def search_by_authors(self,
authors,
match_all=True,
limit=None,
only_latest=True):
"""Execute a search for servables from certain authors.
Authors in DLHub may be different than the owners of the servable and generally are
the people who developed functionality of a certain servable (e.g., the creators
of the machine learning model used in a servable).
If you want to search by ownership, see :meth:`search_by_servable`
Args:
authors (str or list of str): The authors to match. Names must be in
"Family Name, Given Name" format
match_all (bool): If ``True``, will require all authors be on any results.
If ``False``, will only require one author to be in results.
**Default**: ``True``.
limit (int): The maximum number of results to return.
**Default:** ``None``, for no limit.
only_latest (bool): When ``True``, will only return the latest version
of each servable. When ``False``, will return all matching versions.
**Default**: ``True``.
Returns:
[dict]: List of servables from the desired authors
"""
results = self.query.match_authors(
authors, match_all=match_all).search(limit=limit)
return filter_latest(results) if only_latest else results
def search_by_related_doi(self, doi, limit=None, only_latest=True):
"""Get all of the servables associated with a certain publication
Args:
doi (string): DOI of related paper
limit (int): Maximum number of results to return
only_latest (bool): Whether to return only the most recent version of the model
Returns:
[dict]: List of servables from the requested paper
"""
results = self.query.match_doi(doi).search(limit=limit)
return filter_latest(results) if only_latest else results
def search_cmd(owner, name, all_versions, author, domain, doi, query):
"""Search command
See above for argument details
"""
# Get the client
client = get_dlhub_client()
# Start the query object
query = DLHubSearchHelper(client._search_client, q="(" + " ".join(query), advanced=True)
# Add the filters
query.match_owner(owner)
query.match_servable(servable_name=name)
query.match_authors(author)
query.match_domains(domain)
query.match_doi(doi)
# If no query strings are given, return an error
if not query.initialized:
click.echo('Error: No query specified. For options, call: dlhub search --help')
click.get_current_context().exit(1)
# Perform the query
results = query.search()
# If no results, return nothing
if len(results) == 0:
click.echo('No results')
return
# If desired, filter the entries
if not all_versions:
results = filter_latest(results)
# Get only a subset of the data and print it as a table
results_df = pd.DataFrame([{
'Owner': r['dlhub']['owner'],
'Model Name': r['dlhub']['name'],
'Publication Date': datetime.fromtimestamp(int(r['dlhub']['publication_date']) /
1000).strftime('%Y-%m-%d %H:%M'),
'Type': r['servable']['type']
} for r in results])
results_df.sort_values(['Owner', 'Model Name', 'Publication Date'],
ascending=[True, True, False], inplace=True)
click.echo(tabulate(results_df.values, headers=results_df.columns))
def search_by_servable(self,
servable_name=None,
owner=None,
version=None,
only_latest=True,
limit=None,
get_info=False):
"""Search by the ownership, name, or version of a servable
Args:
servable_name (str): The name of the servable. **Default**: None, to match
all servable names.
owner (str): The name of the owner of the servable. **Default**: ``None``,
to match all owners.
version (int): Model version, which corresponds to the date when the
servable was published. **Default**: ``None``, to match all versions.
only_latest (bool): When ``True``, will only return the latest version
of each servable. When ``False``, will return all matching versions.
**Default**: ``True``.
limit (int): The maximum number of results to return.
**Default:** ``None``, for no limit.
get_info (bool): If ``False``, search will return a list of the results.
If ``True``, search will return a tuple containing the results list
and other information about the query.
**Default:** ``False``.
Returns:
If ``info`` is ``False``, *list*: The search results.
If ``info`` is ``True``, *tuple*: The search results,
and a dictionary of query information.
"""
if not servable_name and not owner and not version:
raise ValueError(
"One of 'servable_name', 'owner', or 'publication_date' is required."
)
# Perform the query
results, info = (self.query.match_servable(
servable_name=servable_name, owner=owner,
publication_date=version).search(limit=limit, info=True))
# Filter out the latest models
if only_latest:
results = filter_latest(results)
if get_info:
return results, info
return results
def search(self, query, advanced=False, limit=None, only_latest=True):
"""Query the DLHub servable library
By default, the query is used as a simple plaintext search of all model metadata.
Optionally, you can provided an advanced query on any of the indexed fields in
the DLHub model metadata by setting :code:`advanced=True` and following the guide for
constructing advanced queries found in the
`Globus Search documentation <https://docs.globus.org/api/search/search/#query_syntax>`_.
Args:
query (string): Query to be performed
advanced (bool): Whether to perform an advanced query
limit (int): Maximum number of entries to return
only_latest (bool): Whether to return only the latest version of the model
Returns:
([dict]): All records matching the search query
"""
results = self.query.search(query, advanced=advanced, limit=limit)
return filter_latest(results) if only_latest else results
