def updatesearchlistandsearchobject(so: SearchObject) -> SearchObject:
"""
you have a searchlist; now tell the searchobject more about it...
this has been peeled off so that golangvectors() can call it too
"""
# mark works that have passage exclusions associated with them:
# gr0001x001 instead of gr0001w001 if you are skipping part of w001
so.searchlist = flagexclusions(so.searchlist, so.session)
so.poll.statusis('Calculating full authors to search')
so.searchlist = calculatewholeauthorsearches(so.searchlist, authordict)
so.usedcorpora = so.wholecorporasearched()
so.poll.statusis('Configuring the search restrictions')
so.indexrestrictions = configurewhereclausedata(so.searchlist, workdict,
so)
return so
def checkneedtoabort(so: SearchObject) -> str:
"""
can/should we even do this?
"""
if so.iamarobot:
return str()
abortjson = str()
abort = lambda x: emptyvectoroutput(so, x)
activecorpora = so.getactivecorpora()
so.poll.statusis('Compiling the list of works to search')
so.searchlist = compilesearchlist(listmapper, so.session)
# so.seeking should only be set via a fallback when session['baggingmethod'] == 'unlemmatized'
if (so.lemmaone or so.tovectorize or so.seeking) and activecorpora:
pass
elif not activecorpora:
abortjson = abort(['no active corpora'])
elif not so.searchlist:
abortjson = abort(['empty list of places to look'])
elif so.vectorquerytype == 'topicmodel':
# we don't have and don't need a lemmaone, etc.
pass
elif so.vectorquerytype == 'analogies':
if not so.lemmaone or not so.lemmatwo or not so.lemmathree:
abortjson = abort('[did not have three lemmata]')
else:
# note that some vector queries do not need a term; fix this later...
abortjson = abort(['there was no search term'])
maxwords = hipparchia.config['MAXVECTORSPACE']
wordstotal = 0
for work in so.searchlist:
work = work[:10]
try:
wordstotal += workdict[work].wordcount
except TypeError:
# TypeError: unsupported operand type(s) for +=: 'int' and 'NoneType'
pass
if wordstotal > maxwords:
m = 'the vector scope max exceeded: {a} > {b} '
abortjson = abort([
m.format(a=locale.format_string('%d', wordstotal, grouping=True),
b=locale.format_string('%d', maxwords, grouping=True))
])
return abortjson
def perparesoforsecondsqldict(so: SearchObject, initialhitlines: List[dbWorkLine], usebetweensyntax=True) -> SearchObject:
"""
after finding initialhitlines sqlwithinxlinessearch() will run a second query
it needs a new sqldict
note that "usebetweensyntax=False" will break precomposedphraseandproximitysearch()
"""
so.indexrestrictions = dict()
authorsandlines = dict()
if not usebetweensyntax:
# consolewarning('sqlwithinxlinessearch(): temptable')
# time trials...
# Sought all 13 known forms of »ὕβριϲ« within 4 lines of all 230 known forms of »φεύγω«
# Searched 7,873 texts and found 9 passages (11.87s)
# Searched between 400 B.C.E. and 350 B.C.E.
# Sought all 230 known forms of »φεύγω« within 4 lines of all 16 known forms of »κρίϲιϲ«
# Searched 7,873 texts and found 12 passages (14.64s)
# Searched between 400 B.C.E. and 350 B.C.E.
for hl in initialhitlines:
linestosearch = list(range(hl.index - so.distance, hl.index + so.distance + 1))
try:
authorsandlines[hl.authorid].extend(linestosearch)
except KeyError:
authorsandlines[hl.authorid] = linestosearch
so.searchlist = list(authorsandlines.keys())
for a in authorsandlines:
so.indexrestrictions[a] = dict()
so.indexrestrictions[a]['type'] = 'temptable'
so.indexrestrictions[a]['where'] = wholeworktemptablecontents(a, set(authorsandlines[a]))
# print("so.indexrestrictions[a]['where']", so.indexrestrictions[a]['where'])
else:
# Sought all 13 known forms of »ὕβριϲ« within 4 lines of all 230 known forms of »φεύγω«
# Searched 7,873 texts and found 9 passages (9.35s)
# Searched between 400 B.C.E. and 350 B.C.E.
# Sought all 230 known forms of »φεύγω« within 4 lines of all 16 known forms of »κρίϲιϲ«
# Searched 7,873 texts and found 12 passages (11.35s)
# Searched between 400 B.C.E. and 350 B.C.E.
# consolewarning('sqlwithinxlinessearch(): between')
for hl in initialhitlines:
boundiaries = (hl.index - so.distance, hl.index + so.distance)
try:
authorsandlines[hl.authorid].append(boundiaries)
except KeyError:
authorsandlines[hl.authorid] = [boundiaries]
for a in authorsandlines:
so.searchlist = list(authorsandlines.keys())
so.indexrestrictions[a] = dict()
so.indexrestrictions[a]['where'] = dict()
so.indexrestrictions[a]['type'] = 'between'
so.indexrestrictions[a]['where']['listofboundaries'] = authorsandlines[a]
so.indexrestrictions[a]['where']['listofomissions'] = list()
return so