import struct
import os# 搜狗的scel词库就是保存的文本的unicode编码，每两个字节一个字符（中文汉字或者英文字母）
# 找出其每部分的偏移位置即可
# 主要两部分
# 1.全局拼音表，貌似是所有的拼音组合，字典序
#       格式为(index,len,pinyin)的列表
#       index: 两个字节的整数 代表这个拼音的索引
#       len: 两个字节的整数 拼音的字节长度
#       pinyin: 当前的拼音，每个字符两个字节，总长len
#
# 2.汉语词组表
#       格式为(same,py_table_len,py_table,{word_len,word,ext_len,ext})的一个列表
#       same: 两个字节 整数 同音词数量
#       py_table_len:  两个字节 整数
#       py_table: 整数列表，每个整数两个字节,每个整数代表一个拼音的索引
#
#       word_len:两个字节 整数 代表中文词组字节数长度
#       word: 中文词组,每个中文汉字两个字节，总长度word_len
#       ext_len: 两个字节 整数 代表扩展信息的长度，好像都是10
#       ext: 扩展信息 前两个字节是一个整数(不知道是不是词频) 后八个字节全是0
#
#      {word_len,word,ext_len,ext} 一共重复same次 同音词 相同拼音表# 拼音表偏移，
startPy = 0x1540;# 汉语词组表偏移
startChinese = 0x2628;# 全局拼音表
GPy_Table = {}# 解析结果
# 元组(词频,拼音,中文词组)的列表
GTable = []# 原始字节码转为字符串
def byte2str(data):pos = 0str = ''while pos < len(data):c = chr(struct.unpack('H', bytes([data[pos], data[pos + 1]]))[0])if c != chr(0):str += cpos += 2return str# 获取拼音表
def getPyTable(data):data = data[4:]pos = 0while pos < len(data):index = struct.unpack('H', bytes([data[pos],data[pos + 1]]))[0]pos += 2lenPy = struct.unpack('H', bytes([data[pos], data[pos + 1]]))[0]pos += 2py = byte2str(data[pos:pos + lenPy])GPy_Table[index] = pypos += lenPy# 获取一个词组的拼音
def getWordPy(data):pos = 0ret = ''while pos < len(data):index = struct.unpack('H', bytes([data[pos], data[pos + 1]]))[0]ret += GPy_Table[index]pos += 2return ret# 读取中文表
def getChinese(data):pos = 0while pos < len(data):# 同音词数量same = struct.unpack('H', bytes([data[pos], data[pos + 1]]))[0]# 拼音索引表长度pos += 2py_table_len = struct.unpack('H', bytes([data[pos], data[pos + 1]]))[0]# 拼音索引表pos += 2py = getWordPy(data[pos: pos + py_table_len])# 中文词组pos += py_table_lenfor i in range(same):# 中文词组长度c_len = struct.unpack('H', bytes([data[pos], data[pos + 1]]))[0]# 中文词组pos += 2word = byte2str(data[pos: pos + c_len])# 扩展数据长度pos += c_lenext_len = struct.unpack('H', bytes([data[pos], data[pos + 1]]))[0]# 词频pos += 2count = struct.unpack('H', bytes([data[pos], data[pos + 1]]))[0]# 保存GTable.append((count, py, word))# 到下个词的偏移位置pos += ext_lendef scel2txt(file_name):print('-' * 60)with open(file_name, 'rb') as f:data = f.read()print("词库名：", byte2str(data[0x130:0x338])) # .encode('GB18030')print("词库类型：", byte2str(data[0x338:0x540]))print("描述信息：", byte2str(data[0x540:0xd40]))print("词库示例：", byte2str(data[0xd40:startPy]))getPyTable(data[startPy:startChinese])getChinese(data[startChinese:])if __name__ == '__main__':# scel所在文件夹路径in_path = "E:\python_workspace"# 输出词典所在文件夹路径out_path = "coal_dict.txt"fin = [fname for fname in os.listdir(in_path) if fname[-5:] == ".scel"]for f in fin:f = os.path.join(in_path, f)scel2txt(f)# 保存结果with open(out_path, 'w', encoding='utf8') as f:f.writelines([word+'\n' for count, py, word in GTable])

from IPython.core.interactiveshell import InteractiveShellInteractiveShell.ast_node_interactivity = "all"from pypinyin import pinyin, lazy_pinyin, Styleidiom_dic = {}
idiom_list = []
idiom_char_dic = {}with open('E:\python_workspace\coal_dict.txt', 'r', encoding='utf8') as r:for line in r:line = line.strip()if None == line or line == '':continueidiom_list.append(line)key = lazy_pinyin(line)[0]value = ''if key in idiom_dic.keys():value = idiom_dic[key] + ',' + lineelse:value = lineidiom_dic[key] = value# 汉字接龙key_char = line[0]value_char = ''if key_char in idiom_char_dic.keys():value_char = idiom_char_dic[key_char] + ',' + lineelse:value_char = lineidiom_char_dic[key_char] = value_char# 汉字接龙，polyphone -- 是否匹配读音
def idiom_next_char(idiom, polyphone=False):if idiom not in idiom_list:res = idiom + ' is not one idiom'else:last = idiom[len(idiom) - 1]if polyphone:passif last not in idiom_char_dic:res = 'library without the supply idioms'else:aa = idiom_char_dic[last]last = lazy_pinyin(idiom)[len(idiom) - 1]bb = idiom_dic[last]aa_list = aa.split(',')bb_list = bb.split(',')cd_list = set(aa_list).intersection(set(bb_list))  # 求并集res = ','.join(cd_list)else:if last not in idiom_char_dic:res = 'library without the supply idioms'else:res = idiom_char_dic[last]return res# 拼音接龙
def idiom_next(idiom):if idiom not in idiom_list:res = idiom + ' is not one idiom'else:last = lazy_pinyin(idiom)[len(idiom) - 1]if last not in idiom_dic:res = 'library without the supply idioms'else:res = idiom_dic[last]return res# print(idiom_next('怒发冲冠'))# 汉字定长接龙
def idiom_multi_char_length(idiom, length=10, polyphone=False):index = 0res_list = [idiom]while index < length:res = idiom_next_char(idiom, polyphone)if 'idiom' in res:breakelse:res_next = res.split(',')idiom = res_next[0]res_list.append(idiom)index = index + 1return res_list# 拼音定长接龙
def idiom_multi_length(idiom, length=10):index = 0res_list = [idiom]while index < length:res = idiom_next(idiom)if 'idiom' in res:breakelse:res_next = res.split(',')idiom = res_next[0]res_list.append(idiom)index = index + 1return res_listdef check_none_follow_list():none_follow = []for idiom in idiom_list:res = idiom_next(idiom)if 'idiom' in res:none_follow.append(idiom)return none_follow# none_supply = check_none_follow_list()
# print(none_supply)

idiom_multi_length('刻舟求剑')
Out[6]:
['刻舟求剑','兼爱无私','死败涂地','低昂不就','灸艾分痛','同胞共气','期月有成','撑岸就船','传杯换盏','粘皮带骨','告朔饩羊']

idiom_multi_char_length('刻舟求剑')
Out[5]:
['刻舟求剑','剑拔弩张','张本继末','末大必折','折本买卖','卖卜测字','字挟风霜','霜刀小径','径情而行','行行出状元','元恶大憝']

idiom_multi_char_length('刻舟求剑',polyphone=True)
Out[7]:
['刻舟求剑','剑拔弩张','张冠李戴','戴凭夺席','席丰履厚','厚貌深情','情恕理遣','遣将调兵','兵来将挡水来土掩','掩耳不闻','闻弦歌而知雅意']