예제 #1
0
    def TestCase(self):
        kmp = KMP()
        rs = kmp.search_MP("abcabcabcabc", "cabc")
        self.assertListEqual(rs, [2, 5, 8])

        rs = kmp.search_MP("ABC ABCDAB ABCDABCDABDE", "ABCDABD")
        self.assertListEqual(rs, [15])
예제 #2
0
 def __init__(self, p):
     # p : m by m sized pattern.
     self.p = list(p)
     self.m = len(p)
     # dr : pi[1..m] -> distinct row number.
     # pp : p converted in to sequence of distinct row #s.
     self.dr, self.pp = self.construct()
     # ac : Aho-Corasick instance for p (row-matching)
     self.ac = AC(self.dr.keys())
     # kmp : KMP instance for pp (column-matching)
     self.kmp = KMP(self.pp)
예제 #3
0
    def __init__(self, stream, pattern_len):
        '''
        Baker-bird 알고리즘 이니셜라이징
        :param patterns: Baker-bird 알고리즘을 실행할 패턴 배열
        '''
        self.ac = AhoCorasick()
        for _ in range(pattern_len):
            line = stream.next()
            self.ac.add_patterns(line)
        self.ac.build()

        self.r = {}
        idx = 1

        stream.set_seek()
        for _ in range(pattern_len):
            row = stream.next()
            if row not in self.r.keys():
                self.r[row] = str(idx)
                idx += 1

        stream.set_seek()
        self.kmp = KMP("".join([str(self.r[stream.next()]) for _ in range(pattern_len)]))
예제 #4
0
    tock = time.time()
    print('re search time:', tock - tick)

    tick = time.time()
    for text in text_iterator():
        for keyword in keywords:
            result = bf_search(text.strip(), keyword)
            # if result:
            #     print(keyword, result)
        tock = time.time()
    print('bf search time:', tock - tick)

    tick = time.time()
    for text in text_iterator():
        for keyword in keywords:
            result = KMP().search(text.strip(), keyword)
            # if result:
            #     print(keyword, result)
    tock = time.time()
    print('kmp search time:', tock - tick)

    tick = time.time()
    for text in text_iterator():
        result = ac_automation.search(text.strip())
    tock = time.time()
    # word2pos = defaultdict(list)
    # for start, end in result:
    #     word2pos[line[start: end+1]].append((start, end))
    # for word, pos in word2pos.items():
    #     print(word, pos)
    print('ac search time:', tock - tick)
예제 #5
0
from kmp import KMP
from fa import AUTOMATA
import sys

matcher = sys.argv[1]
pattern = sys.argv[2]
file = open(sys.argv[3], "r")
text = ""
for a in file.read().splitlines():
    text += a

if matcher == "KMP":

    print("wyszukiwanie wzorca za pomoca KMP")
    print("=================================")
    kmp = KMP(text, pattern)
    kmp.kmp()

else:

    print("wyszukiwanie wzorca za pomoca FA")
    print("================================")
    finite = AUTOMATA(text, pattern)
    finite.automata_matcher()
def kmp_array(fasta_list):
    kmp = KMP()
   
    kmp.build_kmp_table(fasta_list[0][1], print_table = True)
 def fifthw(self):
     QMessageBox.information(self, "规则","请输入 用半角逗号间隔的字符串 第一串最少6个字符最多20个 第二串最少一个 第二串字符数不超过第一串 回车完成输入",QMessageBox.Yes)
     from kmp import KMP
     self.demo5 = KMP()