def _make_anygroup_hashes(annots, nids):
""" helper function
import wbia
qreq_ = wbia.testdata_qreq_(
defaultdb='PZ_MTEST',
qaid_override=[1, 2, 3, 4, 5, 6, 10, 11],
daid_override=[2, 3, 5, 6, 20, 21, 22, 23, 24],
)
import wbia
qreq_ = wbia.testdata_qreq_(defaultdb='PZ_Master1')
%timeit qreq_._make_namegroup_data_hashes()
%timeit qreq_._make_namegroup_data_uuids()
"""
# make sure items are sorted to ensure same assignment
# gives same uuids
# annots = qreq_.ibs.annots(sorted(qreq_.daids))
unique_nids, groupxs = vt.group_indices(nids)
grouped_visual_uuids = ut.apply_grouping(annots.visual_uuids, groupxs)
group_hashes = [
ut.combine_hashes(sorted(u.bytes for u in uuids), hasher=hashlib.sha1())
for uuids in grouped_visual_uuids
]
nid_to_grouphash = dict(zip(unique_nids, group_hashes))
return nid_to_grouphash
def get_qreq_pcc_hashes(qreq_, aids):
"""
aids = [1, 2, 3]
"""
nids = qreq_.get_qreq_annot_nids(aids)
b = ut.util_hash.b
zero = b('\x00' * 16)
# Should we just be combining with a hash that represents the entire
# database PCC state? Maybe.
# For now, only considers grouping of database names
dannot_name_hashes = ut.dict_take(qreq_.dnid_to_grouphash, nids, zero)
dannot_visual_uuids = qreq_.get_qreq_annot_visual_uuids(aids)
dannot_visual_hashes = (u.bytes for u in dannot_visual_uuids)
for vuuid, nuuid in zip(dannot_visual_hashes, dannot_name_hashes):
bytes_ = ut.combine_hashes((vuuid, nuuid), hasher=hashlib.sha1())
yield bytes_
def get_qreq_pcc_hashid(qreq_, aids, prefix='', with_nids=False):
"""
Gets a combined hash of a group of aids. Each aid hash represents
itself in the context of the query database.
only considers grouping of database names
CommandLine:
python -m wbia.algo.hots.query_request --test-get_qreq_pcc_hashid:0
Example:
>>> # ENABLE_DOCTEST
>>> from wbia.algo.hots.query_request import * # NOQA
>>> import wbia
>>> p = ['default:K=2,nameknn=True']
>>> defaultdb = 'testdb1'
>>> # Test that UUIDS change when you change the name lookup
>>> new_ = ut.partial(wbia.testdata_qreq_, defaultdb=defaultdb, p=p,
>>> verbose=False)
>>> # All diff names
>>> qreq1 = new_(daid_override=[2, 3, 5, 6],
>>> qaid_override=[1, 2, 4],
>>> custom_nid_lookup={a: a for a in range(14)})
>>> # All same names
>>> qreq2 = new_(daid_override=[2, 3, 5, 6],
>>> qaid_override=[1, 2, 4],
>>> custom_nid_lookup={a: 1 for a in range(14)})
>>> # Change the PCC, removing a query (data should NOT change)
>>> # because the thing being queried against is the same
>>> qreq3 = new_(daid_override=[2, 3, 5, 6],
>>> qaid_override=[1, 2],
>>> custom_nid_lookup={a: 1 for a in range(14)})
>>> # Now remove a database object (query SHOULD change)
>>> # because the results are different depending on
>>> # nameing of database (maybe they shouldnt change...)
>>> qreq4 = new_(daid_override=[2, 3, 6],
>>> qaid_override=[1, 2, 4],
>>> custom_nid_lookup={a: 1 for a in range(14)})
>>> print(qreq1.get_cfgstr(with_input=True, with_pipe=False))
>>> print(qreq2.get_cfgstr(with_input=True, with_pipe=False))
>>> print(qreq3.get_cfgstr(with_input=True, with_pipe=False))
>>> print(qreq4.get_cfgstr(with_input=True, with_pipe=False))
>>> assert qreq3.get_data_hashid() == qreq2.get_data_hashid()
>>> assert qreq1.get_data_hashid() != qreq2.get_data_hashid()
"""
# TODO: pcc based hashing should only be used if name dependant
# attributes are used in the pipeline.
label = ''.join(('_', prefix, 'PCC_UUIDS'))
pcc_hashes = qreq_.get_qreq_pcc_hashes(sorted(aids))
pcc_hash = ut.combine_hashes(pcc_hashes, hasher=hashlib.sha1())
pcc_hashstr = ut.convert_bytes_to_bigbase(pcc_hash)
pcc_hashstr = pcc_hashstr[0:16]
sep = '-'
n_aids = 'a' + str(len(aids))
if with_nids:
unique_nids = set(qreq_.get_qreq_annot_nids(aids))
n_nids = 'n' + str(len(unique_nids))
pcc_hashid = sep.join([label, n_aids, n_nids, pcc_hashstr])
else:
pcc_hashid = sep.join([label, n_aids, pcc_hashstr])
return pcc_hashid