def extract_process(texts):
list_ = []
trie = _global['trie']
for text in texts:
if not text: continue
list_ += extract_new_string(trie, text)
return list_
def doc_extract(texts):
map_ = {}
trie = _global['trie']
words_set = _global['words_set']
for text in texts:
doc = DOCID_RE.search(text)
if not doc:continue
words = extract_new_string(trie, text)
for word in words:
if (not map_.get(word)) and word in words_set:
map_[word]=doc.group()
return map_