# nltk.download("punkt")
# nltk.download("maxnet_treebank_pos_tagger")
#设置新添的下载的nltk依赖库路径
data.path.append(r"nltk_data")
DIRECTNAME = 'Reuters'
# print("establishing the INDEX...")
# establishIndex.createIndex(DIRECTNAME)
print("getting word list...")
WORDLIST = getIndex.getWordList()
print("getting index...")
INDEX = getIndex.getIndex()
print("loading the wordnet...")
stemming.lemmatize_sentence("a", False)
PATH = tools.projectpath + DIRECTNAME
FILES = os.listdir(tools.reuterspath)
FILENUM = len(FILES)
LOOP = True
print("=================Searching System=================")
while LOOP:
print("searching operation: ")
print(
"[1] Overall [2]TOP K [3]BOOL [4]Phrase [5]wildcard [6]synonyms [7]exit"
)
print("your choice(int):")
try:
def preProcess(filename):
file = open(filename, 'r')
content = file.read()
words = stemming.lemmatize_sentence(content, False)
return words
K = 10
while LOOP:
print("---------> Start search No. {0}".format(SEARCH_NUM))
syn_FLAG = False
print("Enable Synonym Retrieval?[Y]/[N] ", end='')
choose = input()
if choose == "Y":
syn_FLAG = True
print("input the query statement(EXIT to quit): ", end='')
STATEMENT = input()
if STATEMENT == "EXIT":
break
print("stemming...")
INPUT_WORDS = stemming.lemmatize_sentence(STATEMENT, True)
DOC_LIST = BoolSearchDel.bool_search(DOC_NUM, INPUT_WORDS, INDEX, syn_FLAG)
print("Found {0} document(s) that matched query".format(len(DOC_LIST)))
for i in range(min(K, len(DOC_LIST))):
print("doc name:{0}.html, score = {1}".format(DOC_LIST[i][0],
DOC_LIST[i][1]))
SEARCH_NUM += 1
print("ByeBye!")
def preProcess(filename):
file = open(filename, 'r')
content = file.read()
words = stemming.lemmatize_sentence(content)
print(words)