def parse_tree(self):
p_tree = ParseTree()
p_tree.add_rule(('L', self.prod))
L = ['L_%s' % c for c in self.l]
if self.prod == 'l33t':
p_tree.add_rule(('l33t', zip(L, self.r)))
return p_tree
def parse_tree(self):
p_tree = ParseTree()
if isinstance(self.prod, basestring):
return self.prod
elif isinstance(self.prod, list):
for p in self.prod:
p_tree.add_rule((p.sym, p.parse_tree()))
else:
return self.prod.parse_tree()
return p_tree
def parse_tree(self):
p_tree = ParseTree()
if isinstance(self.prod, str): # 单纯字符串则返回字符串，这里其实可以看成只有一个根节点的语法树
return self.prod
elif isinstance(self.prod, list): # 是一个list，则将list中的每一个读出，添加后生成成一棵语法树
for p in self.prod:
p_tree.add_rule((p.sym, p.parse_tree()))
else: # 这是一个语法树，不用做任何处理了，直接看语法树内的节点是否还能生成语法树
return self.prod.parse_tree()
return p_tree
def parse_tree(self):
p_tree = ParseTree()
if isinstance(self.prod, basestring):
return self.prod
elif isinstance(self.prod, list):
for p in self.prod:
p_tree.add_rule((p.sym,p.parse_tree()))
else:
return self.prod.parse_tree()
return p_tree
def parse_tree(self):
p_tree = ParseTree()
p_tree.add_rule(('L', self.prod))
L = ['L_%s' % c for c in self.l]
if self.prod == 'l33t':
p_tree.add_rule(('l33t', zip(L, self.r)))
return p_tree
def defaultPasswordParse(self, word):
# 将所有的密码格式设置成G -> W1,G | D1,G | Y1,G | W1 | D1 | Y1的形式
pt = ParseTree()
n = len(word)
for i, c in enumerate(word):
r = whatchar(c) + '1'
# if i<n-1:
# r = r + ',G'
pt.add_rule(('G', r))
pt.add_rule((r[:2], c.lower()))
if r.startswith('W'):
nont_l = NonT_L(c, c)
pt.extend_rules(nont_l.parse_tree())
return pt
def default_parse_tree(self, word):
"""
Returns the default parse of a word. Default parse is
G -> W1,G | D1,G | Y1,G | W1 | D1 | Y1
This parses any string over the allowed alphabet
returns a l-o-r traversed parse tree
"""
pt = ParseTree()
n = len(word)
for i,c in enumerate(word):
r = whatchar(c) + '1'
if i<n-1:
r = r + ',G'
pt.add_rule(('G', r))
pt.add_rule((r[:2], c.lower()))
if r.startswith('W'):
nont_l = NonT_L(c, c)
pt.extend_rules(nont_l.parse_tree())
return pt
def default_parse_tree(self, word):
"""
Returns the default parse of a word. Default parse is
G -> W1,G | D1,G | Y1,G | W1 | D1 | Y1
This parses any string over the allowed alphabet
returns a l-o-r traversed parse tree
"""
pt = ParseTree()
n = len(word)
for i,c in enumerate(word):
r = whatchar(c) + '1'
if i<n-1:
r = r + ',G'
pt.add_rule(('G', r))
pt.add_rule((r[:2], c.lower()))
if r.startswith('W'):
nont_l = NonT_L(c, c)
pt.extend_rules(nont_l.parse_tree())
return pt
def parse_tree(self):
if isinstance(self.prod, basestring):
return ParseTree(self.sym, self.prod)
else:
return self.prod.parse_tree()
def parse_tree(self):
pt = ParseTree()
pt.add_rule((self.sym, self.prod))
pt.extend_rules(self.L.parse_tree())
return pt
def l_parse_tree(self, word): # leftmost parse-tree
pt = ParseTree()
p = self.parse(word)
if not p:
print "Failing at ", word.encode('utf-8')
return pt
pt.add_rule(('G', p[0]))
for l, each_r in zip(p[0].split(','), p[1]):
if isinstance(each_r, basestring):
pt.add_rule((l, each_r))
elif l.startswith('W'):
pt.add_rule((l, each_r[0]))
L_parse_tree = each_r[1].parse_tree()
pt.add_rule(L_parse_tree[0])
if len(L_parse_tree.tree)>1:
pt.tree.extend(L_parse_tree[1][1])
elif l == 'T':
p = each_r[1]
rule_name = ','.join([r[0].replace('T_','')
for r in p])
pt.add_rule((l, rule_name))
pt.extend_rule(p)
else:
print "Something is severly wrong"
return pt
def l_parse_tree(self, word): # leftmost parse-tree
pt = ParseTree()
p = self.parse(word)
if not p:
print "Failing at ", word.encode('utf-8')
return pt
#assert p[0] in self.G['G'], "Wrong rule: {} --> {}".format('G', p[0])
if p[0] not in self.G['G']:
return self.default_parse_tree(word)
pt.add_rule(('G', p[0]))
for l, each_r in zip(p[0].split(','), p[1]):
if isinstance(each_r, basestring):
pt.add_rule((l, each_r))
elif l.startswith('W'):
pt.add_rule((l, each_r[0]))
L_parse_tree = each_r[1].parse_tree()
pt.add_rule(L_parse_tree[0])
if len(L_parse_tree.tree)>1:
pt.tree.extend(L_parse_tree[1][1])
elif l == 'T':
p = each_r[1]
rule_name = ','.join([r[0].replace('T_','')
for r in p])
pt.add_rule((l, rule_name))
pt.extend_rules(p)
else:
print "Something is severly wrong"
return pt
def parse_tree(self):
pt = ParseTree()
pt.add_rule((self.sym, self.prod))
pt.extend_rules(self.L.parse_tree())
return pt
def lParseTree(self, passwd):
pt = ParseTree()
rule = self.parse(passwd)
print("our rule is ")
print(rule)
# 如果返回值为空的话，则说明翻译失败。记录此时密码
if not rule:
print("Failed encode %s" % passwd)
return pt
# 假如是无G状态，就是说简单的密码时，就使用简单的密码加密
if rule[0] not in self.G['G']:
return self.defaultPasswordParse(passwd)
# 否则的话，首先设定第一层的规则
pt.add_rule(('G', rule[0]))
# 然后，将每一层规则和每一个内容读出来，安插到parsetree中
for sym, rhs in zip(rule[0].split(','), rule[1]):
# 首先确认一下，假如规则不是W或者T的话，rhs此时应该只是字符串
if isinstance(rhs, str):
# 然后可以直接把这个规则放入
pt.add_rule((sym, rhs))
# 假如这个规则是W的话，那么后面跟着的就是(similarkeys_list,NonT_L)则此时要记得先把最相似对象内容放入存档中，并且记录下此时的内容大小写状态
elif sym.startswith('W'):
pt.add_rule((sym, rhs[0]))
# 这里使用parse_tree变量，把此时的单词的状态子叶记录
ltree = rhs[1].parse_tree()
# 然后，此时先把最初的规则放进去
pt.add_rule(ltree[0])
# 假如此时为’133t'规则的话，此时在'133t'之后会记录下此时可能发生替换的元素，则要把这些元素也放入(这些元素已经打包好了)
if len(ltree) > 1:
pt.tree.extend(ltree[1][1])
# 假如规则是T的话，那么肯定是('T',[('T_Y','1993')..]..)之类的
elif sym.startswith('T'):
# 为了与cfg文件内部保持一致，我们此时需要把文件转换成与cfg内的文件一致的格式
temp_sym = ''
for each_label in rhs[1]:
temp_sym += each_label[0].replace("T_", "")
pt.add_rule((sym, temp_sym))
# 然后把其他的节点也放进去
pt.extend_rules(rhs[1])
else:
print("we can't figure out this word")
# 完成
return pt