def export_wnsql_synsets(args):
print(
"Exporting synsets' info (lemmas/defs/examples) from WordnetSQL (Princeton Wordnet 3.0) to text file"
)
show_info(args)
output_with_sid_file = os.path.abspath('./data/wn30_lemmas.txt')
output_without_sid_file = os.path.abspath('./data/wn30_lemmas_noss.txt')
output_defs = os.path.abspath('./data/wn30_defs.txt')
output_exes = os.path.abspath('./data/wn30_exes.txt')
wn = get_wn(args)
# Extract lemmas
records = wn.get_all_synsets()
synsets_lemmas = []
for r in records:
synsets_lemmas.append(
(SynsetID.from_string(str(r.synsetid)).to_canonical(), r.lemma))
synsets_lemmas.sort(key=itemgetter(0, 1))
with open(output_with_sid_file,
'w') as with_sid, open(output_without_sid_file,
'w') as without_sid:
for row in synsets_lemmas:
with_sid.write('%s\t%s\n' % row)
without_sid.write('%s\n' % (row[1], )) # just the lemma
# Extract synset definitions
records = wn.schema.ss.select(orderby='synsetid')
synsets_defs = []
for r in records:
synsets_defs.append(
(SynsetID.from_string(r.synsetid).to_canonical(), r.definition))
synsets_defs.sort(key=itemgetter(0))
with open(output_defs, 'w') as def_file:
for row in synsets_defs:
def_file.write('%s\t%s\n' % row)
# Extract examples
records = wn.schema.ex.select(orderby='synsetid')
synsets_examples = []
for r in records:
synsets_examples.append(
(SynsetID.from_string(r.synsetid).to_canonical(), r.sample))
synsets_examples.sort(key=itemgetter(0))
with open(output_exes, 'w') as ex_file:
for row in synsets_examples:
ex_file.write('%s\t%s\n' % row)
# summary
print("Data has been extracted to:")
print(" + {}".format(output_with_sid_file))
print(" + {}".format(output_without_sid_file))
print(" + {}".format(output_defs))
print(" + {}".format(output_exes))
print("Done!")
def export_gwnsql_synsets(args):
print(
"Exporting synsets' info (lemmas/defs/examples) from GlossWordNet (SQLite) to text file"
)
show_info(args)
output_with_sid_file = os.path.abspath('./data/glosstag_lemmas.txt')
output_without_sid_file = os.path.abspath(
'./data/glosstag_lemmas_noss.txt')
output_defs = os.path.abspath('./data/glosstag_defs.txt')
output_exes = os.path.abspath('./data/glosstag_exes.txt')
gwn = get_gwn(args)
# Extract synsets' lemmas, definitions and examples
if args.mockup:
synsets = get_gwnxml(args).synsets
else:
synsets = gwn.all_synsets()
synsets.synsets.sort(key=lambda x: x.sid.to_canonical())
with open(output_defs,
'w') as def_file, open(output_exes, 'w') as ex_file, open(
output_with_sid_file,
'w') as with_sid, open(output_without_sid_file,
'w') as without_sid:
# synsets = gwn.get_synsets_by_ids(['01828736-v', '00001740-r'])
for ss in synsets:
for t in sorted(ss.terms, key=lambda x: x.term):
with_sid.write('%s\t%s\n' % (ss.sid.to_canonical(), t.term))
without_sid.write('%s\n' % (t.term, ))
for gloss in ss.glosses:
if gloss.cat == 'def':
def_file.write('{sid}\t{d}\n'.format(sid=ss.sid,
d=gloss.text()))
elif gloss.cat == 'ex':
ex_file.write('{sid}\t{ex}\n'.format(sid=ss.sid,
ex=gloss.text()))
# summary
print("Data has been extracted to:")
print(" + {}".format(output_with_sid_file))
print(" + {}".format(output_without_sid_file))
print(" + {}".format(output_defs))
print(" + {}".format(output_exes))
print("Extracted synsets: {}".format(len(synsets)))
print("Done!")
def glosstag2ntumc(args):
print("Extracting Glosstag to NTU-MC")
show_info(args)
print("To be developed")
pass