diff --git a/analyse/analyse_test.go b/analyse/analyse_test.go index de2191f..059902f 100644 --- a/analyse/analyse_test.go +++ b/analyse/analyse_test.go @@ -92,92 +92,93 @@ var ( "C++和c#是什么关系?11+122=133,是吗?PI=3.14159", "你认识那个和主席握手的的哥吗?他开一辆黑色的士。", "枪杆子中出政权"} + Tags = [][]string{ - []string{"Python", "C++", "\u4f38\u624b\u4e0d\u89c1\u4e94\u6307", "\u5b59\u609f\u7a7a", "\u9ed1\u591c", "\u5317\u4eac", "\u8fd9\u662f", "\u4e00\u4e2a"}, - []string{"\u548c\u670d", "\u559c\u6b22", "\u65e5\u672c"}, - []string{"\u96f7\u7334", "\u4eba\u95f4", "\u56de\u5f52"}, - []string{"\u5de5\u4fe1\u5904", "\u5973\u5e72\u4e8b", "24", "\u4ea4\u6362\u673a", "\u79d1\u5ba4", "\u4eb2\u53e3", "\u5668\u4ef6", "\u6280\u672f\u6027", "\u4e0b\u5c5e", "\u4ea4\u4ee3", "\u6bcf\u6708", "\u5b89\u88c5", "\u7ecf\u8fc7", "\u5de5\u4f5c"}, - []string{"\u5ec9\u79df\u623f", "\u9700\u8981"}, - []string{"\u9970\u54c1", "\u6c38\u548c", "\u670d\u88c5", "\u6709\u9650\u516c\u53f8"}, - []string{"\u5929\u5b89\u95e8", "\u5317\u4eac"}, + []string{"Python", "C++", "伸手不见五指", "孙悟空", "黑夜", "北京", "这是", "一个"}, + []string{"和服", "喜欢", "日本"}, + []string{"雷猴", "人间", "回归"}, + []string{"工信处", "女干事", "24", "交换机", "科室", "亲口", "器件", "技术性", "下属", "交代", "每月", "安装", "经过", "工作"}, + []string{"廉租房", "需要"}, + []string{"饰品", "永和", "服装", "有限公司"}, + []string{"天安门", "北京"}, []string{"abc"}, - []string{"\u9a6c\u5c14\u53ef\u592b"}, - []string{"\u96f7\u7334", "\u7f51\u7ad9"}, - []string{"SOFTware", "Microsoft", "MICROcomputer", "\u5fae\u578b", "\u4e00\u8bcd", "\u8f6f\u4ef6", "\u8ba1\u7b97\u673a", "\u7ec4\u6210", "\u90e8\u5206"}, - []string{"\u8349\u6ce5\u9a6c", "\u6b3a\u5b9e", "\u8bcd\u6c47", "\u6d41\u884c", "\u4eca\u5e74"}, - []string{"\u6d0b\u534e\u5802", "\u603b\u5e9c", "\u4f0a\u85e4"}, - []string{"\u4e2d\u56fd\u79d1\u5b66\u9662\u8ba1\u7b97\u6280\u672f\u7814\u7a76\u6240"}, - []string{"\u6731\u4e3d\u53f6", "\u7f57\u5bc6\u6b27"}, - []string{"\u9053\u5177", "\u670d\u88c5", "\u8d2d\u4e70"}, - []string{"\u81ea\u73cd", "\u655e\u5e1a", "PS", "\u5f00\u6e90", "\u4e0d\u65ad\u6539\u8fdb", "\u6566\u4fc3", "\u597d\u5904", "\u907f\u514d", "\u80fd\u591f", "\u89c9\u5f97", "\u5c31\u662f", "\u81ea\u5df1", "\u4e00\u4e2a"}, - []string{"\u77f3\u9996\u5e02", "\u6e56\u5317\u7701"}, - []string{"\u5341\u5830\u5e02", "\u6e56\u5317\u7701"}, - []string{"\u603b\u7ecf\u7406", "\u8fd9\u4ef6", "\u5b8c\u6210", "\u4e8b\u60c5"}, - []string{"\u4fee\u597d", "\u7535\u8111"}, - []string{"\u4e00\u4e86\u767e\u4e86", "\u505a\u597d", "\u8fd9\u4ef6", "\u4e8b\u60c5"}, - []string{"\u5ba1\u7f8e", "\u89c2\u70b9", "\u4eba\u4eec", "\u4e0d\u540c"}, - []string{"\u7f8e\u7684", "\u7a7a\u8c03", "\u6211\u4eec", "\u4e00\u4e2a"}, - []string{"\u7ebf\u7a0b", "\u521d\u59cb\u5316", "\u6ce8\u610f", "\u6211\u4eec"}, - []string{"\u597d\u591a", "\u539f\u5b50", "\u5206\u5b50", "\u7ec4\u7ec7", "\u4e00\u4e2a"}, - []string{"\u9a6c\u5230\u529f\u6210"}, - []string{"\u65e0\u5e95\u6d1e"}, - []string{"\u9996\u90fd", "\u5317\u4eac", "\u4e2d\u56fd"}, - []string{"\u5b59\u541b\u610f"}, - []string{"\u9a6c\u671d\u65ed", "\u5916\u4ea4\u90e8", "\u53d1\u8a00\u4eba"}, - []string{"\u7b2c\u56db\u5c4a", "\u4e1c\u4e9a", "\u5cf0\u4f1a", "\u9886\u5bfc\u4eba", "\u4f1a\u8bae"}, - []string{"\u4e94\u5e74", "\u8fc7\u53bb"}, - []string{"\u5f88\u957f", "\u9700\u8981"}, - []string{"60", "\u9605\u5175", "\u5468\u5e74", "\u9996\u90fd"}, - []string{"\u5ba1\u7f8e", "\u4f60\u597d", "\u89c2\u70b9", "\u4eba\u4eec", "\u4e0d\u540c"}, - []string{"\u4e16\u535a\u56ed", "\u6c34\u679c", "\u7136\u540e"}, - []string{"\u4e16\u535a\u56ed", "\u6c34\u679c", "\u7136\u540e"}, - []string{"\u540e\u6765", "\u4f46\u662f", "\u77e5\u9053"}, - []string{"\u5408\u7406", "\u5b58\u5728"}, + []string{"马尔可夫"}, + []string{"雷猴", "网站"}, + []string{"SOFTware", "Microsoft", "MICROcomputer", "微型", "一词", "软件", "计算机", "组成", "部分"}, + []string{"草泥马", "欺实", "词汇", "流行", "今年"}, + []string{"洋华堂", "总府", "伊藤"}, + []string{"中国科学院计算技术研究所"}, + []string{"朱丽叶", "罗密欧"}, + []string{"道具", "服装", "购买"}, + []string{"自珍", "敞帚", "PS", "开源", "不断改进", "敦促", "好处", "避免", "能够", "觉得", "就是", "自己", "一个"}, + []string{"石首市", "湖北省"}, + []string{"十堰市", "湖北省"}, + []string{"总经理", "这件", "完成", "事情"}, + []string{"修好", "电脑"}, + []string{"一了百了", "做好", "这件", "事情"}, + []string{"审美", "观点", "人们", "不同"}, + []string{"美的", "空调", "我们", "一个"}, + []string{"线程", "初始化", "注意", "我们"}, + []string{"好多", "原子", "分子", "组织", "一个"}, + []string{"马到功成"}, + []string{"无底洞"}, + []string{"首都", "北京", "中国"}, + []string{"孙君意"}, + []string{"马朝旭", "外交部", "发言人"}, + []string{"第四届", "东亚", "峰会", "领导人", "会议"}, + []string{"五年", "过去"}, + []string{"很长", "需要"}, + []string{"60", "阅兵", "周年", "首都"}, + []string{"审美", "你好", "观点", "人们", "不同"}, + []string{"世博园", "水果", "然后"}, + []string{"世博园", "水果", "然后"}, + []string{"后来", "但是", "知道"}, + []string{"合理", "存在"}, []string{}, - []string{"rong", "love", "\u4e0d\u4ee5\u4e3a\u803b", "\u4ee5\u4e3a"}, + []string{"rong", "love", "不以为耻", "以为"}, []string{}, []string{}, - []string{"hello", "\u5ba1\u7f8e", "\u4f60\u597d", "\u89c2\u70b9", "\u4eba\u4eec", "\u4e0d\u540c"}, - []string{"\u7f51\u9875", "\u57fa\u4e8e", "\u5f62\u5f0f", "\u4e3b\u8981"}, - []string{"hello", "\u5ba1\u7f8e", "\u4f60\u597d", "\u89c2\u70b9", "\u4eba\u4eec", "\u4e0d\u540c"}, - []string{"\u60f3\u8981", "\u62e5\u6709", "\u4e3a\u4ec0\u4e48", "\u751f\u6d3b", "\u4e0d\u80fd"}, - []string{"\u540e\u6765"}, - []string{"\u6b64\u6b21", "\u4e3a\u4e86", "\u4e2d\u56fd"}, - []string{"\u89e3\u51b3", "\u4f7f\u7528", "\u4e00\u4e9b", "\u95ee\u9898", "\u53ef\u4ee5"}, - []string{"\u89e3\u51b3", "\u4f7f\u7528", "\u4e00\u4e9b", "\u95ee\u9898", "\u53ef\u4ee5"}, - []string{"\u89e3\u51b3", "\u5176\u5b9e", "\u4f7f\u7528", "\u4e00\u4e9b", "\u95ee\u9898", "\u53ef\u4ee5"}, - []string{"\u597d\u4eba", "\u89e3\u51b3", "\u4f7f\u7528", "\u4e00\u4e9b", "\u95ee\u9898", "\u53ef\u4ee5"}, - []string{"\u662f\u56e0\u4e3a", "\u56fd\u5bb6"}, - []string{"\u8001\u5e74", "\u641c\u7d22", "\u652f\u6301"}, - []string{"\u95f2\u6cd5", "\u4e2d\u672c", "laoshipukong", "RT", "27", "\u8d23\u4efb\u6cd5", "\u8499\u4eba", "\u4e07\u52ab\u4e0d\u590d", "\u4e3e\u8bc1", "\u5012\u7f6e", "\u533b\u60a3", "\u90a3\u90e8", "\u62c9\u5012", "\u4fb5\u6743", "\u5168\u56fd\u4eba\u5927\u5e38\u59d4\u4f1a", "\u8349\u6848", "\u5883\u5730", "\u7ea0\u7eb7", "\u5220\u9664", "\u5f31\u52bf"}, + []string{"hello", "审美", "你好", "观点", "人们", "不同"}, + []string{"网页", "基于", "形式", "主要"}, + []string{"hello", "审美", "你好", "观点", "人们", "不同"}, + []string{"想要", "拥有", "为什么", "生活", "不能"}, + []string{"后来"}, + []string{"此次", "为了", "中国"}, + []string{"解决", "使用", "一些", "问题", "可以"}, + []string{"解决", "使用", "一些", "问题", "可以"}, + []string{"解决", "其实", "使用", "一些", "问题", "可以"}, + []string{"好人", "解决", "使用", "一些", "问题", "可以"}, + []string{"是因为", "国家"}, + []string{"老年", "搜索", "支持"}, + []string{"闲法", "中本", "laoshipukong", "RT", "27", "责任法", "蒙人", "万劫不复", "举证", "倒置", "医患", "那部", "拉倒", "侵权", "全国人大常委会", "草案", "境地", "纠纷", "删除", "弱势"}, []string{}, []string{}, - []string{"\u5728\u7406", "\u786e\u5b9e"}, - []string{"\u957f\u6625", "\u6625\u8282", "\u8bb2\u8bdd", "\u5e02\u957f"}, - []string{"\u7ed3\u5a5a", "\u5c1a\u672a"}, - []string{"\u5206\u5b50", "\u7ed3\u5408"}, - []string{"\u65c5\u6e38", "\u6700\u597d", "\u670d\u52a1"}, - []string{"\u7684\u786e", "\u8fd9\u4ef6", "\u4e8b\u60c5"}, - []string{"\u6307\u6b63", "\u53c2\u8003", "\u5927\u5bb6"}, - []string{"\u584c\u6865", "\u54c8\u5c14\u6ee8", "\u516c\u5e03", "\u539f\u56e0", "\u653f\u5e9c"}, - []string{"\u5165\u53e3\u5904", "\u673a\u573a"}, - []string{"\u90a2\u6c38\u81e3", "\u6444\u5f71", "\u62a5\u9053"}, - []string{"\u533a\u5206\u5ea6", "BP", "\u795e\u7ecf\u7f51\u7edc", "\u8bad\u7ec3", "\u5206\u7c7b", "\u624d\u80fd", "\u5982\u4f55", "\u589e\u52a0"}, - []string{"\u957f\u6c5f\u5927\u6865", "\u5357\u4eac\u5e02"}, - []string{"SMT", "NiuTrans", "\u4f7f\u7528\u8005", "\u4fbf\u4e8e", "\u7528\u4e8e", "\u5efa\u8bae", "\u5229\u7528", "\u4e3a\u4e86", "\u7814\u7a76", "\u4e00\u4e9b"}, - []string{"\u957f\u6625\u5e02", "\u836f\u5e97", "\u957f\u6625"}, - []string{"\u9093\u9896\u8d85", "\u751f\u524d", "\u8863\u670d", "\u559c\u6b22"}, - []string{"\u653f\u6cbb\u5c40", "\u70ed\u7231", "\u5e38\u59d4", "\u80e1\u9526\u6d9b", "\u548c\u5e73", "\u4e16\u754c"}, - []string{"\u53f3\u9762", "\u5b59\u5065", "\u8303\u51ef", "\u674e\u677e\u6d2a", "\u6731\u4f1a\u9707", "\u6d77\u6797", "\u5de6\u9762", "\u7a0b\u5e8f\u5458", "\u518d\u5f80"}, - []string{"\u4e00\u6b21\u6027", "\u591a\u5c11"}, - []string{"\u56db\u5757", "\u4e94\u5757", "\u4e09\u5757", "\u4e00\u65a4", "\u4e24\u5757", "\u4e00\u672c", "\u4e00\u5957", "\u4e00\u6761"}, - []string{"\u548c\u5c1a", "\u548c\u5c1a\u5934", "\u4e00\u6837", "\u4e00\u4e2a"}, - []string{"\u548c\u5e73\u95e8", "\u5171\u548c\u515a", "\u5730\u94c1", "\u515a\u5458", "\u516c\u6c11", "\u7238\u7238", "\u4e2d\u534e\u4eba\u6c11\u5171\u548c\u56fd"}, - []string{"\u5f20\u6653\u6885", "T\u6064", "B\u8d85", "\u533b\u9662", "\u4eba\u6c11", "\u7136\u540e"}, - []string{"offer", "AT&T", "\u4e0d\u9519", "\u4e00\u4ef6", "\u516c\u53f8"}, - []string{"c#", "PI", "C++", "3.14159", "133", "122", "11", "\u5173\u7cfb", "\u4ec0\u4e48"}, - []string{"\u7684\u58eb", "\u7684\u54e5", "\u4ed6\u5f00", "\u63e1\u624b", "\u4e00\u8f86", "\u9ed1\u8272", "\u4e3b\u5e2d", "\u8ba4\u8bc6", "\u90a3\u4e2a"}, - []string{"\u67aa\u6746\u5b50", "\u653f\u6743"}, + []string{"在理", "确实"}, + []string{"长春", "春节", "讲话", "市长"}, + []string{"结婚", "尚未"}, + []string{"分子", "结合"}, + []string{"旅游", "最好", "服务"}, + []string{"的确", "这件", "事情"}, + []string{"指正", "参考", "大家"}, + []string{"塌桥", "哈尔滨", "公布", "原因", "政府"}, + []string{"入口处", "机场"}, + []string{"邢永臣", "摄影", "报道"}, + []string{"区分度", "BP", "神经网络", "训练", "分类", "才能", "如何", "增加"}, + []string{"长江大桥", "南京市"}, + []string{"SMT", "NiuTrans", "使用者", "便于", "用于", "建议", "利用", "为了", "研究", "一些"}, + []string{"长春市", "药店", "长春"}, + []string{"邓颖超", "生前", "衣服", "喜欢"}, + []string{"政治局", "热爱", "常委", "胡锦涛", "和平", "世界"}, + []string{"右面", "孙健", "范凯", "李松洪", "朱会震", "海林", "左面", "程序员", "再往"}, + []string{"一次性", "多少"}, + []string{"四块", "五块", "三块", "一斤", "两块", "一本", "一套", "一条"}, + []string{"和尚", "和尚头", "一样", "一个"}, + []string{"和平门", "共和党", "地铁", "党员", "公民", "爸爸", "中华人民共和国"}, + []string{"张晓梅", "T恤", "B超", "医院", "人民", "然后"}, + []string{"offer", "AT&T", "不错", "一件", "公司"}, + []string{"c#", "PI", "C++", "3.14159", "133", "122", "11", "关系", "什么"}, + []string{"的士", "的哥", "他开", "握手", "一辆", "黑色", "主席", "认识", "那个"}, + []string{"枪杆子", "政权"}, } )