def get_ccg_lexicon():
lexicon = Lexicon()
filename = os.path.join(LEXICON_DIR, 'geo-lexicon.txt')
entries = []
with open(filename) as f:
for line in f:
x, y = line.strip().split(' :- NP : ')
entries.append((x, y))
lexicon.add_entries(entries, False)
return lexicon
def get_ccg_lexicon():
lexicon = Lexicon()
filename = os.path.join(DB_DIR, 'lexicon.txt')
entries = []
with open(filename) as f:
for line in f:
x, y = line.strip().split(' :- NP : ')
y = y.replace(':', ':_')
entries.append((x, y))
lexicon.add_entries(entries)
return lexicon
def get_ccg_lexicon():
lexicon = Lexicon()
filename = os.path.join(DB_DIR, 'lexicon.txt')
entries = []
with open(filename) as f:
for line in f:
x, y = line.strip().split(' :- NP : ')
y = y.replace(':', ':_')
entries.append((x, y))
lexicon.add_entries(entries)
return lexicon
def get_lexicon_from_raw_lexicon_then_write(basename, newname):
filename = os.path.join(LEXICON_DIR, basename)
newfilename = os.path.join(LEXICON_DIR, newname)
lex = Lexicon()
entries = []
with open(filename) as f:
for line in f:
lexicon_tuple = parse_entry(line)
name = lexicon_tuple[0]
entity = normalize_entity(lexicon_tuple[1])
if entity == '':
continue
entries.append((name, entity))
lex.add_entries(entries, False)
with open(newfilename, 'w') as f:
for name, entity in lex.entries.items():
#print('%s :- NP : %s' % (name, entity), file=f)
pass
return lex
def get_manual_lexicon():
DAYS_OF_WEEK = [(s, '%s:_da' % s)
for s in ('monday', 'tuesday', 'wednesday', 'thursday',
'friday', 'saturday', 'sunday')]
# For dates
WORD_NUMBERS = [('one', '1:_dn'), ('two', '2:_dn'), ('three', '3:_dn'),
('four', '4:_dn'), ('five', '5:_dn'), ('six', '6:_dn'),
('seven', '7:_dn'), ('eight', '8:_dn'), ('nine', '9:_dn'),
('ten', '10:_dn'), ('eleven', '11:_dn'),
('twelve', '12:_dn'), ('thirteen', '13:_dn'),
('fourteen', '14:_dn'), ('fifteen', '15:_dn'),
('sixteen', '16:_dn'), ('seventeen', '17:_dn'),
('eighteen', '18:_dn'), ('nineteen', '19:_dn'),
('twenty', '20:_dn'), ('twenty one', '21:_dn'),
('twenty two', '22:_dn'), ('twenty three', '23:_dn'),
('twenty four', '24:_dn'), ('twenty five', '25:_dn'),
('twenty six', '26:_dn'), ('twenty seven', '27:_dn'),
('twenty eight', '28:_dn'), ('twenty nine', '29:_dn'),
('thirty', '30:_dn'), ('thirty one', '31:_dn')]
ORDINAL_NUMBERS = [
('second', '2:_dn'), ('third', '3:_dn'), ('fourth', '4:_dn'),
('fifth', '5:_dn'), ('sixth', '6:_dn'), ('seventh', '7:_dn'),
('eighth', '8:_dn'), ('ninth', '9:_dn'), ('tenth', '10:_dn'),
('eleventh', '11:_dn'), ('twelfth', '12:_dn'),
('thirteenth', '13:_dn'), ('fourteenth', '14:_dn'),
('fifteenth', '15:_dn'), ('sixteenth', '16:_dn'),
('seventeenth', '17:_dn'), ('eighteenth', '18:_dn'),
('nineteenth', '19:_dn'), ('twentieth', '20:_dn'),
('twenty first', '21:_dn'), ('twenty second', '22:_dn'),
('twenty third', '23:_dn'), ('twenty fourth', '24:_dn'),
('twenty fifth', '25:_dn'), ('twenty sixth', '26:_dn'),
('twenty seventh', '27:_dn'), ('twenty eighth', '28:_dn'),
('twenty ninth', '29:_dn'), ('thirtieth', '30:_dn'),
('thirty first', '31:_dn')
] # Prefer first class to "first = 1"
MEALS = [(m, '%s:_me' % m)
for m in ('breakfast', 'lunch', 'dinner', 'snack')]
lex = Lexicon()
lex.add_entries(read_db('CITY.TAB', 1, 1, '_ci', strip_id=['.']))
lex.add_entries(DAYS_OF_WEEK)
lex.add_entries([(x + 's', y)
for x, y in DAYS_OF_WEEK]) # Handle "on tuesdays"
lex.add_entries(
read_db('AIRLINE.TAB', 0, 1, '_al', strip_name=[', inc.', ', ltd.']))
handle_times(lex)
lex.add_entries(read_db('INTERVAL.TAB', 0, 0, '_pd'))
lex.add_entries(WORD_NUMBERS)
lex.add_entries(ORDINAL_NUMBERS)
lex.add_entries(read_db('MONTH.TAB', 1, 1, '_mn'))
lex.add_entries(
read_db('AIRPORT.TAB', 0, 1, '_ap', strip_name=[], split_name=['/']))
lex.add_entries(read_db('COMP_CLS.TAB', 1, 1, '_cl'))
lex.add_entries(read_db('CLS_SVC.TAB', 0, 0, '_fb', prefix_name='code '))
handle_flight_numbers(lex)
lex.add_entries(MEALS)
handle_dollars(lex)
return lex
def get_manual_lexicon():
DAYS_OF_WEEK = [
(s, '%s:_da' % s)
for s in ('monday', 'tuesday', 'wednesday', 'thursday',
'friday', 'saturday', 'sunday')
]
# For dates
WORD_NUMBERS = [('one', '1:_dn'), ('two', '2:_dn'), ('three', '3:_dn'), ('four', '4:_dn'), ('five', '5:_dn'), ('six', '6:_dn'), ('seven', '7:_dn'), ('eight', '8:_dn'), ('nine', '9:_dn'), ('ten', '10:_dn'), ('eleven', '11:_dn'), ('twelve', '12:_dn'), ('thirteen', '13:_dn'), ('fourteen', '14:_dn'), ('fifteen', '15:_dn'), ('sixteen', '16:_dn'), ('seventeen', '17:_dn'), ('eighteen', '18:_dn'), ('nineteen', '19:_dn'), ('twenty', '20:_dn'), ('twenty one', '21:_dn'), ('twenty two', '22:_dn'), ('twenty three', '23:_dn'), ('twenty four', '24:_dn'), ('twenty five', '25:_dn'), ('twenty six', '26:_dn'), ('twenty seven', '27:_dn'), ('twenty eight', '28:_dn'), ('twenty nine', '29:_dn'), ('thirty', '30:_dn'), ('thirty one', '31:_dn')]
ORDINAL_NUMBERS = [('second', '2:_dn'), ('third', '3:_dn'), ('fourth', '4:_dn'), ('fifth', '5:_dn'), ('sixth', '6:_dn'), ('seventh', '7:_dn'), ('eighth', '8:_dn'), ('ninth', '9:_dn'), ('tenth', '10:_dn'), ('eleventh', '11:_dn'), ('twelfth', '12:_dn'), ('thirteenth', '13:_dn'), ('fourteenth', '14:_dn'), ('fifteenth', '15:_dn'), ('sixteenth', '16:_dn'), ('seventeenth', '17:_dn'), ('eighteenth', '18:_dn'), ('nineteenth', '19:_dn'), ('twentieth', '20:_dn'), ('twenty first', '21:_dn'), ('twenty second', '22:_dn'), ('twenty third', '23:_dn'), ('twenty fourth', '24:_dn'), ('twenty fifth', '25:_dn'), ('twenty sixth', '26:_dn'), ('twenty seventh', '27:_dn'), ('twenty eighth', '28:_dn'), ('twenty ninth', '29:_dn'), ('thirtieth', '30:_dn'), ('thirty first', '31:_dn')] # Prefer first class to "first = 1"
MEALS = [(m, '%s:_me' % m) for m in ('breakfast', 'lunch', 'dinner', 'snack')]
lex = Lexicon()
lex.add_entries(read_db('CITY.TAB', 1, 1, '_ci', strip_id=['.']))
lex.add_entries(DAYS_OF_WEEK)
lex.add_entries([(x + 's', y) for x, y in DAYS_OF_WEEK]) # Handle "on tuesdays"
lex.add_entries(read_db('AIRLINE.TAB', 0, 1, '_al',
strip_name=[', inc.', ', ltd.']))
handle_times(lex)
lex.add_entries(read_db('INTERVAL.TAB', 0, 0, '_pd'))
lex.add_entries(WORD_NUMBERS)
lex.add_entries(ORDINAL_NUMBERS)
lex.add_entries(read_db('MONTH.TAB', 1, 1, '_mn'))
lex.add_entries(read_db('AIRPORT.TAB', 0, 1, '_ap',
strip_name=[], split_name=['/']))
lex.add_entries(read_db('COMP_CLS.TAB', 1, 1, '_cl'))
lex.add_entries(read_db('CLS_SVC.TAB', 0, 0, '_fb', prefix_name='code '))
handle_flight_numbers(lex)
lex.add_entries(MEALS)
handle_dollars(lex)
return lex
