def dispatchvectorsearch(vectortype: str,
searchid: str,
one=None,
two=None,
three=None) -> JSON_STR:
"""
dispatcher for "/vectors/..." requests
"""
if not hipparchia.config['SEMANTICVECTORSENABLED']:
so = SearchObject(str(), str(), str(), str(), str(), session)
oo = SearchOutputObject(so)
target = 'searchsummary'
message = '[semantic vectors have not been enabled]'
return oo.generatenulloutput(itemname=target, itemval=message)
pollid = validatepollid(searchid)
one = depunct(one)
two = depunct(two)
three = depunct(three)
simple = [pollid, one]
triple = [pollid, one, two, three]
knownfunctions = {
'nearestneighborsquery': {
'bso': simple,
'pref': 'CONCEPTMAPPINGENABLED'
},
'analogies': {
'bso': triple,
'pref': 'VECTORANALOGIESENABLED'
},
'topicmodel': {
'bso': simple,
'pref': 'TOPICMODELINGENABLED'
},
'vectortestfunction': {
'bso': simple,
'pref': 'TESTINGVECTORBUTTONENABLED'
},
'unused': {
'fnc': lambda: str(),
'bso': None,
'pref': None
},
}
if not knownfunctions[vectortype]['pref'] or not hipparchia.config[
knownfunctions[vectortype]['pref']]:
return json.dumps('this type of search has not been enabled')
bso = knownfunctions[vectortype]['bso']
so = None
if len(bso) == 4:
so = buildtriplelemmasearchobject(*bso)
if len(bso) == 2:
so = buildsinglelemmasearchobject(*bso)
so.vectorquerytype = vectortype
progresspolldict[pollid] = ProgressPoll(pollid)
so.poll = progresspolldict[pollid]
so.poll.activate()
so.poll.statusis('Preparing to vectorize')
if hipparchia.config['EXTERNALVECTORHELPER']:
j = externalvectors(so)
else:
j = pythonvectors(so)
if hipparchia.config['JSONDEBUGMODE']:
print('/vectors/{f}\n\t{j}'.format(f=vectortype, j=j))
try:
del so.poll
except AttributeError:
pass
return j
def buildfakesearchobject(qtype='nearestneighborsquery') -> SearchObject:
"""
do what it takes to build a hollow searchobject
:return:
"""
frozensession = dict()
frozensession['vdim'] = hipparchia.config['VECTORDIMENSIONS']
frozensession['vwindow'] = hipparchia.config['VECTORWINDOW']
frozensession['viterat'] = hipparchia.config['VECTORTRAININGITERATIONS']
frozensession['vminpres'] = hipparchia.config['VECTORMINIMALPRESENCE']
frozensession['vdsamp'] = hipparchia.config['VECTORDOWNSAMPLE']
frozensession['vcutloc'] = hipparchia.config['VECTORDISTANCECUTOFFLOCAL']
frozensession['vcutneighb'] = hipparchia.config[
'VECTORDISTANCECUTOFFNEARESTNEIGHBOR']
frozensession['vcutlem'] = hipparchia.config[
'VECTORDISTANCECUTOFFLEMMAPAIR']
frozensession['vnncap'] = hipparchia.config['NEARESTNEIGHBORSCAP']
frozensession['vsentperdoc'] = hipparchia.config['SENTENCESPERDOCUMENT']
frozensession['ldamaxfeatures'] = hipparchia.config['LDAMAXFEATURES']
frozensession['ldacomponents'] = hipparchia.config['LDACOMPONENTS']
frozensession['ldamaxfreq'] = hipparchia.config['LDAMAXFREQ']
frozensession['ldaminfreq'] = hipparchia.config['LDAMINFREQ']
frozensession['ldaiterations'] = hipparchia.config['LDAITERATIONS']
frozensession['ldamustbelongerthan'] = hipparchia.config[
'LDAMUSTBELONGERTHAN']
frozensession['baggingmethod'] = hipparchia.config['DEFAULTBAGGINGMETHOD']
blanks = ['searchscope', 'nearornot', 'onehit']
for b in blanks:
frozensession[b] = None
nulls = ['psgselections', 'psgexclusions']
for n in nulls:
frozensession[n] = list()
zeroes = ['proximity', 'maxresults', 'linesofcontext']
for z in zeroes:
frozensession[z] = 0
trueorfalse = [
'onehit', 'icandodates', 'nearestneighborsquery', 'searchinsidemarkup'
]
for x in trueorfalse:
frozensession[x] = False
for x in [
'agnexclusions', 'agnselections', 'alocexclusions',
'alocselections', 'analogyfinder', 'auexclusions', 'auselections'
]:
frozensession[x] = list()
for s in [
'wkexclusions', 'wkgnexclusions', 'wkgnselections', 'wkselections',
'wlocexclusions', 'wlocselections'
]:
frozensession[s] = list()
for p in ['psgexclusions', 'psgselections']:
frozensession[p] = list()
for c in [
'christiancorpus', 'latincorpus', 'greekcorpus',
'inscriptioncorpus'
]:
frozensession[c] = True
frozensession['latestdate'] = 1500
frozensession['earliestdate'] = -850
so = SearchObject('vectorbot', str(), str(), None, None, frozensession)
# parsevectorsentences() needs the following:
so.vectorquerytype = qtype
so.usecolumn = 'marked_up_line'
so.sortorder = 'shortname'
so.iamarobot = True
return so