type` or `extension`. This can be
specified multiple times for more than one facet to be added.
in: query
name: facet
schema:
type: string
- description: >
Filter the results by the given field. This is useful when used in
conjunction with facet to create a drill-down mechanism. Useful
fields are:
- `collection_id`, documents belonging to a particular collection.
- `title`, of the document.
- `file_name`, of the source file.
- `source_url`, URL of the source file.
- `extension`, file extension of the source file.
- `languages`, in the document.
- `countries`, associated with the document.
- `keywords`, from the document.
- `emails`, email addresses mentioned in the document.
- `domains`, websites mentioned in the document.
- `phones`, mentioned in the document.
- `dates`, in any of the following formats: yyyy-MM-dd, yyyy-MM,
yyyy-MM-d, yyyy-M, yyyy
- `mime_type`, of the source file.
- `author`, according to the source file's metadata.
- `summary`, of the document.
- `text`, entire text extracted from the document.
- `created_at`, when the document was added to aleph (yyyy-mm
-ddThh:ii:ss.uuuuuu).
- `updated_at`, when the document was modified in aleph (yyyy
-mm-ddThh:ii:ss.uuuuuu).
in: query
name: 'filter:{field_name}'
schema:
type: string
- description: 'The number of results to return, max. 10,000.'
in: query
name: limit
schema:
type: integer
- description: >
The number of results to skip at the beginning of the result set.
in: query
name: offset
schema:
type: integer
responses:
'200':
description: Resturns a list of entities in result
content:
application/json:
schema:
$ref: '#/components/schemas/EntitiesResponse'
tags:
- Entity
"""
# enable_cache(vary_user=True)
parser = SearchQueryParser(request.values, request.authz)
result = EntitiesQuery.handle(request, parser=parser)
tag_request(query=result.query.to_text(), prefix=parser.prefix)
links = {}
if request.authz.logged_in and result.total <= MAX_PAGE:
query = list(request.args.items(multi=True))
links["export"] = url_for("entities_api.export", _query=query)
return EntitySerializer.jsonify_result(result, extra={"links": links})
def index():
# enable_cache(vary_user=True)
parser = SearchQueryParser(request.args, request.authz)
result = EntitiesQuery.handle(request, parser=parser)
return EntitySerializer.jsonify_result(result)
