def lsiformatoutput(findshtml: str, workssearched: int, matches: list,
searchobject: SearchObject) -> str:
"""
should use OutputObject() instead
:param findshtml:
:param workssearched:
:param searchobject:
:param activepoll:
:param starttime:
:return:
"""
so = searchobject
activepoll = so.poll
output = SearchOutputObject(so)
output.found = findshtml
output.js = insertbrowserclickjs('browser')
output.setscope(workssearched)
output.title = 'Sentences that are reminiscent of »{skg}«'.format(
skg=so.seeking)
output.thesearch = output.title
output.htmlsearch = 'sentences that are reminiscent of <span class="sought">»{skg}«</span>'.format(
skg=so.seeking)
output.resultcount = '{n} sentences above the cutoff'.format(
n=len(matches))
output.searchtime = so.getelapsedtime()
activepoll.deactivate()
jsonoutput = json.dumps(output.generateoutput())
return jsonoutput
def ldatopicsgenerateoutput(ldavishtmlandjs: str, searchobject: SearchObject):
"""
pyLDAvis.prepared_data_to_html() outputs something that is almost pure JS and looks like this:
<link rel="stylesheet" type="text/css" href="https://cdn.rawgit.com/bmabey/pyLDAvis/files/ldavis.v1.0.0.css">
<div id="ldavis_el7428760626948328485476648"></div>
<script type="text/javascript">
var ldavis_el7428760626948328485476648_data = {"mdsDat": ...
}
</script>
instance = {
'maxfeatures': 2000,
'components': 15, # topics
'maxfreq': .75, # fewer than n% of sentences should have this word (i.e., purge common words)
'minfreq': 5, # word must be found >n times
'iterations': 12,
'mustbelongerthan': 3
}
:param ldavishtmlandjs:
:param workssearched:
:param settings:
:param searchobject:
:return:
"""
so = searchobject
activepoll = so.poll
output = SearchOutputObject(so)
workssearched = len(so.searchlist)
vv = searchobject.vectorvalues
settings = {
'maxfeatures': vv.ldamaxfeatures,
'components': vv.ldacomponents, # topics
'maxfreq': vv.
ldamaxfreq, # fewer than n% of sentences should have this word (i.e., purge common words)
'minfreq': vv.ldaminfreq, # word must be found >n times
'iterations': vv.ldaiterations,
'mustbelongerthan': vv.ldamustbelongerthan
}
lines = ldavishtmlandjs.split('\n')
lines = [re.sub(r'\t', str(), l) for l in lines if l]
lines.reverse()
thisline = str()
html = list()
while not re.search(r'<script type="text/javascript">', thisline):
html.append(thisline)
try:
thisline = lines.pop()
except IndexError:
# oops, we never found the script...
thisline = '<script type="text/javascript">'
# we cut '<script>'; now drop '</script>'
lines.reverse()
js = lines[:-1]
findshtml = '\n'.join(html)
findsjs = '\n'.join(js)
ldacssurl = r'https://cdn.rawgit.com/bmabey/pyLDAvis/files/ldavis.v1.0.0.css'
ldacsslocal = '/css/ldavis.css'
findshtml = re.sub(ldacssurl, ldacsslocal, findshtml)
# brittle: ldavis might change its URLs between versions, etc.
# should probably make this conditional upon the presence of the file locally...
ldajsurl = r'https://cdn.rawgit.com/bmabey/pyLDAvis/files/ldavis.v1.0.0.js'
ldajslocal = '/static/jsforldavis.js'
findsjs = re.sub(ldajsurl, ldajslocal, findsjs)
# this next will break the reloaded figure: hm...
# d3jsurl = r'https://cdnjs.cloudflare.com/ajax/libs/d3/3.5.5/d3.min'
# d3jslocal = '/static/jsd3'
# findsjs = re.sub(d3jsurl, d3jslocal, findsjs)
#
# print('findsjs',findsjs)
who = str()
where = '{n} authors'.format(n=searchobject.numberofauthorssearched())
if searchobject.numberofauthorssearched() == 1:
a = authordict[searchobject.searchlist[0][:6]]
who = a.akaname
where = who
if workssearched == 1:
try:
w = workdict[searchobject.searchlist[0]]
w = w.title
except KeyError:
w = str()
where = '{a}, <worktitle>{w}</worktitle>'.format(a=who, w=w)
output.title = 'Latent Dirichlet Allocation'
output.found = findshtml
output.js = findsjs
output.setscope(workssearched)
output.sortby = 'weight'
output.thesearch = 'thesearch'.format(skg='')
output.resultcount = 'the following topics'
output.htmlsearch = '{n} topics in {w}'.format(n=settings['components'],
w=where)
output.searchtime = so.getelapsedtime()
activepoll.deactivate()
jsonoutput = json.dumps(output.generateoutput())
return jsonoutput