Python实现高精度敏感词过滤

class ACTrie:
    def __init__(self):
        self.root = {'fail': None, 'children': {}}
    
    def build_fail_pointers(self):
        queue = deque()
        for child in self.root['children'].values():
            child['fail'] = self.root
            queue.append(child)
        
        while queue:
            node = queue.popleft()
            for char, child in node['children'].items():
                fail = node['fail']
                while fail and char not in fail['children']:
                    fail = fail['fail']
                child['fail'] = fail['children'][char] if fail else self.root
                queue.append(child)

    def add_keyword(self, keyword):
        node = self.root
        for char in keyword:
            node = node['children'].setdefault(char, {'children': {}, 'is_end': False})
        node['is_end'] = True

    def filter_text(self, text):
        current = self.root
        result = []
        for i, char in enumerate(text):
            while current and char not in current['children']:
                current = current['fail']
            if not current:
                current = self.root
                continue
            current = current['children'][char]
            if current['is_end']:
                start = i - len(keyword) + 1
                result.append((start, i+1))
        return result

public class DFASensitiveFilter {
    private Map<Object, Object> dfaMap = new HashMap<>();

    public void buildDFA(Set<String> sensitiveWords) {
        for (String word : sensitiveWords) {
            Map nowMap = dfaMap;
            for (int i = 0; i < word.length(); i++) {
                char keyChar = word.charAt(i);
                Map<String, String> subMap = (Map) nowMap.get(keyChar);
                if (subMap == null) {
                    subMap = new HashMap<>();
                    nowMap.put(keyChar, subMap);
                }
                nowMap = subMap;
                if (i == word.length() - 1) {
                    nowMap.put("isEnd", "1");
                }
            }
        }
    }

    public String filter(String text) {
        StringBuilder result = new StringBuilder();
        for (int i = 0; i < text.length(); i++) {
            int length = checkDFA(text, i);
            if (length > 0) {
                result.append("***");
                i += length - 1;
            } else {
                result.append(text.charAt(i));
            }
        }
        return result.toString();
    }
}

from pypinyin import lazy_pinyin

def detect_pinyin(text):
    pinyin_text = ''.join(lazy_pinyin(text))
    return trie.search(pinyin_text)

{
  "⓪":"0", "①":"1", "②":"2",
  "𝓪":"a", "𝓑":"B", "𝒄":"c",
  "𝕯":"D", "è":"e", "ƒ":"f" 
}

def homophone_replace(word):
    mapping = {
        '艹': 'cao',
        '氵': 'shui',
        '扌': 'ti' 
    }
    return ''.join([mapping.get(c, c) for c in word])