def match_dataset(kwd, cur_inst):
""" check for dataset match in current DBS instances """
if len(kwd) < 3:
return None
score, data = match_value_dataset(kwd, cur_inst)
if score:
return data.get('adjusted_keyword', kwd)
def match_dataset(kwd, cur_inst):
""" check for dataset match in current DBS instances """
if len(kwd) < 3:
return None
score, data = match_value_dataset(kwd, cur_inst)
if score:
return data.get('adjusted_keyword', kwd)
def match_dataset_all_inst(kwd, cur_inst):
""" list matching dataset patterns in all DBS instances """
if len(kwd) < 3:
return []
matches = []
for inst in list_dbs_instances():
score, data = match_value_dataset(kwd, inst)
if not score:
continue
data['inst'] = inst
data['match'] = data.get('adjusted_keyword', kwd)
# score matches in other DBS instances lower
score = score - 0.15 if inst != cur_inst else score
data['score'] = score
matches.append(data)
return sorted(matches, key=lambda item: item['score'], reverse=True)
def match_dataset_all_inst(kwd, cur_inst):
""" list matching dataset patterns in all DBS instances """
if len(kwd) < 3:
return []
matches = []
for inst in list_dbs_instances():
score, data = match_value_dataset(kwd, inst)
if not score:
continue
data['inst'] = inst
data['match'] = data.get('adjusted_keyword', kwd)
# score matches in other DBS instances lower
score = score - 0.15 if inst != cur_inst else score
data['score'] = score
matches.append(data)
return sorted(matches, key=lambda item: item['score'], reverse=True)
def keyword_value_weights(keyword):
"""
for each attribute, calculates likelihood that given keyword is a value of
the attribute (we are mostly interested in API parameters, but
"""
# to minimize false positives, we exclude the fields from regexp matching
# for which we have a list of possible values (the quite static ones)
fields_tracked = input_values_tracker.get_fields_tracked(only_stable=True)
scores_dict = _select_best_scores(
(score, field) for score, field in keyword_regexp_weights(keyword)
if field not in fields_tracked)
# check for matching of existing datasets, and override regexp based score
dataset_score, data = match_value_dataset(keyword)
if dataset_score:
scores_dict['dataset.name'] = (dataset_score, data)
# check for matching fields those values are fairly static (site, release..)
scores_dict.update(input_values_tracker.input_value_matches(keyword))
return sorted(scores_dict.itervalues(),
key=lambda item: item[0], reverse=True)
def keyword_value_weights(keyword):
"""
for each attribute, calculates likelihood that given keyword is a value of
the attribute (we are mostly interested in API parameters, but
"""
# to minimize false positives, we exclude the fields from regexp matching
# for which we have a list of possible values (the quite static ones)
fields_tracked = input_values_tracker.get_fields_tracked(only_stable=True)
scores_dict = _select_best_scores(
(score, field) for score, field in keyword_regexp_weights(keyword)
if field not in fields_tracked)
# check for matching of existing datasets, and override regexp based score
dataset_score, data = match_value_dataset(keyword)
if dataset_score:
scores_dict['dataset.name'] = (dataset_score, data)
# check for matching fields those values are fairly static (site, release..)
scores_dict.update(input_values_tracker.input_value_matches(keyword))
return sorted(scores_dict.itervalues(),
key=lambda item: item[0], reverse=True)
