def human2machine(msg):
if not isinstance(msg, unicode):
msg = msg.decode('utf-8')
#: process with some hard coded translations first
for k, v in h_d.items():
if k in msg.split('@3bugs')[-1]:
return v[0]
action = None
action_type = None
obj = None
repeated_duration = 0
import jieba.posseg as pseg
seg = classify(pseg.cut(msg), l_d.keys())
for v in seg['verb']:
action = ch_d.get(v, None)[0] or action
action_type = action_type_d.get(action, None)[0]
for n in seg['noun']:
obj = ch_d.get(n, None)[0] or obj
repeated_duration = find_repeated(seg) or 0
if action and (action_type is not None) and \
(action == 'capture' or obj):
return action, action_type, obj, repeated_duration
else:
logger.info('Found unknown command %s' % msg)
logger.debug('%s %s %s %s' % (str(action), str(action_type), str(obj),
str(repeated_duration)))
logger.debug(seg)
return None
def find_repeated(d):
'''Find repeated duration'''
if not d.get('num', None) or \
not (d.get('measure', None) or d.get('noun', None)):
return None
basic, unit = None, None
for n in d['num']:
try:
basic = int(n)
except:
pass
for m in d.get('measure', []) + d.get('noun', []):
unit = t_d.get(ch_d.get(m, None)[0], None) or unit
if basic and unit:
return unit(basic)
return None