def _do_new_item(self, desc, initial_tag, create_time=None, other=None):
"""helper function for implementing :meth:`new_item`"""
assert isinstance(desc, ItemDescBase), \
'bad desc: {!r}'.format(type(desc))
assert isinstance(initial_tag, list) and \
all([isinstance(i, basestring) for i in initial_tag]), \
'bad initial_tag: {!r}'.format(initial_tag)
assert other is None or isinstance(other, dict), \
'bad other arg: {!r}'.format(other)
initial_tag = map(unicode, initial_tag)
declare_tag(initial_tag)
if create_time is None:
create_time = time.localtime()
db = get_mongo('item')
item_id = global_counter('item')
db.ensure_index('fetcher_type')
db.ensure_index('fetcher_name')
db.ensure_index('tag')
db.ensure_index('creation_time')
doc = {
'_id': item_id,
'fetcher_type': self.fetcher_type,
'fetcher_name': self.fetcher_name,
'desc': deepcopy(desc),
'tag': initial_tag,
'other': other,
'creation_time': datetime.fromtimestamp(time.mktime(create_time))}
prefilter.apply(self, doc)
doc['desc'] = Binary(doc['desc'].serialize())
db.insert(doc)
return item_id
def auto_tagging(ctx, doc):
"""auto tagging an item.
It will load tagger model from `ukconfig.tagger_path`.
Model should be trained prior to make this function work"""
global _tagger
if _tagger is None:
try:
log_info('loading tagger ...')
_tagger = TextTagger.load(ukconfig.tagger_path)
except IOError:
log_info('tagger model not found.')
return
tags = _tagger.predict_one(doc['desc'].render_content())
declare_tag(tags)
log_info('original tag: ' + str(doc['tag']))
log_info('autotagging: ' + str(tags))
doc['tag'] = list(set(doc['tag'] + tags))
"""auto tag """
