def read_nttat(cli, args):
''' Convert NTTAT patch to JSON '''
stdout = TextReport()
ext = 'json'
rp = TextReport("{}_1.{}".format(args.output, ext))
rp2 = TextReport("{}_2.{}".format(args.output, ext))
gwn = get_gwn()
data = []
with open(args.input, 'r') as infile, gwn.ctx() as ctx:
ssids = re.findall('\d{8}-[nvarx]', infile.read())
print(len(ssids))
print(ssids)
for sid in ssids:
ss = gwn.get_synset(sid, ctx=ctx)
sdef = fix_gwn_def(ss.definition)
stdout.header(sid, "Lemmas: {}".format(", ".join(ss.lemmas)))
stdout.print(sdef)
data.append({
"synset": sid,
"lemmas": ss.lemmas,
"definition": sdef
})
cut = int(len(data) / 2)
# first half
first_half = json.dumps(data[:cut], indent=2)
rp.write(first_half)
# second half
second_half = json.dumps(data[cut:], indent=2)
rp2.write(second_half)
def test_get_gloss_synsets(self):
print("Test get glossed synset(s)")
db = get_gwn()
glosses = db.schema.gloss.select()
# select glosses
print("Gloss count: {}".format(len(glosses)))
print(glosses[:5])
pass
def test_dump_synset(self):
print("Test get synset by ID")
gwn = get_gwn()
ss = get_synset_by_id(gwn, '01775535-v')
self.assertIsNotNone(ss)
self.assertGreater(len(ss.lemmas), 0)
self.assertGreater(len(ss.keys), 0)
self.assertGreater(len(ss.glosses), 0)
dump_synset(ss)
pass
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!")
from puchikarui import Schema, with_ctx
from coolisf import GrammarHub
from chirptext.leutile import grouper
from chirptext.io import CSV
from chirptext import TextReport, FileHelper, Counter, FileHub
from chirptext.cli import CLIApp, setup_logging
from yawlib.helpers import get_gwn
from yawlib.helpers import get_wn, get_omw
# -------------------------------------------------------------------------------
# Configuration
# -------------------------------------------------------------------------------
DATA_FOLDER = os.path.abspath(os.path.expanduser('./data'))
omw = get_omw()
gwn = get_gwn()
wn = get_wn()
setup_logging('logging.json', 'logs')
ghub = GrammarHub()
MY_DIR = os.path.dirname(__file__)
SETUP_FILE = os.path.join(MY_DIR, 'scripts', 'ewdb.sql')
ROOTS = {'n': 'root_wn_n', 'v': 'root_wn_v', 'a': 'root_wn_adj', 'r': ''}
DEFAULT_DB_PATH = FileHelper.abspath('data/ewmap.db')
class EWDB(Schema):
class Flags:
PROCESSED = 1
NO_PARSE = 2
MWE = 3
MWE_PURE = 100
def test_get_by_sk(self):
ss = get_synset_by_sk(get_gwn(),
'test%2:41:00::',
report_file=self.nullrep)
self.assertIsNotNone(ss)