def dictionary_check(text, dictionary):
    words = text.split()  # 簡單分詞（實際場景需更復雜的分詞邏輯）
    errors = []
    for word in words:
        if word.lower() not in dictionary:
            errors.append(word)
    return errors

# 示例詞典
standard_dict = {"今天", "天氣", "很好", "我", "去", "學校", "學習"}
text = "今天天汽很好 我區(qū)學校學習"
errors = dictionary_check(text, standard_dict)
print("檢測到的錯別字:", errors)  # 輸出: ['天汽', '區(qū)']

from Levenshtein import distance

def find_closest_word(word, dictionary):
    candidates = []
    for dict_word in dictionary:
        edit_dist = distance(word, dict_word)
        candidates.append((dict_word, edit_dist))
    candidates.sort(key=lambda x: x[1])
    return candidates[0][0] if candidates else None

# 擴展詞典檢查函數(shù)
def enhanced_dictionary_check(text, dictionary):
    words = text.split()
    errors = []
    for word in words:
        if word.lower() not in dictionary:
            correction = find_closest_word(word, dictionary)
            if correction:
                errors.append((word, correction))
    return errors

text = "我喜換編程"
errors = enhanced_dictionary_check(text, {"我", "喜歡", "編程"})
print("錯別字及建議:", errors)  # 輸出: [('喜換', '喜歡')]

import enchant

def enchant_check(text, lang='en_US'):
    d = enchant.Dict(lang)
    words = text.split()
    errors = [word for word in words if not d.check(word)]
    return errors

text = "I havv a speling eror"
errors = enchant_check(text)
print("檢測到的錯誤:", errors)  # 輸出: ['havv', 'speling', 'eror']

import symspellpy

def symspell_check(text):
    sym_spell = symspellpy.SymSpell()
    sym_spell.load_dictionary("frequency_dictionary_en_82_765.txt", 0, 1)
    
    suggestions = sym_spell.lookup_compound(text, max_edit_distance=2)
    errors = []
    for suggestion in suggestions:
        if suggestion.term != text:
            errors.append((text, suggestion.term))
    return errors

text = "I am goig to the park"
errors = symspell_check(text)
print("錯誤及建議:", errors)  # 輸出: [('I am goig to the park', 'I am going to the park')]

from transformers import BertTokenizer, BertForMaskedLM
import torch

def bert_check(text, model_name='bert-base-chinese'):
    tokenizer = BertTokenizer.from_pretrained(model_name)
    model = BertForMaskedLM.from_pretrained(model_name)
    
    # 模擬檢測邏輯（實際需更復雜的實現(xiàn)）
    suspicious_words = []
    for i, char in enumerate(text):
        # 簡單示例：檢測連續(xù)相同字符（如"天天"）
        if i > 0 and text[i] == text[i-1]:
            suspicious_words.append((i-1, i+1, text[i-1:i+1]))
    
    # 實際應通過模型預測最可能正確詞
    return suspicious_words

text = "今天天氣天晴朗"
errors = bert_check(text)
print("可疑片段:", errors)  # 輸出: [(5, 7, '天天')]

# 偽代碼示例（實際需訓練模型）
from transformers import AutoTokenizer, AutoModelForTokenClassification

def sequence_labeling_check(text):
    tokenizer = AutoTokenizer.from_pretrained("bert-base-chinese")
    model = AutoModelForTokenClassification.from_pretrained("your-trained-model")
    
    inputs = tokenizer(text, return_tensors="pt")
    outputs = model(**inputs)
    predictions = torch.argmax(outputs.logits, dim=2)
    
    # 假設標簽1表示錯誤
    errors = []
    for i, pred in enumerate(predictions[0]):
        if pred == 1:
            start = inputs.char_to_token(i, position_id=0)
            # 實際需更復雜的字符位置映射
            errors.append((i, text[i]))
    return errors

def hybrid_check(text):
    # 第一層：詞典檢查
    base_errors = dictionary_check(text, standard_dict)
    
    # 第二層：規(guī)則檢查（如重復詞、特殊符號）
    rule_errors = []
    for i in range(len(text)-1):
        if text[i] == text[i+1]:
            rule_errors.append((i, text[i:i+2]))
    
    # 第三層：模型檢查（需加載預訓練模型）
    # model_errors = bert_check(text)
    
    return {
        "dictionary_errors": base_errors,
        "rule_errors": rule_errors,
        # "model_errors": model_errors
    }

def domain_specific_check(text, domain="medical"):
    domain_dict = {
        "medical": {"抗生素", "炎癥", "處方"},
        "legal": {"合同", "甲方", "違約"}
    }.get(domain, set())
    
    # 加載領域詞典進行檢測
    return dictionary_check(text, domain_dict)

import jieba
from collections import defaultdict

class ChineseSpellChecker:
    def __init__(self):
        # 加載基礎詞典
        self.base_dict = self.load_dictionary("base_dict.txt")
        # 加載常見錯別字映射
        self.error_map = self.load_error_map("common_errors.csv")
    
    def load_dictionary(self, filepath):
        with open(filepath, 'r', encoding='utf-8') as f:
            return set(line.strip() for line in f)
    
    def load_error_map(self, filepath):
        error_map = defaultdict(list)
        with open(filepath, 'r', encoding='utf-8') as f:
            for line in f:
                wrong, correct = line.strip().split(',')
                error_map[wrong].append(correct)
        return error_map
    
    def check(self, text):
        words = jieba.lcut(text)
        errors = []
        
        for word in words:
            # 1. 直接詞典匹配
            if word not in self.base_dict:
                # 2. 檢查常見錯別字映射
                if word in self.error_map:
                    suggestions = self.error_map[word]
                    errors.append((word, suggestions[0]))  # 取第一個建議
                else:
                    # 3. 未來可集成模型預測
                    errors.append((word, None))
        
        return errors

# 使用示例
checker = ChineseSpellChecker()
text = "今天天氣晴郎，我很高興。"
errors = checker.check(text)
print("檢測結果:", errors)  # 輸出: [('晴郎', '晴朗')]