From af7fefc5fa29497018c38952df0d8ec6c97c2c2b Mon Sep 17 00:00:00 2001 From: Wang Bin Date: Mon, 26 Jan 2015 16:20:42 +0800 Subject: [PATCH] make tests more readable --- jieba_test.go | 993 +++++++++++++++++++++++++------------------------- 1 file changed, 494 insertions(+), 499 deletions(-) diff --git a/jieba_test.go b/jieba_test.go index a2c807a..fb6276e 100644 --- a/jieba_test.go +++ b/jieba_test.go @@ -93,532 +93,527 @@ var ( "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"} - defaultCutResult = [][]string{ - []string{"\u8fd9\u662f", "\u4e00\u4e2a", "\u4f38\u624b\u4e0d\u89c1\u4e94\u6307", "\u7684", "\u9ed1\u591c", "\u3002", "\u6211", "\u53eb", "\u5b59\u609f\u7a7a", "\uff0c", "\u6211", "\u7231", "\u5317\u4eac", "\uff0c", "\u6211", "\u7231", "Python", "\u548c", "C++", "\u3002"}, - []string{"\u6211", "\u4e0d", "\u559c\u6b22", "\u65e5\u672c", "\u548c\u670d", "\u3002"}, - []string{"\u96f7\u7334", "\u56de\u5f52", "\u4eba\u95f4", "\u3002"}, - []string{"\u5de5\u4fe1\u5904", "\u5973\u5e72\u4e8b", "\u6bcf\u6708", "\u7ecf\u8fc7", "\u4e0b\u5c5e", "\u79d1\u5ba4", "\u90fd", "\u8981", "\u4eb2\u53e3", "\u4ea4\u4ee3", "24", "\u53e3", "\u4ea4\u6362\u673a", "\u7b49", "\u6280\u672f\u6027", "\u5668\u4ef6", "\u7684", "\u5b89\u88c5", "\u5de5\u4f5c"}, - []string{"\u6211", "\u9700\u8981", "\u5ec9\u79df\u623f"}, - []string{"\u6c38\u548c", "\u670d\u88c5", "\u9970\u54c1", "\u6709\u9650\u516c\u53f8"}, - []string{"\u6211", "\u7231", "\u5317\u4eac", "\u5929\u5b89\u95e8"}, + defaultCutResult = [][]string{[]string{"这是", "一个", "伸手不见五指", "的", "黑夜", "。", "我", "叫", "孙悟空", ",", "我", "爱", "北京", ",", "我", "爱", "Python", "和", "C++", "。"}, + []string{"我", "不", "喜欢", "日本", "和服", "。"}, + []string{"雷猴", "回归", "人间", "。"}, + []string{"工信处", "女干事", "每月", "经过", "下属", "科室", "都", "要", "亲口", "交代", "24", "口", "交换机", "等", "技术性", "器件", "的", "安装", "工作"}, + []string{"我", "需要", "廉租房"}, + []string{"永和", "服装", "饰品", "有限公司"}, + []string{"我", "爱", "北京", "天安门"}, []string{"abc"}, - []string{"\u9690", "\u9a6c\u5c14\u53ef\u592b"}, - []string{"\u96f7\u7334", "\u662f", "\u4e2a", "\u597d", "\u7f51\u7ad9"}, - []string{"\u201c", "Microsoft", "\u201d", "\u4e00\u8bcd", "\u7531", "\u201c", "MICROcomputer", "\uff08", "\u5fae\u578b", "\u8ba1\u7b97\u673a", "\uff09", "\u201d", "\u548c", "\u201c", "SOFTware", "\uff08", "\u8f6f\u4ef6", "\uff09", "\u201d", "\u4e24", "\u90e8\u5206", "\u7ec4\u6210"}, - []string{"\u8349\u6ce5\u9a6c", "\u548c", "\u6b3a\u5b9e", "\u9a6c", "\u662f", "\u4eca\u5e74", "\u7684", "\u6d41\u884c", "\u8bcd\u6c47"}, - []string{"\u4f0a\u85e4", "\u6d0b\u534e\u5802", "\u603b\u5e9c", "\u5e97"}, - []string{"\u4e2d\u56fd\u79d1\u5b66\u9662\u8ba1\u7b97\u6280\u672f\u7814\u7a76\u6240"}, - []string{"\u7f57\u5bc6\u6b27", "\u4e0e", "\u6731\u4e3d\u53f6"}, - []string{"\u6211", "\u8d2d\u4e70", "\u4e86", "\u9053\u5177", "\u548c", "\u670d\u88c5"}, - []string{"PS", ":", " ", "\u6211", "\u89c9\u5f97", "\u5f00\u6e90", "\u6709", "\u4e00\u4e2a", "\u597d\u5904", "\uff0c", "\u5c31\u662f", "\u80fd\u591f", "\u6566\u4fc3", "\u81ea\u5df1", "\u4e0d\u65ad\u6539\u8fdb", "\uff0c", "\u907f\u514d", "\u655e\u5e1a", "\u81ea\u73cd"}, - []string{"\u6e56\u5317\u7701", "\u77f3\u9996\u5e02"}, - []string{"\u6e56\u5317\u7701", "\u5341\u5830\u5e02"}, - []string{"\u603b\u7ecf\u7406", "\u5b8c\u6210", "\u4e86", "\u8fd9\u4ef6", "\u4e8b\u60c5"}, - []string{"\u7535\u8111", "\u4fee\u597d", "\u4e86"}, - []string{"\u505a\u597d", "\u4e86", "\u8fd9\u4ef6", "\u4e8b\u60c5", "\u5c31", "\u4e00\u4e86\u767e\u4e86", "\u4e86"}, - []string{"\u4eba\u4eec", "\u5ba1\u7f8e", "\u7684", "\u89c2\u70b9", "\u662f", "\u4e0d\u540c", "\u7684"}, - []string{"\u6211\u4eec", "\u4e70", "\u4e86", "\u4e00\u4e2a", "\u7f8e\u7684", "\u7a7a\u8c03"}, - []string{"\u7ebf\u7a0b", "\u521d\u59cb\u5316", "\u65f6", "\u6211\u4eec", "\u8981", "\u6ce8\u610f"}, - []string{"\u4e00\u4e2a", "\u5206\u5b50", "\u662f", "\u7531", "\u597d\u591a", "\u539f\u5b50", "\u7ec4\u7ec7", "\u6210", "\u7684"}, - []string{"\u795d", "\u4f60", "\u9a6c\u5230\u529f\u6210"}, - []string{"\u4ed6", "\u6389", "\u8fdb", "\u4e86", "\u65e0\u5e95\u6d1e", "\u91cc"}, - []string{"\u4e2d\u56fd", "\u7684", "\u9996\u90fd", "\u662f", "\u5317\u4eac"}, - []string{"\u5b59\u541b\u610f"}, - []string{"\u5916\u4ea4\u90e8", "\u53d1\u8a00\u4eba", "\u9a6c\u671d\u65ed"}, - []string{"\u9886\u5bfc\u4eba", "\u4f1a\u8bae", "\u548c", "\u7b2c\u56db\u5c4a", "\u4e1c\u4e9a", "\u5cf0\u4f1a"}, - []string{"\u5728", "\u8fc7\u53bb", "\u7684", "\u8fd9", "\u4e94\u5e74"}, - []string{"\u8fd8", "\u9700\u8981", "\u5f88\u957f", "\u7684", "\u8def", "\u8981", "\u8d70"}, - []string{"60", "\u5468\u5e74", "\u9996\u90fd", "\u9605\u5175"}, - []string{"\u4f60\u597d", "\u4eba\u4eec", "\u5ba1\u7f8e", "\u7684", "\u89c2\u70b9", "\u662f", "\u4e0d\u540c", "\u7684"}, - []string{"\u4e70", "\u6c34\u679c", "\u7136\u540e", "\u6765", "\u4e16\u535a\u56ed"}, - []string{"\u4e70", "\u6c34\u679c", "\u7136\u540e", "\u53bb", "\u4e16\u535a\u56ed"}, - []string{"\u4f46\u662f", "\u540e\u6765", "\u6211", "\u624d", "\u77e5\u9053", "\u4f60", "\u662f", "\u5bf9", "\u7684"}, - []string{"\u5b58\u5728", "\u5373", "\u5408\u7406"}, - []string{"\u7684", "\u7684", "\u7684", "\u7684", "\u7684", "\u5728", "\u7684", "\u7684", "\u7684", "\u7684", "\u5c31", "\u4ee5", "\u548c", "\u548c", "\u548c"}, - []string{"I", " ", "love", "\u4f60", "\uff0c", "\u4e0d\u4ee5\u4e3a\u803b", "\uff0c", "\u53cd", "\u4ee5\u4e3a", "rong"}, - []string{"\u56e0"}, + []string{"隐", "马尔可夫"}, + []string{"雷猴", "是", "个", "好", "网站"}, + []string{"“", "Microsoft", "”", "一词", "由", "“", "MICROcomputer", "(", "微型", "计算机", ")", "”", "和", "“", "SOFTware", "(", "软件", ")", "”", "两", "部分", "组成"}, + []string{"草泥马", "和", "欺实", "马", "是", "今年", "的", "流行", "词汇"}, + []string{"伊藤", "洋华堂", "总府", "店"}, + []string{"中国科学院计算技术研究所"}, + []string{"罗密欧", "与", "朱丽叶"}, + []string{"我", "购买", "了", "道具", "和", "服装"}, + []string{"PS", ":", " ", "我", "觉得", "开源", "有", "一个", "好处", ",", "就是", "能够", "敦促", "自己", "不断改进", ",", "避免", "敞帚", "自珍"}, + []string{"湖北省", "石首市"}, + []string{"湖北省", "十堰市"}, + []string{"总经理", "完成", "了", "这件", "事情"}, + []string{"电脑", "修好", "了"}, + []string{"做好", "了", "这件", "事情", "就", "一了百了", "了"}, + []string{"人们", "审美", "的", "观点", "是", "不同", "的"}, + []string{"我们", "买", "了", "一个", "美的", "空调"}, + []string{"线程", "初始化", "时", "我们", "要", "注意"}, + []string{"一个", "分子", "是", "由", "好多", "原子", "组织", "成", "的"}, + []string{"祝", "你", "马到功成"}, + []string{"他", "掉", "进", "了", "无底洞", "里"}, + []string{"中国", "的", "首都", "是", "北京"}, + []string{"孙君意"}, + []string{"外交部", "发言人", "马朝旭"}, + []string{"领导人", "会议", "和", "第四届", "东亚", "峰会"}, + []string{"在", "过去", "的", "这", "五年"}, + []string{"还", "需要", "很长", "的", "路", "要", "走"}, + []string{"60", "周年", "首都", "阅兵"}, + []string{"你好", "人们", "审美", "的", "观点", "是", "不同", "的"}, + []string{"买", "水果", "然后", "来", "世博园"}, + []string{"买", "水果", "然后", "去", "世博园"}, + []string{"但是", "后来", "我", "才", "知道", "你", "是", "对", "的"}, + []string{"存在", "即", "合理"}, + []string{"的", "的", "的", "的", "的", "在", "的", "的", "的", "的", "就", "以", "和", "和", "和"}, + []string{"I", " ", "love", "你", ",", "不以为耻", ",", "反", "以为", "rong"}, + []string{"因"}, []string{}, - []string{"hello", "\u4f60\u597d", "\u4eba\u4eec", "\u5ba1\u7f8e", "\u7684", "\u89c2\u70b9", "\u662f", "\u4e0d\u540c", "\u7684"}, - []string{"\u5f88", "\u597d", "\u4f46", "\u4e3b\u8981", "\u662f", "\u57fa\u4e8e", "\u7f51\u9875", "\u5f62\u5f0f"}, - []string{"hello", "\u4f60\u597d", "\u4eba\u4eec", "\u5ba1\u7f8e", "\u7684", "\u89c2\u70b9", "\u662f", "\u4e0d\u540c", "\u7684"}, - []string{"\u4e3a\u4ec0\u4e48", "\u6211", "\u4e0d\u80fd", "\u62e5\u6709", "\u60f3\u8981", "\u7684", "\u751f\u6d3b"}, - []string{"\u540e\u6765", "\u6211", "\u624d"}, - []string{"\u6b64\u6b21", "\u6765", "\u4e2d\u56fd", "\u662f", "\u4e3a\u4e86"}, - []string{"\u4f7f\u7528", "\u4e86", "\u5b83", "\u5c31", "\u53ef\u4ee5", "\u89e3\u51b3", "\u4e00\u4e9b", "\u95ee\u9898"}, - []string{",", "\u4f7f\u7528", "\u4e86", "\u5b83", "\u5c31", "\u53ef\u4ee5", "\u89e3\u51b3", "\u4e00\u4e9b", "\u95ee\u9898"}, - []string{"\u5176\u5b9e", "\u4f7f\u7528", "\u4e86", "\u5b83", "\u5c31", "\u53ef\u4ee5", "\u89e3\u51b3", "\u4e00\u4e9b", "\u95ee\u9898"}, - []string{"\u597d\u4eba", "\u4f7f\u7528", "\u4e86", "\u5b83", "\u5c31", "\u53ef\u4ee5", "\u89e3\u51b3", "\u4e00\u4e9b", "\u95ee\u9898"}, - []string{"\u662f\u56e0\u4e3a", "\u548c", "\u56fd\u5bb6"}, - []string{"\u8001\u5e74", "\u641c\u7d22", "\u8fd8", "\u652f\u6301"}, - []string{"\u5e72\u8106", "\u5c31", "\u628a", "\u90a3\u90e8", "\u8499\u4eba", "\u7684", "\u95f2\u6cd5", "\u7ed9", "\u5e9f", "\u4e86", "\u62c9\u5012", "\uff01", "RT", " ", "@", "laoshipukong", " ", ":", " ", "27", "\u65e5", "\uff0c", "\u5168\u56fd\u4eba\u5927\u5e38\u59d4\u4f1a", "\u7b2c\u4e09\u6b21", "\u5ba1\u8bae", "\u4fb5\u6743", "\u8d23\u4efb\u6cd5", "\u8349\u6848", "\uff0c", "\u5220\u9664", "\u4e86", "\u6709\u5173", "\u533b\u7597", "\u635f\u5bb3", "\u8d23\u4efb", "\u201c", "\u4e3e\u8bc1", "\u5012\u7f6e", "\u201d", "\u7684", "\u89c4\u5b9a", "\u3002", "\u5728", "\u533b\u60a3", "\u7ea0\u7eb7", "\u4e2d\u672c", "\u5df2", "\u5904\u4e8e", "\u5f31\u52bf", "\u5730\u4f4d", "\u7684", "\u6d88\u8d39\u8005", "\u7531\u6b64", "\u5c06", "\u9677\u5165", "\u4e07\u52ab\u4e0d\u590d", "\u7684", "\u5883\u5730", "\u3002", " "}, - []string{"\u5927"}, + []string{"hello", "你好", "人们", "审美", "的", "观点", "是", "不同", "的"}, + []string{"很", "好", "但", "主要", "是", "基于", "网页", "形式"}, + []string{"hello", "你好", "人们", "审美", "的", "观点", "是", "不同", "的"}, + []string{"为什么", "我", "不能", "拥有", "想要", "的", "生活"}, + []string{"后来", "我", "才"}, + []string{"此次", "来", "中国", "是", "为了"}, + []string{"使用", "了", "它", "就", "可以", "解决", "一些", "问题"}, + []string{",", "使用", "了", "它", "就", "可以", "解决", "一些", "问题"}, + []string{"其实", "使用", "了", "它", "就", "可以", "解决", "一些", "问题"}, + []string{"好人", "使用", "了", "它", "就", "可以", "解决", "一些", "问题"}, + []string{"是因为", "和", "国家"}, + []string{"老年", "搜索", "还", "支持"}, + []string{"干脆", "就", "把", "那部", "蒙人", "的", "闲法", "给", "废", "了", "拉倒", "!", "RT", " ", "@", "laoshipukong", " ", ":", " ", "27", "日", ",", "全国人大常委会", "第三次", "审议", "侵权", "责任法", "草案", ",", "删除", "了", "有关", "医疗", "损害", "责任", "“", "举证", "倒置", "”", "的", "规定", "。", "在", "医患", "纠纷", "中本", "已", "处于", "弱势", "地位", "的", "消费者", "由此", "将", "陷入", "万劫不复", "的", "境地", "。", " "}, + []string{"大"}, []string{}, - []string{"\u4ed6", "\u8bf4", "\u7684", "\u786e\u5b9e", "\u5728\u7406"}, - []string{"\u957f\u6625", "\u5e02\u957f", "\u6625\u8282", "\u8bb2\u8bdd"}, - []string{"\u7ed3\u5a5a", "\u7684", "\u548c", "\u5c1a\u672a", "\u7ed3\u5a5a", "\u7684"}, - []string{"\u7ed3\u5408", "\u6210", "\u5206\u5b50", "\u65f6"}, - []string{"\u65c5\u6e38", "\u548c", "\u670d\u52a1", "\u662f", "\u6700\u597d", "\u7684"}, - []string{"\u8fd9\u4ef6", "\u4e8b\u60c5", "\u7684\u786e", "\u662f", "\u6211", "\u7684", "\u9519"}, - []string{"\u4f9b", "\u5927\u5bb6", "\u53c2\u8003", "\u6307\u6b63"}, - []string{"\u54c8\u5c14\u6ee8", "\u653f\u5e9c", "\u516c\u5e03", "\u584c\u6865", "\u539f\u56e0"}, - []string{"\u6211", "\u5728", "\u673a\u573a", "\u5165\u53e3\u5904"}, - []string{"\u90a2\u6c38\u81e3", "\u6444\u5f71", "\u62a5\u9053"}, - []string{"BP", "\u795e\u7ecf\u7f51\u7edc", "\u5982\u4f55", "\u8bad\u7ec3", "\u624d\u80fd", "\u5728", "\u5206\u7c7b", "\u65f6", "\u589e\u52a0", "\u533a\u5206\u5ea6", "\uff1f"}, - []string{"\u5357\u4eac\u5e02", "\u957f\u6c5f\u5927\u6865"}, - []string{"\u5e94", "\u4e00\u4e9b", "\u4f7f\u7528\u8005", "\u7684", "\u5efa\u8bae", "\uff0c", "\u4e5f", "\u4e3a\u4e86", "\u4fbf\u4e8e", "\u5229\u7528", "NiuTrans", "\u7528\u4e8e", "SMT", "\u7814\u7a76"}, - []string{"\u957f\u6625\u5e02", "\u957f\u6625", "\u836f\u5e97"}, - []string{"\u9093\u9896\u8d85", "\u751f\u524d", "\u6700", "\u559c\u6b22", "\u7684", "\u8863\u670d"}, - []string{"\u80e1\u9526\u6d9b", "\u662f", "\u70ed\u7231", "\u4e16\u754c", "\u548c\u5e73", "\u7684", "\u653f\u6cbb\u5c40", "\u5e38\u59d4"}, - []string{"\u7a0b\u5e8f\u5458", "\u795d", "\u6d77\u6797", "\u548c", "\u6731\u4f1a\u9707", "\u662f", "\u5728", "\u5b59\u5065", "\u7684", "\u5de6\u9762", "\u548c", "\u53f3\u9762", ",", " ", "\u8303\u51ef", "\u5728", "\u6700", "\u53f3\u9762", ".", "\u518d\u5f80", "\u5de6", "\u662f", "\u674e\u677e\u6d2a"}, - []string{"\u4e00\u6b21\u6027", "\u4ea4", "\u591a\u5c11", "\u94b1"}, - []string{"\u4e24\u5757", "\u4e94", "\u4e00\u5957", "\uff0c", "\u4e09\u5757", "\u516b", "\u4e00\u65a4", "\uff0c", "\u56db\u5757", "\u4e03", "\u4e00\u672c", "\uff0c", "\u4e94\u5757", "\u516d", "\u4e00\u6761"}, - []string{"\u5c0f", "\u548c\u5c1a", "\u7559", "\u4e86", "\u4e00\u4e2a", "\u50cf", "\u5927", "\u548c\u5c1a", "\u4e00\u6837", "\u7684", "\u548c\u5c1a\u5934"}, - []string{"\u6211", "\u662f", "\u4e2d\u534e\u4eba\u6c11\u5171\u548c\u56fd", "\u516c\u6c11", ";", "\u6211", "\u7238\u7238", "\u662f", "\u5171\u548c\u515a", "\u515a\u5458", ";", " ", "\u5730\u94c1", "\u548c\u5e73\u95e8", "\u7ad9"}, - []string{"\u5f20\u6653\u6885", "\u53bb", "\u4eba\u6c11", "\u533b\u9662", "\u505a", "\u4e86", "\u4e2a", "B\u8d85", "\u7136\u540e", "\u53bb", "\u4e70", "\u4e86", "\u4ef6", "T\u6064"}, - []string{"AT&T", "\u662f", "\u4e00\u4ef6", "\u4e0d\u9519", "\u7684", "\u516c\u53f8", "\uff0c", "\u7ed9", "\u4f60", "\u53d1", "offer", "\u4e86", "\u5417", "\uff1f"}, - []string{"C++", "\u548c", "c#", "\u662f", "\u4ec0\u4e48", "\u5173\u7cfb", "\uff1f", "11", "+", "122", "=", "133", "\uff0c", "\u662f", "\u5417", "\uff1f", "PI", "=", "3.14159"}, - []string{"\u4f60", "\u8ba4\u8bc6", "\u90a3\u4e2a", "\u548c", "\u4e3b\u5e2d", "\u63e1\u624b", "\u7684", "\u7684\u54e5", "\u5417", "\uff1f", "\u4ed6\u5f00", "\u4e00\u8f86", "\u9ed1\u8272", "\u7684\u58eb", "\u3002"}, - []string{"\u67aa\u6746\u5b50", "\u4e2d", "\u51fa", "\u653f\u6743"}, + []string{"他", "说", "的", "确实", "在理"}, + []string{"长春", "市长", "春节", "讲话"}, + []string{"结婚", "的", "和", "尚未", "结婚", "的"}, + []string{"结合", "成", "分子", "时"}, + []string{"旅游", "和", "服务", "是", "最好", "的"}, + []string{"这件", "事情", "的确", "是", "我", "的", "错"}, + []string{"供", "大家", "参考", "指正"}, + []string{"哈尔滨", "政府", "公布", "塌桥", "原因"}, + []string{"我", "在", "机场", "入口处"}, + []string{"邢永臣", "摄影", "报道"}, + []string{"BP", "神经网络", "如何", "训练", "才能", "在", "分类", "时", "增加", "区分度", "?"}, + []string{"南京市", "长江大桥"}, + []string{"应", "一些", "使用者", "的", "建议", ",", "也", "为了", "便于", "利用", "NiuTrans", "用于", "SMT", "研究"}, + []string{"长春市", "长春", "药店"}, + []string{"邓颖超", "生前", "最", "喜欢", "的", "衣服"}, + []string{"胡锦涛", "是", "热爱", "世界", "和平", "的", "政治局", "常委"}, + []string{"程序员", "祝", "海林", "和", "朱会震", "是", "在", "孙健", "的", "左面", "和", "右面", ",", " ", "范凯", "在", "最", "右面", ".", "再往", "左", "是", "李松洪"}, + []string{"一次性", "交", "多少", "钱"}, + []string{"两块", "五", "一套", ",", "三块", "八", "一斤", ",", "四块", "七", "一本", ",", "五块", "六", "一条"}, + []string{"小", "和尚", "留", "了", "一个", "像", "大", "和尚", "一样", "的", "和尚头"}, + []string{"我", "是", "中华人民共和国", "公民", ";", "我", "爸爸", "是", "共和党", "党员", ";", " ", "地铁", "和平门", "站"}, + []string{"张晓梅", "去", "人民", "医院", "做", "了", "个", "B超", "然后", "去", "买", "了", "件", "T恤"}, + []string{"AT&T", "是", "一件", "不错", "的", "公司", ",", "给", "你", "发", "offer", "了", "吗", "?"}, + []string{"C++", "和", "c#", "是", "什么", "关系", "?", "11", "+", "122", "=", "133", ",", "是", "吗", "?", "PI", "=", "3.14159"}, + []string{"你", "认识", "那个", "和", "主席", "握手", "的", "的哥", "吗", "?", "他开", "一辆", "黑色", "的士", "。"}, + []string{"枪杆子", "中", "出", "政权"}, } - cutAllResult = [][]string{ - []string{"\u8fd9", "\u662f", "\u4e00\u4e2a", "\u4f38\u624b", "\u4f38\u624b\u4e0d\u89c1", "\u4f38\u624b\u4e0d\u89c1\u4e94\u6307", "\u4e0d\u89c1", "\u4e94\u6307", "\u7684", "\u9ed1\u591c", "", "", "\u6211", "\u53eb", "\u5b59\u609f\u7a7a", "\u609f\u7a7a", "", "", "\u6211", "\u7231", "\u5317\u4eac", "", "", "\u6211", "\u7231", "Python", "\u548c", "C++", ""}, - []string{"\u6211", "\u4e0d", "\u559c\u6b22", "\u65e5\u672c", "\u548c\u670d", "", ""}, - []string{"\u96f7\u7334", "\u56de\u5f52", "\u4eba\u95f4", "", ""}, - []string{"\u5de5\u4fe1\u5904", "\u5904\u5973", "\u5973\u5e72\u4e8b", "\u5e72\u4e8b", "\u6bcf\u6708", "\u6708\u7ecf", "\u7ecf\u8fc7", "\u4e0b\u5c5e", "\u79d1\u5ba4", "\u90fd", "\u8981", "\u4eb2\u53e3", "\u53e3\u4ea4", "\u4ea4\u4ee3", "24", "\u53e3\u4ea4", "\u4ea4\u6362", "\u4ea4\u6362\u673a", "\u6362\u673a", "\u7b49", "\u6280\u672f", "\u6280\u672f\u6027", "\u6027\u5668", "\u5668\u4ef6", "\u7684", "\u5b89\u88c5", "\u5b89\u88c5\u5de5", "\u88c5\u5de5", "\u5de5\u4f5c"}, - []string{"\u6211", "\u9700\u8981", "\u5ec9\u79df", "\u5ec9\u79df\u623f", "\u79df\u623f"}, - []string{"\u6c38\u548c", "\u548c\u670d", "\u670d\u88c5", "\u88c5\u9970", "\u88c5\u9970\u54c1", "\u9970\u54c1", "\u6709\u9650", "\u6709\u9650\u516c\u53f8", "\u516c\u53f8"}, - []string{"\u6211", "\u7231", "\u5317\u4eac", "\u5929\u5b89", "\u5929\u5b89\u95e8"}, + cutAllResult = [][]string{[]string{"这", "是", "一个", "伸手", "伸手不见", "伸手不见五指", "不见", "五指", "的", "黑夜", "", "", "我", "叫", "孙悟空", "悟空", "", "", "我", "爱", "北京", "", "", "我", "爱", "Python", "和", "C++", ""}, + []string{"我", "不", "喜欢", "日本", "和服", "", ""}, + []string{"雷猴", "回归", "人间", "", ""}, + []string{"工信处", "处女", "女干事", "干事", "每月", "月经", "经过", "下属", "科室", "都", "要", "亲口", "口交", "交代", "24", "口交", "交换", "交换机", "换机", "等", "技术", "技术性", "性器", "器件", "的", "安装", "安装工", "装工", "工作"}, + []string{"我", "需要", "廉租", "廉租房", "租房"}, + []string{"永和", "和服", "服装", "装饰", "装饰品", "饰品", "有限", "有限公司", "公司"}, + []string{"我", "爱", "北京", "天安", "天安门"}, []string{"abc"}, - []string{"\u9690", "\u9a6c\u5c14\u53ef", "\u9a6c\u5c14\u53ef\u592b", "\u53ef\u592b"}, - []string{"\u96f7\u7334", "\u662f", "\u4e2a", "\u597d", "\u7f51\u7ad9"}, - []string{"", "Microsoft", "", "\u4e00", "\u8bcd", "\u7531", "", "MICROcomputer", "", "\u5fae\u578b", "\u8ba1\u7b97", "\u8ba1\u7b97\u673a", "\u7b97\u673a", "", "", "", "\u548c", "", "SOFTware", "", "\u8f6f\u4ef6", "", "", "", "\u4e24\u90e8", "\u90e8\u5206", "\u5206\u7ec4", "\u7ec4\u6210"}, - []string{"\u8349\u6ce5\u9a6c", "\u548c", "\u6b3a", "\u5b9e", "\u9a6c", "\u662f", "\u4eca\u5e74", "\u7684", "\u6d41\u884c", "\u8bcd\u6c47"}, - []string{"\u4f0a", "\u85e4", "\u6d0b\u534e\u5802", "\u603b\u5e9c", "\u5e97"}, - []string{"\u4e2d\u56fd", "\u4e2d\u56fd\u79d1\u5b66\u9662", "\u4e2d\u56fd\u79d1\u5b66\u9662\u8ba1\u7b97\u6280\u672f\u7814\u7a76\u6240", "\u79d1\u5b66", "\u79d1\u5b66\u9662", "\u5b66\u9662", "\u8ba1\u7b97", "\u8ba1\u7b97\u6280\u672f", "\u6280\u672f", "\u7814\u7a76", "\u7814\u7a76\u6240"}, - []string{"\u7f57\u5bc6\u6b27", "\u4e0e", "\u6731\u4e3d\u53f6"}, - []string{"\u6211", "\u8d2d\u4e70", "\u4e86", "\u9053\u5177", "\u548c\u670d", "\u670d\u88c5"}, - []string{"PS", "", "", "\u6211", "\u89c9\u5f97", "\u5f00\u6e90", "\u6709", "\u4e00\u4e2a", "\u597d\u5904", "", "", "\u5c31\u662f", "\u80fd\u591f", "\u6566\u4fc3", "\u81ea\u5df1", "\u4e0d\u65ad", "\u4e0d\u65ad\u6539\u8fdb", "\u6539\u8fdb", "", "", "\u907f\u514d", "\u655e", "\u5e1a", "\u81ea\u73cd"}, - []string{"\u6e56\u5317", "\u6e56\u5317\u7701", "\u77f3\u9996", "\u77f3\u9996\u5e02"}, - []string{"\u6e56\u5317", "\u6e56\u5317\u7701", "\u5341\u5830", "\u5341\u5830\u5e02"}, - []string{"\u603b\u7ecf\u7406", "\u7ecf\u7406", "\u7406\u5b8c", "\u5b8c\u6210", "\u4e86", "\u8fd9\u4ef6", "\u4e8b\u60c5"}, - []string{"\u7535\u8111", "\u4fee\u597d", "\u4e86"}, - []string{"\u505a\u597d", "\u4e86", "\u8fd9\u4ef6", "\u4e8b\u60c5", "\u5c31", "\u4e00\u4e86\u767e\u4e86", "\u4e86\u4e86"}, - []string{"\u4eba\u4eec", "\u5ba1\u7f8e", "\u7f8e\u7684", "\u89c2\u70b9", "\u662f", "\u4e0d\u540c", "\u7684"}, - []string{"\u6211\u4eec", "\u4e70", "\u4e86", "\u4e00\u4e2a", "\u7f8e\u7684", "\u7a7a\u8c03"}, - []string{"\u7ebf\u7a0b", "\u521d\u59cb", "\u521d\u59cb\u5316", "\u5316\u65f6", "\u6211\u4eec", "\u8981", "\u6ce8\u610f"}, - []string{"\u4e00\u4e2a", "\u5206\u5b50", "\u662f", "\u7531", "\u597d\u591a", "\u539f\u5b50", "\u7ec4\u7ec7", "\u7ec7\u6210", "\u7684"}, - []string{"\u795d", "\u4f60", "\u9a6c\u5230\u529f\u6210"}, - []string{"\u4ed6", "\u6389", "\u8fdb", "\u4e86", "\u65e0\u5e95", "\u65e0\u5e95\u6d1e", "\u91cc"}, - []string{"\u4e2d\u56fd", "\u7684", "\u9996\u90fd", "\u662f", "\u5317\u4eac"}, - []string{"\u5b59", "\u541b", "\u610f"}, - []string{"\u5916\u4ea4", "\u5916\u4ea4\u90e8", "\u90e8\u53d1", "\u53d1\u8a00", "\u53d1\u8a00\u4eba", "\u4eba\u9a6c", "\u9a6c\u671d\u65ed"}, - []string{"\u9886\u5bfc", "\u9886\u5bfc\u4eba", "\u4f1a\u8bae", "\u8bae\u548c", "\u7b2c\u56db", "\u7b2c\u56db\u5c4a", "\u56db\u5c4a", "\u4e1c\u4e9a", "\u5cf0\u4f1a"}, - []string{"\u5728", "\u8fc7\u53bb", "\u7684", "\u8fd9", "\u4e94\u5e74"}, - []string{"\u8fd8", "\u9700\u8981", "\u5f88", "\u957f", "\u7684", "\u8def", "\u8981", "\u8d70"}, - []string{"60", "\u5468\u5e74", "\u9996\u90fd", "\u9605\u5175"}, - []string{"\u4f60\u597d", "\u597d\u4eba", "\u4eba\u4eec", "\u5ba1\u7f8e", "\u7f8e\u7684", "\u89c2\u70b9", "\u662f", "\u4e0d\u540c", "\u7684"}, - []string{"\u4e70", "\u6c34\u679c", "\u679c\u7136", "\u7136\u540e", "\u540e\u6765", "\u6765\u4e16", "\u4e16\u535a", "\u4e16\u535a\u56ed", "\u535a\u56ed"}, - []string{"\u4e70", "\u6c34\u679c", "\u679c\u7136", "\u7136\u540e", "\u540e\u53bb", "\u53bb\u4e16", "\u4e16\u535a", "\u4e16\u535a\u56ed", "\u535a\u56ed"}, - []string{"\u4f46\u662f", "\u540e\u6765", "\u6211", "\u624d", "\u77e5\u9053", "\u4f60", "\u662f", "\u5bf9", "\u7684"}, - []string{"\u5b58\u5728", "\u5373", "\u5408\u7406"}, - []string{"\u7684", "\u7684", "\u7684", "\u7684", "\u7684", "\u5728", "\u7684", "\u7684", "\u7684", "\u7684", "\u5c31", "\u4ee5", "\u548c", "\u548c", "\u548c"}, - []string{"I", "love", "\u4f60", "", "", "\u4e0d\u4ee5", "\u4e0d\u4ee5\u4e3a\u803b", "\u4ee5\u4e3a", "\u803b", "", "", "\u53cd", "\u4ee5\u4e3a", "rong"}, - []string{"\u56e0"}, + []string{"隐", "马尔可", "马尔可夫", "可夫"}, + []string{"雷猴", "是", "个", "好", "网站"}, + []string{"", "Microsoft", "", "一", "词", "由", "", "MICROcomputer", "", "微型", "计算", "计算机", "算机", "", "", "", "和", "", "SOFTware", "", "软件", "", "", "", "两部", "部分", "分组", "组成"}, + []string{"草泥马", "和", "欺", "实", "马", "是", "今年", "的", "流行", "词汇"}, + []string{"伊", "藤", "洋华堂", "总府", "店"}, + []string{"中国", "中国科学院", "中国科学院计算技术研究所", "科学", "科学院", "学院", "计算", "计算技术", "技术", "研究", "研究所"}, + []string{"罗密欧", "与", "朱丽叶"}, + []string{"我", "购买", "了", "道具", "和服", "服装"}, + []string{"PS", "", "", "我", "觉得", "开源", "有", "一个", "好处", "", "", "就是", "能够", "敦促", "自己", "不断", "不断改进", "改进", "", "", "避免", "敞", "帚", "自珍"}, + []string{"湖北", "湖北省", "石首", "石首市"}, + []string{"湖北", "湖北省", "十堰", "十堰市"}, + []string{"总经理", "经理", "理完", "完成", "了", "这件", "事情"}, + []string{"电脑", "修好", "了"}, + []string{"做好", "了", "这件", "事情", "就", "一了百了", "了了"}, + []string{"人们", "审美", "美的", "观点", "是", "不同", "的"}, + []string{"我们", "买", "了", "一个", "美的", "空调"}, + []string{"线程", "初始", "初始化", "化时", "我们", "要", "注意"}, + []string{"一个", "分子", "是", "由", "好多", "原子", "组织", "织成", "的"}, + []string{"祝", "你", "马到功成"}, + []string{"他", "掉", "进", "了", "无底", "无底洞", "里"}, + []string{"中国", "的", "首都", "是", "北京"}, + []string{"孙", "君", "意"}, + []string{"外交", "外交部", "部发", "发言", "发言人", "人马", "马朝旭"}, + []string{"领导", "领导人", "会议", "议和", "第四", "第四届", "四届", "东亚", "峰会"}, + []string{"在", "过去", "的", "这", "五年"}, + []string{"还", "需要", "很", "长", "的", "路", "要", "走"}, + []string{"60", "周年", "首都", "阅兵"}, + []string{"你好", "好人", "人们", "审美", "美的", "观点", "是", "不同", "的"}, + []string{"买", "水果", "果然", "然后", "后来", "来世", "世博", "世博园", "博园"}, + []string{"买", "水果", "果然", "然后", "后去", "去世", "世博", "世博园", "博园"}, + []string{"但是", "后来", "我", "才", "知道", "你", "是", "对", "的"}, + []string{"存在", "即", "合理"}, + []string{"的", "的", "的", "的", "的", "在", "的", "的", "的", "的", "就", "以", "和", "和", "和"}, + []string{"I", "love", "你", "", "", "不以", "不以为耻", "以为", "耻", "", "", "反", "以为", "rong"}, + []string{"因"}, []string{}, - []string{"hello", "\u4f60\u597d", "\u597d\u4eba", "\u4eba\u4eec", "\u5ba1\u7f8e", "\u7f8e\u7684", "\u89c2\u70b9", "\u662f", "\u4e0d\u540c", "\u7684"}, - []string{"\u5f88", "\u597d", "\u4f46", "\u4e3b\u8981", "\u8981\u662f", "\u57fa\u4e8e", "\u7f51\u9875", "\u5f62\u5f0f"}, - []string{"hello", "\u4f60\u597d", "\u597d\u4eba", "\u4eba\u4eec", "\u5ba1\u7f8e", "\u7f8e\u7684", "\u89c2\u70b9", "\u662f", "\u4e0d\u540c", "\u7684"}, - []string{"\u4e3a\u4ec0\u4e48", "\u4ec0\u4e48", "\u6211", "\u4e0d\u80fd", "\u62e5\u6709", "\u60f3\u8981", "\u7684", "\u751f\u6d3b"}, - []string{"\u540e\u6765", "\u6211", "\u624d"}, - []string{"\u6b64\u6b21", "\u6765", "\u4e2d\u56fd", "\u56fd\u662f", "\u4e3a\u4e86"}, - []string{"\u4f7f\u7528", "\u4e86", "\u5b83", "\u5c31", "\u53ef\u4ee5", "\u89e3\u51b3", "\u4e00\u4e9b", "\u95ee\u9898"}, - []string{"", "", "\u4f7f\u7528", "\u4e86", "\u5b83", "\u5c31", "\u53ef\u4ee5", "\u89e3\u51b3", "\u4e00\u4e9b", "\u95ee\u9898"}, - []string{"\u5176\u5b9e", "\u4f7f\u7528", "\u4e86", "\u5b83", "\u5c31", "\u53ef\u4ee5", "\u89e3\u51b3", "\u4e00\u4e9b", "\u95ee\u9898"}, - []string{"\u597d\u4eba", "\u4f7f\u7528", "\u4e86", "\u5b83", "\u5c31", "\u53ef\u4ee5", "\u89e3\u51b3", "\u4e00\u4e9b", "\u95ee\u9898"}, - []string{"\u662f\u56e0\u4e3a", "\u56e0\u4e3a", "\u548c", "\u56fd\u5bb6"}, - []string{"\u8001\u5e74", "\u641c\u7d22", "\u7d22\u8fd8", "\u652f\u6301"}, - []string{"\u5e72\u8106", "\u5c31", "\u628a", "\u90a3\u90e8", "\u8499\u4eba", "\u7684", "\u95f2", "\u6cd5", "\u7ed9", "\u5e9f", "\u4e86", "\u62c9\u5012", "", "RT", "", "laoshipukong", "", "", "27", "\u65e5", "", "", "\u5168\u56fd", "\u5168\u56fd\u4eba\u5927", "\u5168\u56fd\u4eba\u5927\u5e38\u59d4\u4f1a", "\u56fd\u4eba", "\u4eba\u5927", "\u4eba\u5927\u5e38\u59d4\u4f1a", "\u5e38\u59d4", "\u5e38\u59d4\u4f1a", "\u59d4\u4f1a", "\u7b2c\u4e09", "\u7b2c\u4e09\u6b21", "\u4e09\u6b21", "\u5ba1\u8bae", "\u4fb5\u6743", "\u6743\u8d23", "\u8d23\u4efb", "\u8d23\u4efb\u6cd5", "\u8349\u6848", "", "", "\u5220\u9664", "\u9664\u4e86", "\u6709\u5173", "\u533b\u7597", "\u635f\u5bb3", "\u8d23\u4efb", "", "", "\u4e3e\u8bc1", "\u5012\u7f6e", "", "", "\u7684", "\u89c4\u5b9a", "", "", "\u5728", "\u533b\u60a3", "\u7ea0\u7eb7", "\u4e2d", "\u672c", "\u5df2", "\u5904\u4e8e", "\u5f31\u52bf", "\u5730\u4f4d", "\u7684", "\u6d88\u8d39", "\u6d88\u8d39\u8005", "\u7531\u6b64", "\u5c06", "\u9677\u5165", "\u4e07\u52ab\u4e0d\u590d", "\u4e0d\u590d", "\u7684", "\u5883\u5730", "", "", ""}, - []string{"\u5927"}, + []string{"hello", "你好", "好人", "人们", "审美", "美的", "观点", "是", "不同", "的"}, + []string{"很", "好", "但", "主要", "要是", "基于", "网页", "形式"}, + []string{"hello", "你好", "好人", "人们", "审美", "美的", "观点", "是", "不同", "的"}, + []string{"为什么", "什么", "我", "不能", "拥有", "想要", "的", "生活"}, + []string{"后来", "我", "才"}, + []string{"此次", "来", "中国", "国是", "为了"}, + []string{"使用", "了", "它", "就", "可以", "解决", "一些", "问题"}, + []string{"", "", "使用", "了", "它", "就", "可以", "解决", "一些", "问题"}, + []string{"其实", "使用", "了", "它", "就", "可以", "解决", "一些", "问题"}, + []string{"好人", "使用", "了", "它", "就", "可以", "解决", "一些", "问题"}, + []string{"是因为", "因为", "和", "国家"}, + []string{"老年", "搜索", "索还", "支持"}, + []string{"干脆", "就", "把", "那部", "蒙人", "的", "闲", "法", "给", "废", "了", "拉倒", "", "RT", "", "laoshipukong", "", "", "27", "日", "", "", "全国", "全国人大", "全国人大常委会", "国人", "人大", "人大常委会", "常委", "常委会", "委会", "第三", "第三次", "三次", "审议", "侵权", "权责", "责任", "责任法", "草案", "", "", "删除", "除了", "有关", "医疗", "损害", "责任", "", "", "举证", "倒置", "", "", "的", "规定", "", "", "在", "医患", "纠纷", "中", "本", "已", "处于", "弱势", "地位", "的", "消费", "消费者", "由此", "将", "陷入", "万劫不复", "不复", "的", "境地", "", "", ""}, + []string{"大"}, []string{}, - []string{"\u4ed6", "\u8bf4", "\u7684\u786e", "\u786e\u5b9e", "\u5b9e\u5728", "\u7406"}, - []string{"\u957f\u6625", "\u957f\u6625\u5e02", "\u5e02\u957f", "\u957f\u6625", "\u6625\u8282", "\u8bb2\u8bdd"}, - []string{"\u7ed3\u5a5a", "\u7684", "\u548c\u5c1a", "\u5c1a\u672a", "\u672a\u7ed3", "\u7ed3\u5a5a", "\u7684"}, - []string{"\u7ed3\u5408", "\u5408\u6210", "\u6210\u5206", "\u5206\u5b50", "\u65f6"}, - []string{"\u65c5\u6e38", "\u548c\u670d", "\u670d\u52a1", "\u662f", "\u6700\u597d", "\u7684"}, - []string{"\u8fd9\u4ef6", "\u4e8b\u60c5", "\u7684\u786e", "\u662f", "\u6211", "\u7684", "\u9519"}, - []string{"\u4f9b", "\u5927\u5bb6", "\u53c2\u8003", "\u6307\u6b63"}, - []string{"\u54c8\u5c14", "\u54c8\u5c14\u6ee8", "\u653f\u5e9c", "\u516c\u5e03", "\u584c", "\u6865", "\u539f\u56e0"}, - []string{"\u6211", "\u5728", "\u673a\u573a", "\u5165\u53e3", "\u5165\u53e3\u5904"}, - []string{"\u90a2", "\u6c38", "\u81e3", "\u6444\u5f71", "\u62a5\u9053"}, - []string{"BP", "\u795e\u7ecf", "\u795e\u7ecf\u7f51", "\u795e\u7ecf\u7f51\u7edc", "\u7f51\u7edc", "\u5982\u4f55", "\u8bad\u7ec3", "\u624d\u80fd", "\u5728", "\u5206\u7c7b", "\u65f6", "\u589e\u52a0", "\u52a0\u533a", "\u533a\u5206", "\u533a\u5206\u5ea6", "\u5206\u5ea6", "", ""}, - []string{"\u5357\u4eac", "\u5357\u4eac\u5e02", "\u4eac\u5e02", "\u5e02\u957f", "\u957f\u6c5f", "\u957f\u6c5f\u5927\u6865", "\u5927\u6865"}, - []string{"\u5e94", "\u4e00\u4e9b", "\u4f7f\u7528", "\u4f7f\u7528\u8005", "\u7528\u8005", "\u7684", "\u5efa\u8bae", "", "", "\u4e5f", "\u4e3a\u4e86", "\u4fbf\u4e8e", "\u5229\u7528", "NiuTrans", "\u7528\u4e8e", "SMT", "\u7814\u7a76"}, - []string{"\u957f\u6625", "\u957f\u6625\u5e02", "\u5e02\u957f", "\u957f\u6625", "\u6625\u836f", "\u836f\u5e97"}, - []string{"\u9093\u9896\u8d85", "\u8d85\u751f", "\u751f\u524d", "\u6700", "\u559c\u6b22", "\u7684", "\u8863\u670d"}, - []string{"\u80e1\u9526\u6d9b", "\u9526\u6d9b", "\u662f", "\u70ed\u7231", "\u4e16\u754c", "\u548c\u5e73", "\u7684", "\u653f\u6cbb", "\u653f\u6cbb\u5c40", "\u5e38\u59d4"}, - []string{"\u7a0b\u5e8f", "\u7a0b\u5e8f\u5458", "\u795d", "\u6d77\u6797", "\u548c", "\u6731", "\u4f1a", "\u9707", "\u662f", "\u5728", "\u5b59", "\u5065", "\u7684", "\u5de6\u9762", "\u548c", "\u53f3\u9762", "", "", "", "\u8303", "\u51ef", "\u5728", "\u6700", "\u53f3\u9762", "", "", "\u518d\u5f80", "\u5de6", "\u662f", "\u674e", "\u677e", "\u6d2a"}, - []string{"\u4e00\u6b21", "\u4e00\u6b21\u6027", "\u6027\u4ea4", "\u591a\u5c11", "\u591a\u5c11\u94b1"}, - []string{"\u4e24\u5757", "\u4e94\u4e00", "\u4e00\u5957", "", "", "\u4e09\u5757", "\u516b\u4e00", "\u4e00\u65a4", "", "", "\u56db\u5757", "\u4e03\u4e00", "\u4e00\u672c", "", "", "\u4e94\u5757", "\u516d\u4e00", "\u4e00\u6761"}, - []string{"\u5c0f", "\u548c\u5c1a", "\u7559", "\u4e86", "\u4e00\u4e2a", "\u50cf", "\u5927", "\u548c\u5c1a", "\u4e00\u6837", "\u7684", "\u548c\u5c1a", "\u548c\u5c1a\u5934"}, - []string{"\u6211", "\u662f", "\u4e2d\u534e", "\u4e2d\u534e\u4eba\u6c11", "\u4e2d\u534e\u4eba\u6c11\u5171\u548c\u56fd", "\u534e\u4eba", "\u4eba\u6c11", "\u4eba\u6c11\u5171\u548c\u56fd", "\u5171\u548c", "\u5171\u548c\u56fd", "\u56fd\u516c", "\u516c\u6c11", "", "", "\u6211", "\u7238\u7238", "\u662f", "\u5171\u548c", "\u5171\u548c\u515a", "\u515a\u5458", "", "", "", "\u5730\u94c1", "\u548c\u5e73", "\u548c\u5e73\u95e8", "\u7ad9"}, - []string{"\u5f20\u6653\u6885", "\u53bb", "\u4eba\u6c11", "\u6c11\u533b\u9662", "\u533b\u9662", "\u505a", "\u4e86", "\u4e2a", "B", "\u8d85\u7136", "\u7136\u540e", "\u540e\u53bb", "\u4e70", "\u4e86", "\u4ef6", "T", "\u6064"}, - []string{"AT", "T", "\u662f", "\u4e00\u4ef6", "\u4e0d\u9519", "\u7684", "\u516c\u53f8", "", "", "\u7ed9", "\u4f60", "\u53d1", "offer", "\u4e86", "\u5417", "", ""}, - []string{"C++", "\u548c", "c#", "\u662f", "\u4ec0\u4e48", "\u5173\u7cfb", "", "11+122", "133", "", "\u662f", "\u5417", "", "PI", "3", "14159"}, - []string{"\u4f60", "\u8ba4\u8bc6", "\u90a3\u4e2a", "\u548c", "\u4e3b\u5e2d", "\u63e1\u624b", "\u7684", "\u7684\u54e5", "\u5417", "", "", "\u4ed6", "\u5f00", "\u4e00\u8f86", "\u9ed1\u8272", "\u7684\u58eb", "", ""}, - []string{"\u67aa\u6746", "\u67aa\u6746\u5b50", "\u6746\u5b50", "\u4e2d\u51fa", "\u653f\u6743"}, + []string{"他", "说", "的确", "确实", "实在", "理"}, + []string{"长春", "长春市", "市长", "长春", "春节", "讲话"}, + []string{"结婚", "的", "和尚", "尚未", "未结", "结婚", "的"}, + []string{"结合", "合成", "成分", "分子", "时"}, + []string{"旅游", "和服", "服务", "是", "最好", "的"}, + []string{"这件", "事情", "的确", "是", "我", "的", "错"}, + []string{"供", "大家", "参考", "指正"}, + []string{"哈尔", "哈尔滨", "政府", "公布", "塌", "桥", "原因"}, + []string{"我", "在", "机场", "入口", "入口处"}, + []string{"邢", "永", "臣", "摄影", "报道"}, + []string{"BP", "神经", "神经网", "神经网络", "网络", "如何", "训练", "才能", "在", "分类", "时", "增加", "加区", "区分", "区分度", "分度", "", ""}, + []string{"南京", "南京市", "京市", "市长", "长江", "长江大桥", "大桥"}, + []string{"应", "一些", "使用", "使用者", "用者", "的", "建议", "", "", "也", "为了", "便于", "利用", "NiuTrans", "用于", "SMT", "研究"}, + []string{"长春", "长春市", "市长", "长春", "春药", "药店"}, + []string{"邓颖超", "超生", "生前", "最", "喜欢", "的", "衣服"}, + []string{"胡锦涛", "锦涛", "是", "热爱", "世界", "和平", "的", "政治", "政治局", "常委"}, + []string{"程序", "程序员", "祝", "海林", "和", "朱", "会", "震", "是", "在", "孙", "健", "的", "左面", "和", "右面", "", "", "", "范", "凯", "在", "最", "右面", "", "", "再往", "左", "是", "李", "松", "洪"}, + []string{"一次", "一次性", "性交", "多少", "多少钱"}, + []string{"两块", "五一", "一套", "", "", "三块", "八一", "一斤", "", "", "四块", "七一", "一本", "", "", "五块", "六一", "一条"}, + []string{"小", "和尚", "留", "了", "一个", "像", "大", "和尚", "一样", "的", "和尚", "和尚头"}, + []string{"我", "是", "中华", "中华人民", "中华人民共和国", "华人", "人民", "人民共和国", "共和", "共和国", "国公", "公民", "", "", "我", "爸爸", "是", "共和", "共和党", "党员", "", "", "", "地铁", "和平", "和平门", "站"}, + []string{"张晓梅", "去", "人民", "民医院", "医院", "做", "了", "个", "B", "超然", "然后", "后去", "买", "了", "件", "T", "恤"}, + []string{"AT", "T", "是", "一件", "不错", "的", "公司", "", "", "给", "你", "发", "offer", "了", "吗", "", ""}, + []string{"C++", "和", "c#", "是", "什么", "关系", "", "11+122", "133", "", "是", "吗", "", "PI", "3", "14159"}, + []string{"你", "认识", "那个", "和", "主席", "握手", "的", "的哥", "吗", "", "", "他", "开", "一辆", "黑色", "的士", "", ""}, + []string{"枪杆", "枪杆子", "杆子", "中出", "政权"}, } - defaultCutNoHMMResult = [][]string{ - []string{"\u8fd9", "\u662f", "\u4e00\u4e2a", "\u4f38\u624b\u4e0d\u89c1\u4e94\u6307", "\u7684", "\u9ed1\u591c", "\u3002", "\u6211", "\u53eb", "\u5b59\u609f\u7a7a", "\uff0c", "\u6211", "\u7231", "\u5317\u4eac", "\uff0c", "\u6211", "\u7231", "Python", "\u548c", "C++", "\u3002"}, - []string{"\u6211", "\u4e0d", "\u559c\u6b22", "\u65e5\u672c", "\u548c\u670d", "\u3002"}, - []string{"\u96f7\u7334", "\u56de\u5f52", "\u4eba\u95f4", "\u3002"}, - []string{"\u5de5\u4fe1\u5904", "\u5973\u5e72\u4e8b", "\u6bcf\u6708", "\u7ecf\u8fc7", "\u4e0b\u5c5e", "\u79d1\u5ba4", "\u90fd", "\u8981", "\u4eb2\u53e3", "\u4ea4\u4ee3", "24", "\u53e3", "\u4ea4\u6362\u673a", "\u7b49", "\u6280\u672f\u6027", "\u5668\u4ef6", "\u7684", "\u5b89\u88c5", "\u5de5\u4f5c"}, - []string{"\u6211", "\u9700\u8981", "\u5ec9\u79df\u623f"}, - []string{"\u6c38\u548c", "\u670d\u88c5", "\u9970\u54c1", "\u6709\u9650\u516c\u53f8"}, - []string{"\u6211", "\u7231", "\u5317\u4eac", "\u5929\u5b89\u95e8"}, + defaultCutNoHMMResult = [][]string{[]string{"这", "是", "一个", "伸手不见五指", "的", "黑夜", "。", "我", "叫", "孙悟空", ",", "我", "爱", "北京", ",", "我", "爱", "Python", "和", "C++", "。"}, + []string{"我", "不", "喜欢", "日本", "和服", "。"}, + []string{"雷猴", "回归", "人间", "。"}, + []string{"工信处", "女干事", "每月", "经过", "下属", "科室", "都", "要", "亲口", "交代", "24", "口", "交换机", "等", "技术性", "器件", "的", "安装", "工作"}, + []string{"我", "需要", "廉租房"}, + []string{"永和", "服装", "饰品", "有限公司"}, + []string{"我", "爱", "北京", "天安门"}, []string{"abc"}, - []string{"\u9690", "\u9a6c\u5c14\u53ef\u592b"}, - []string{"\u96f7\u7334", "\u662f", "\u4e2a", "\u597d", "\u7f51\u7ad9"}, - []string{"\u201c", "Microsoft", "\u201d", "\u4e00", "\u8bcd", "\u7531", "\u201c", "MICROcomputer", "\uff08", "\u5fae\u578b", "\u8ba1\u7b97\u673a", "\uff09", "\u201d", "\u548c", "\u201c", "SOFTware", "\uff08", "\u8f6f\u4ef6", "\uff09", "\u201d", "\u4e24", "\u90e8\u5206", "\u7ec4\u6210"}, - []string{"\u8349\u6ce5\u9a6c", "\u548c", "\u6b3a", "\u5b9e", "\u9a6c", "\u662f", "\u4eca\u5e74", "\u7684", "\u6d41\u884c", "\u8bcd\u6c47"}, - []string{"\u4f0a", "\u85e4", "\u6d0b\u534e\u5802", "\u603b\u5e9c", "\u5e97"}, - []string{"\u4e2d\u56fd\u79d1\u5b66\u9662\u8ba1\u7b97\u6280\u672f\u7814\u7a76\u6240"}, - []string{"\u7f57\u5bc6\u6b27", "\u4e0e", "\u6731\u4e3d\u53f6"}, - []string{"\u6211", "\u8d2d\u4e70", "\u4e86", "\u9053\u5177", "\u548c", "\u670d\u88c5"}, - []string{"PS", ":", " ", "\u6211", "\u89c9\u5f97", "\u5f00\u6e90", "\u6709", "\u4e00\u4e2a", "\u597d\u5904", "\uff0c", "\u5c31\u662f", "\u80fd\u591f", "\u6566\u4fc3", "\u81ea\u5df1", "\u4e0d\u65ad\u6539\u8fdb", "\uff0c", "\u907f\u514d", "\u655e", "\u5e1a", "\u81ea\u73cd"}, - []string{"\u6e56\u5317\u7701", "\u77f3\u9996\u5e02"}, - []string{"\u6e56\u5317\u7701", "\u5341\u5830\u5e02"}, - []string{"\u603b\u7ecf\u7406", "\u5b8c\u6210", "\u4e86", "\u8fd9\u4ef6", "\u4e8b\u60c5"}, - []string{"\u7535\u8111", "\u4fee\u597d", "\u4e86"}, - []string{"\u505a\u597d", "\u4e86", "\u8fd9\u4ef6", "\u4e8b\u60c5", "\u5c31", "\u4e00\u4e86\u767e\u4e86", "\u4e86"}, - []string{"\u4eba\u4eec", "\u5ba1\u7f8e", "\u7684", "\u89c2\u70b9", "\u662f", "\u4e0d\u540c", "\u7684"}, - []string{"\u6211\u4eec", "\u4e70", "\u4e86", "\u4e00\u4e2a", "\u7f8e\u7684", "\u7a7a\u8c03"}, - []string{"\u7ebf\u7a0b", "\u521d\u59cb\u5316", "\u65f6", "\u6211\u4eec", "\u8981", "\u6ce8\u610f"}, - []string{"\u4e00\u4e2a", "\u5206\u5b50", "\u662f", "\u7531", "\u597d\u591a", "\u539f\u5b50", "\u7ec4\u7ec7", "\u6210", "\u7684"}, - []string{"\u795d", "\u4f60", "\u9a6c\u5230\u529f\u6210"}, - []string{"\u4ed6", "\u6389", "\u8fdb", "\u4e86", "\u65e0\u5e95\u6d1e", "\u91cc"}, - []string{"\u4e2d\u56fd", "\u7684", "\u9996\u90fd", "\u662f", "\u5317\u4eac"}, - []string{"\u5b59", "\u541b", "\u610f"}, - []string{"\u5916\u4ea4\u90e8", "\u53d1\u8a00\u4eba", "\u9a6c\u671d\u65ed"}, - []string{"\u9886\u5bfc\u4eba", "\u4f1a\u8bae", "\u548c", "\u7b2c\u56db\u5c4a", "\u4e1c\u4e9a", "\u5cf0\u4f1a"}, - []string{"\u5728", "\u8fc7\u53bb", "\u7684", "\u8fd9", "\u4e94\u5e74"}, - []string{"\u8fd8", "\u9700\u8981", "\u5f88", "\u957f", "\u7684", "\u8def", "\u8981", "\u8d70"}, - []string{"60", "\u5468\u5e74", "\u9996\u90fd", "\u9605\u5175"}, - []string{"\u4f60\u597d", "\u4eba\u4eec", "\u5ba1\u7f8e", "\u7684", "\u89c2\u70b9", "\u662f", "\u4e0d\u540c", "\u7684"}, - []string{"\u4e70", "\u6c34\u679c", "\u7136\u540e", "\u6765", "\u4e16\u535a\u56ed"}, - []string{"\u4e70", "\u6c34\u679c", "\u7136\u540e", "\u53bb", "\u4e16\u535a\u56ed"}, - []string{"\u4f46\u662f", "\u540e\u6765", "\u6211", "\u624d", "\u77e5\u9053", "\u4f60", "\u662f", "\u5bf9", "\u7684"}, - []string{"\u5b58\u5728", "\u5373", "\u5408\u7406"}, - []string{"\u7684", "\u7684", "\u7684", "\u7684", "\u7684", "\u5728", "\u7684", "\u7684", "\u7684", "\u7684", "\u5c31", "\u4ee5", "\u548c", "\u548c", "\u548c"}, - []string{"I", " ", "love", "\u4f60", "\uff0c", "\u4e0d\u4ee5\u4e3a\u803b", "\uff0c", "\u53cd", "\u4ee5\u4e3a", "rong"}, - []string{"\u56e0"}, + []string{"隐", "马尔可夫"}, + []string{"雷猴", "是", "个", "好", "网站"}, + []string{"“", "Microsoft", "”", "一", "词", "由", "“", "MICROcomputer", "(", "微型", "计算机", ")", "”", "和", "“", "SOFTware", "(", "软件", ")", "”", "两", "部分", "组成"}, + []string{"草泥马", "和", "欺", "实", "马", "是", "今年", "的", "流行", "词汇"}, + []string{"伊", "藤", "洋华堂", "总府", "店"}, + []string{"中国科学院计算技术研究所"}, + []string{"罗密欧", "与", "朱丽叶"}, + []string{"我", "购买", "了", "道具", "和", "服装"}, + []string{"PS", ":", " ", "我", "觉得", "开源", "有", "一个", "好处", ",", "就是", "能够", "敦促", "自己", "不断改进", ",", "避免", "敞", "帚", "自珍"}, + []string{"湖北省", "石首市"}, + []string{"湖北省", "十堰市"}, + []string{"总经理", "完成", "了", "这件", "事情"}, + []string{"电脑", "修好", "了"}, + []string{"做好", "了", "这件", "事情", "就", "一了百了", "了"}, + []string{"人们", "审美", "的", "观点", "是", "不同", "的"}, + []string{"我们", "买", "了", "一个", "美的", "空调"}, + []string{"线程", "初始化", "时", "我们", "要", "注意"}, + []string{"一个", "分子", "是", "由", "好多", "原子", "组织", "成", "的"}, + []string{"祝", "你", "马到功成"}, + []string{"他", "掉", "进", "了", "无底洞", "里"}, + []string{"中国", "的", "首都", "是", "北京"}, + []string{"孙", "君", "意"}, + []string{"外交部", "发言人", "马朝旭"}, + []string{"领导人", "会议", "和", "第四届", "东亚", "峰会"}, + []string{"在", "过去", "的", "这", "五年"}, + []string{"还", "需要", "很", "长", "的", "路", "要", "走"}, + []string{"60", "周年", "首都", "阅兵"}, + []string{"你好", "人们", "审美", "的", "观点", "是", "不同", "的"}, + []string{"买", "水果", "然后", "来", "世博园"}, + []string{"买", "水果", "然后", "去", "世博园"}, + []string{"但是", "后来", "我", "才", "知道", "你", "是", "对", "的"}, + []string{"存在", "即", "合理"}, + []string{"的", "的", "的", "的", "的", "在", "的", "的", "的", "的", "就", "以", "和", "和", "和"}, + []string{"I", " ", "love", "你", ",", "不以为耻", ",", "反", "以为", "rong"}, + []string{"因"}, []string{}, - []string{"hello", "\u4f60\u597d", "\u4eba\u4eec", "\u5ba1\u7f8e", "\u7684", "\u89c2\u70b9", "\u662f", "\u4e0d\u540c", "\u7684"}, - []string{"\u5f88", "\u597d", "\u4f46", "\u4e3b\u8981", "\u662f", "\u57fa\u4e8e", "\u7f51\u9875", "\u5f62\u5f0f"}, - []string{"hello", "\u4f60\u597d", "\u4eba\u4eec", "\u5ba1\u7f8e", "\u7684", "\u89c2\u70b9", "\u662f", "\u4e0d\u540c", "\u7684"}, - []string{"\u4e3a\u4ec0\u4e48", "\u6211", "\u4e0d\u80fd", "\u62e5\u6709", "\u60f3\u8981", "\u7684", "\u751f\u6d3b"}, - []string{"\u540e\u6765", "\u6211", "\u624d"}, - []string{"\u6b64\u6b21", "\u6765", "\u4e2d\u56fd", "\u662f", "\u4e3a\u4e86"}, - []string{"\u4f7f\u7528", "\u4e86", "\u5b83", "\u5c31", "\u53ef\u4ee5", "\u89e3\u51b3", "\u4e00\u4e9b", "\u95ee\u9898"}, - []string{",", "\u4f7f\u7528", "\u4e86", "\u5b83", "\u5c31", "\u53ef\u4ee5", "\u89e3\u51b3", "\u4e00\u4e9b", "\u95ee\u9898"}, - []string{"\u5176\u5b9e", "\u4f7f\u7528", "\u4e86", "\u5b83", "\u5c31", "\u53ef\u4ee5", "\u89e3\u51b3", "\u4e00\u4e9b", "\u95ee\u9898"}, - []string{"\u597d\u4eba", "\u4f7f\u7528", "\u4e86", "\u5b83", "\u5c31", "\u53ef\u4ee5", "\u89e3\u51b3", "\u4e00\u4e9b", "\u95ee\u9898"}, - []string{"\u662f\u56e0\u4e3a", "\u548c", "\u56fd\u5bb6"}, - []string{"\u8001\u5e74", "\u641c\u7d22", "\u8fd8", "\u652f\u6301"}, - []string{"\u5e72\u8106", "\u5c31", "\u628a", "\u90a3", "\u90e8", "\u8499", "\u4eba", "\u7684", "\u95f2", "\u6cd5", "\u7ed9", "\u5e9f", "\u4e86", "\u62c9\u5012", "\uff01", "RT", " ", "@", "laoshipukong", " ", ":", " ", "27", "\u65e5", "\uff0c", "\u5168\u56fd\u4eba\u5927\u5e38\u59d4\u4f1a", "\u7b2c\u4e09\u6b21", "\u5ba1\u8bae", "\u4fb5\u6743", "\u8d23\u4efb\u6cd5", "\u8349\u6848", "\uff0c", "\u5220\u9664", "\u4e86", "\u6709\u5173", "\u533b\u7597", "\u635f\u5bb3", "\u8d23\u4efb", "\u201c", "\u4e3e\u8bc1", "\u5012\u7f6e", "\u201d", "\u7684", "\u89c4\u5b9a", "\u3002", "\u5728", "\u533b\u60a3", "\u7ea0\u7eb7", "\u4e2d", "\u672c", "\u5df2", "\u5904\u4e8e", "\u5f31\u52bf", "\u5730\u4f4d", "\u7684", "\u6d88\u8d39\u8005", "\u7531\u6b64", "\u5c06", "\u9677\u5165", "\u4e07\u52ab\u4e0d\u590d", "\u7684", "\u5883\u5730", "\u3002", " "}, - []string{"\u5927"}, + []string{"hello", "你好", "人们", "审美", "的", "观点", "是", "不同", "的"}, + []string{"很", "好", "但", "主要", "是", "基于", "网页", "形式"}, + []string{"hello", "你好", "人们", "审美", "的", "观点", "是", "不同", "的"}, + []string{"为什么", "我", "不能", "拥有", "想要", "的", "生活"}, + []string{"后来", "我", "才"}, + []string{"此次", "来", "中国", "是", "为了"}, + []string{"使用", "了", "它", "就", "可以", "解决", "一些", "问题"}, + []string{",", "使用", "了", "它", "就", "可以", "解决", "一些", "问题"}, + []string{"其实", "使用", "了", "它", "就", "可以", "解决", "一些", "问题"}, + []string{"好人", "使用", "了", "它", "就", "可以", "解决", "一些", "问题"}, + []string{"是因为", "和", "国家"}, + []string{"老年", "搜索", "还", "支持"}, + []string{"干脆", "就", "把", "那", "部", "蒙", "人", "的", "闲", "法", "给", "废", "了", "拉倒", "!", "RT", " ", "@", "laoshipukong", " ", ":", " ", "27", "日", ",", "全国人大常委会", "第三次", "审议", "侵权", "责任法", "草案", ",", "删除", "了", "有关", "医疗", "损害", "责任", "“", "举证", "倒置", "”", "的", "规定", "。", "在", "医患", "纠纷", "中", "本", "已", "处于", "弱势", "地位", "的", "消费者", "由此", "将", "陷入", "万劫不复", "的", "境地", "。", " "}, + []string{"大"}, []string{}, - []string{"\u4ed6", "\u8bf4", "\u7684", "\u786e\u5b9e", "\u5728", "\u7406"}, - []string{"\u957f\u6625", "\u5e02\u957f", "\u6625\u8282", "\u8bb2\u8bdd"}, - []string{"\u7ed3\u5a5a", "\u7684", "\u548c", "\u5c1a\u672a", "\u7ed3\u5a5a", "\u7684"}, - []string{"\u7ed3\u5408", "\u6210", "\u5206\u5b50", "\u65f6"}, - []string{"\u65c5\u6e38", "\u548c", "\u670d\u52a1", "\u662f", "\u6700\u597d", "\u7684"}, - []string{"\u8fd9\u4ef6", "\u4e8b\u60c5", "\u7684\u786e", "\u662f", "\u6211", "\u7684", "\u9519"}, - []string{"\u4f9b", "\u5927\u5bb6", "\u53c2\u8003", "\u6307\u6b63"}, - []string{"\u54c8\u5c14\u6ee8", "\u653f\u5e9c", "\u516c\u5e03", "\u584c", "\u6865", "\u539f\u56e0"}, - []string{"\u6211", "\u5728", "\u673a\u573a", "\u5165\u53e3\u5904"}, - []string{"\u90a2", "\u6c38", "\u81e3", "\u6444\u5f71", "\u62a5\u9053"}, - []string{"BP", "\u795e\u7ecf\u7f51\u7edc", "\u5982\u4f55", "\u8bad\u7ec3", "\u624d\u80fd", "\u5728", "\u5206\u7c7b", "\u65f6", "\u589e\u52a0", "\u533a\u5206\u5ea6", "\uff1f"}, - []string{"\u5357\u4eac\u5e02", "\u957f\u6c5f\u5927\u6865"}, - []string{"\u5e94", "\u4e00\u4e9b", "\u4f7f\u7528\u8005", "\u7684", "\u5efa\u8bae", "\uff0c", "\u4e5f", "\u4e3a\u4e86", "\u4fbf\u4e8e", "\u5229\u7528", "NiuTrans", "\u7528\u4e8e", "SMT", "\u7814\u7a76"}, - []string{"\u957f\u6625\u5e02", "\u957f\u6625", "\u836f\u5e97"}, - []string{"\u9093\u9896\u8d85", "\u751f\u524d", "\u6700", "\u559c\u6b22", "\u7684", "\u8863\u670d"}, - []string{"\u80e1\u9526\u6d9b", "\u662f", "\u70ed\u7231", "\u4e16\u754c", "\u548c\u5e73", "\u7684", "\u653f\u6cbb\u5c40", "\u5e38\u59d4"}, - []string{"\u7a0b\u5e8f\u5458", "\u795d", "\u6d77\u6797", "\u548c", "\u6731", "\u4f1a", "\u9707", "\u662f", "\u5728", "\u5b59", "\u5065", "\u7684", "\u5de6\u9762", "\u548c", "\u53f3\u9762", ",", " ", "\u8303", "\u51ef", "\u5728", "\u6700", "\u53f3\u9762", ".", "\u518d", "\u5f80", "\u5de6", "\u662f", "\u674e", "\u677e", "\u6d2a"}, - []string{"\u4e00\u6b21\u6027", "\u4ea4", "\u591a\u5c11", "\u94b1"}, - []string{"\u4e24\u5757", "\u4e94", "\u4e00\u5957", "\uff0c", "\u4e09\u5757", "\u516b", "\u4e00\u65a4", "\uff0c", "\u56db\u5757", "\u4e03", "\u4e00\u672c", "\uff0c", "\u4e94\u5757", "\u516d", "\u4e00\u6761"}, - []string{"\u5c0f", "\u548c\u5c1a", "\u7559", "\u4e86", "\u4e00\u4e2a", "\u50cf", "\u5927", "\u548c\u5c1a", "\u4e00\u6837", "\u7684", "\u548c\u5c1a\u5934"}, - []string{"\u6211", "\u662f", "\u4e2d\u534e\u4eba\u6c11\u5171\u548c\u56fd", "\u516c\u6c11", ";", "\u6211", "\u7238\u7238", "\u662f", "\u5171\u548c\u515a", "\u515a\u5458", ";", " ", "\u5730\u94c1", "\u548c\u5e73\u95e8", "\u7ad9"}, - []string{"\u5f20\u6653\u6885", "\u53bb", "\u4eba\u6c11", "\u533b\u9662", "\u505a", "\u4e86", "\u4e2a", "B\u8d85", "\u7136\u540e", "\u53bb", "\u4e70", "\u4e86", "\u4ef6", "T\u6064"}, - []string{"AT&T", "\u662f", "\u4e00\u4ef6", "\u4e0d\u9519", "\u7684", "\u516c\u53f8", "\uff0c", "\u7ed9", "\u4f60", "\u53d1", "offer", "\u4e86", "\u5417", "\uff1f"}, - []string{"C++", "\u548c", "c#", "\u662f", "\u4ec0\u4e48", "\u5173\u7cfb", "\uff1f", "11", "+", "122", "=", "133", "\uff0c", "\u662f", "\u5417", "\uff1f", "PI", "=", "3", ".", "14159"}, - []string{"\u4f60", "\u8ba4\u8bc6", "\u90a3\u4e2a", "\u548c", "\u4e3b\u5e2d", "\u63e1\u624b", "\u7684", "\u7684\u54e5", "\u5417", "\uff1f", "\u4ed6", "\u5f00", "\u4e00\u8f86", "\u9ed1\u8272", "\u7684\u58eb", "\u3002"}, - []string{"\u67aa\u6746\u5b50", "\u4e2d", "\u51fa", "\u653f\u6743"}, + []string{"他", "说", "的", "确实", "在", "理"}, + []string{"长春", "市长", "春节", "讲话"}, + []string{"结婚", "的", "和", "尚未", "结婚", "的"}, + []string{"结合", "成", "分子", "时"}, + []string{"旅游", "和", "服务", "是", "最好", "的"}, + []string{"这件", "事情", "的确", "是", "我", "的", "错"}, + []string{"供", "大家", "参考", "指正"}, + []string{"哈尔滨", "政府", "公布", "塌", "桥", "原因"}, + []string{"我", "在", "机场", "入口处"}, + []string{"邢", "永", "臣", "摄影", "报道"}, + []string{"BP", "神经网络", "如何", "训练", "才能", "在", "分类", "时", "增加", "区分度", "?"}, + []string{"南京市", "长江大桥"}, + []string{"应", "一些", "使用者", "的", "建议", ",", "也", "为了", "便于", "利用", "NiuTrans", "用于", "SMT", "研究"}, + []string{"长春市", "长春", "药店"}, + []string{"邓颖超", "生前", "最", "喜欢", "的", "衣服"}, + []string{"胡锦涛", "是", "热爱", "世界", "和平", "的", "政治局", "常委"}, + []string{"程序员", "祝", "海林", "和", "朱", "会", "震", "是", "在", "孙", "健", "的", "左面", "和", "右面", ",", " ", "范", "凯", "在", "最", "右面", ".", "再", "往", "左", "是", "李", "松", "洪"}, + []string{"一次性", "交", "多少", "钱"}, + []string{"两块", "五", "一套", ",", "三块", "八", "一斤", ",", "四块", "七", "一本", ",", "五块", "六", "一条"}, + []string{"小", "和尚", "留", "了", "一个", "像", "大", "和尚", "一样", "的", "和尚头"}, + []string{"我", "是", "中华人民共和国", "公民", ";", "我", "爸爸", "是", "共和党", "党员", ";", " ", "地铁", "和平门", "站"}, + []string{"张晓梅", "去", "人民", "医院", "做", "了", "个", "B超", "然后", "去", "买", "了", "件", "T恤"}, + []string{"AT&T", "是", "一件", "不错", "的", "公司", ",", "给", "你", "发", "offer", "了", "吗", "?"}, + []string{"C++", "和", "c#", "是", "什么", "关系", "?", "11", "+", "122", "=", "133", ",", "是", "吗", "?", "PI", "=", "3", ".", "14159"}, + []string{"你", "认识", "那个", "和", "主席", "握手", "的", "的哥", "吗", "?", "他", "开", "一辆", "黑色", "的士", "。"}, + []string{"枪杆子", "中", "出", "政权"}, } - cutForSearchResult = [][]string{ - []string{"\u8fd9\u662f", "\u4e00\u4e2a", "\u4f38\u624b", "\u4e0d\u89c1", "\u4e94\u6307", "\u4f38\u624b\u4e0d\u89c1\u4e94\u6307", "\u7684", "\u9ed1\u591c", "\u3002", "\u6211", "\u53eb", "\u609f\u7a7a", "\u5b59\u609f\u7a7a", "\uff0c", "\u6211", "\u7231", "\u5317\u4eac", "\uff0c", "\u6211", "\u7231", "Python", "\u548c", "C++", "\u3002"}, - []string{"\u6211", "\u4e0d", "\u559c\u6b22", "\u65e5\u672c", "\u548c\u670d", "\u3002"}, - []string{"\u96f7\u7334", "\u56de\u5f52", "\u4eba\u95f4", "\u3002"}, - []string{"\u5de5\u4fe1\u5904", "\u5e72\u4e8b", "\u5973\u5e72\u4e8b", "\u6bcf\u6708", "\u7ecf\u8fc7", "\u4e0b\u5c5e", "\u79d1\u5ba4", "\u90fd", "\u8981", "\u4eb2\u53e3", "\u4ea4\u4ee3", "24", "\u53e3", "\u4ea4\u6362", "\u6362\u673a", "\u4ea4\u6362\u673a", "\u7b49", "\u6280\u672f", "\u6280\u672f\u6027", "\u5668\u4ef6", "\u7684", "\u5b89\u88c5", "\u5de5\u4f5c"}, - []string{"\u6211", "\u9700\u8981", "\u5ec9\u79df", "\u79df\u623f", "\u5ec9\u79df\u623f"}, - []string{"\u6c38\u548c", "\u670d\u88c5", "\u9970\u54c1", "\u6709\u9650", "\u516c\u53f8", "\u6709\u9650\u516c\u53f8"}, - []string{"\u6211", "\u7231", "\u5317\u4eac", "\u5929\u5b89", "\u5929\u5b89\u95e8"}, + cutForSearchResult = [][]string{[]string{"这是", "一个", "伸手", "不见", "五指", "伸手不见五指", "的", "黑夜", "。", "我", "叫", "悟空", "孙悟空", ",", "我", "爱", "北京", ",", "我", "爱", "Python", "和", "C++", "。"}, + []string{"我", "不", "喜欢", "日本", "和服", "。"}, + []string{"雷猴", "回归", "人间", "。"}, + []string{"工信处", "干事", "女干事", "每月", "经过", "下属", "科室", "都", "要", "亲口", "交代", "24", "口", "交换", "换机", "交换机", "等", "技术", "技术性", "器件", "的", "安装", "工作"}, + []string{"我", "需要", "廉租", "租房", "廉租房"}, + []string{"永和", "服装", "饰品", "有限", "公司", "有限公司"}, + []string{"我", "爱", "北京", "天安", "天安门"}, []string{"abc"}, - []string{"\u9690", "\u53ef\u592b", "\u9a6c\u5c14\u53ef", "\u9a6c\u5c14\u53ef\u592b"}, - []string{"\u96f7\u7334", "\u662f", "\u4e2a", "\u597d", "\u7f51\u7ad9"}, - []string{"\u201c", "Microsoft", "\u201d", "\u4e00\u8bcd", "\u7531", "\u201c", "MICROcomputer", "\uff08", "\u5fae\u578b", "\u8ba1\u7b97", "\u7b97\u673a", "\u8ba1\u7b97\u673a", "\uff09", "\u201d", "\u548c", "\u201c", "SOFTware", "\uff08", "\u8f6f\u4ef6", "\uff09", "\u201d", "\u4e24", "\u90e8\u5206", "\u7ec4\u6210"}, - []string{"\u8349\u6ce5\u9a6c", "\u548c", "\u6b3a\u5b9e", "\u9a6c", "\u662f", "\u4eca\u5e74", "\u7684", "\u6d41\u884c", "\u8bcd\u6c47"}, - []string{"\u4f0a\u85e4", "\u6d0b\u534e\u5802", "\u603b\u5e9c", "\u5e97"}, - []string{"\u4e2d\u56fd", "\u79d1\u5b66", "\u5b66\u9662", "\u8ba1\u7b97", "\u6280\u672f", "\u7814\u7a76", "\u79d1\u5b66\u9662", "\u7814\u7a76\u6240", "\u4e2d\u56fd\u79d1\u5b66\u9662\u8ba1\u7b97\u6280\u672f\u7814\u7a76\u6240"}, - []string{"\u7f57\u5bc6\u6b27", "\u4e0e", "\u6731\u4e3d\u53f6"}, - []string{"\u6211", "\u8d2d\u4e70", "\u4e86", "\u9053\u5177", "\u548c", "\u670d\u88c5"}, - []string{"PS", ":", " ", "\u6211", "\u89c9\u5f97", "\u5f00\u6e90", "\u6709", "\u4e00\u4e2a", "\u597d\u5904", "\uff0c", "\u5c31\u662f", "\u80fd\u591f", "\u6566\u4fc3", "\u81ea\u5df1", "\u4e0d\u65ad", "\u6539\u8fdb", "\u4e0d\u65ad\u6539\u8fdb", "\uff0c", "\u907f\u514d", "\u655e\u5e1a", "\u81ea\u73cd"}, - []string{"\u6e56\u5317", "\u6e56\u5317\u7701", "\u77f3\u9996", "\u77f3\u9996\u5e02"}, - []string{"\u6e56\u5317", "\u6e56\u5317\u7701", "\u5341\u5830", "\u5341\u5830\u5e02"}, - []string{"\u7ecf\u7406", "\u603b\u7ecf\u7406", "\u5b8c\u6210", "\u4e86", "\u8fd9\u4ef6", "\u4e8b\u60c5"}, - []string{"\u7535\u8111", "\u4fee\u597d", "\u4e86"}, - []string{"\u505a\u597d", "\u4e86", "\u8fd9\u4ef6", "\u4e8b\u60c5", "\u5c31", "\u4e00\u4e86\u767e\u4e86", "\u4e86"}, - []string{"\u4eba\u4eec", "\u5ba1\u7f8e", "\u7684", "\u89c2\u70b9", "\u662f", "\u4e0d\u540c", "\u7684"}, - []string{"\u6211\u4eec", "\u4e70", "\u4e86", "\u4e00\u4e2a", "\u7f8e\u7684", "\u7a7a\u8c03"}, - []string{"\u7ebf\u7a0b", "\u521d\u59cb", "\u521d\u59cb\u5316", "\u65f6", "\u6211\u4eec", "\u8981", "\u6ce8\u610f"}, - []string{"\u4e00\u4e2a", "\u5206\u5b50", "\u662f", "\u7531", "\u597d\u591a", "\u539f\u5b50", "\u7ec4\u7ec7", "\u6210", "\u7684"}, - []string{"\u795d", "\u4f60", "\u9a6c\u5230\u529f\u6210"}, - []string{"\u4ed6", "\u6389", "\u8fdb", "\u4e86", "\u65e0\u5e95", "\u65e0\u5e95\u6d1e", "\u91cc"}, - []string{"\u4e2d\u56fd", "\u7684", "\u9996\u90fd", "\u662f", "\u5317\u4eac"}, - []string{"\u5b59\u541b\u610f"}, - []string{"\u5916\u4ea4", "\u5916\u4ea4\u90e8", "\u53d1\u8a00", "\u53d1\u8a00\u4eba", "\u9a6c\u671d\u65ed"}, - []string{"\u9886\u5bfc", "\u9886\u5bfc\u4eba", "\u4f1a\u8bae", "\u548c", "\u7b2c\u56db", "\u56db\u5c4a", "\u7b2c\u56db\u5c4a", "\u4e1c\u4e9a", "\u5cf0\u4f1a"}, - []string{"\u5728", "\u8fc7\u53bb", "\u7684", "\u8fd9", "\u4e94\u5e74"}, - []string{"\u8fd8", "\u9700\u8981", "\u5f88\u957f", "\u7684", "\u8def", "\u8981", "\u8d70"}, - []string{"60", "\u5468\u5e74", "\u9996\u90fd", "\u9605\u5175"}, - []string{"\u4f60\u597d", "\u4eba\u4eec", "\u5ba1\u7f8e", "\u7684", "\u89c2\u70b9", "\u662f", "\u4e0d\u540c", "\u7684"}, - []string{"\u4e70", "\u6c34\u679c", "\u7136\u540e", "\u6765", "\u4e16\u535a", "\u535a\u56ed", "\u4e16\u535a\u56ed"}, - []string{"\u4e70", "\u6c34\u679c", "\u7136\u540e", "\u53bb", "\u4e16\u535a", "\u535a\u56ed", "\u4e16\u535a\u56ed"}, - []string{"\u4f46\u662f", "\u540e\u6765", "\u6211", "\u624d", "\u77e5\u9053", "\u4f60", "\u662f", "\u5bf9", "\u7684"}, - []string{"\u5b58\u5728", "\u5373", "\u5408\u7406"}, - []string{"\u7684", "\u7684", "\u7684", "\u7684", "\u7684", "\u5728", "\u7684", "\u7684", "\u7684", "\u7684", "\u5c31", "\u4ee5", "\u548c", "\u548c", "\u548c"}, - []string{"I", " ", "love", "\u4f60", "\uff0c", "\u4e0d\u4ee5", "\u4ee5\u4e3a", "\u4e0d\u4ee5\u4e3a\u803b", "\uff0c", "\u53cd", "\u4ee5\u4e3a", "rong"}, - []string{"\u56e0"}, + []string{"隐", "可夫", "马尔可", "马尔可夫"}, + []string{"雷猴", "是", "个", "好", "网站"}, + []string{"“", "Microsoft", "”", "一词", "由", "“", "MICROcomputer", "(", "微型", "计算", "算机", "计算机", ")", "”", "和", "“", "SOFTware", "(", "软件", ")", "”", "两", "部分", "组成"}, + []string{"草泥马", "和", "欺实", "马", "是", "今年", "的", "流行", "词汇"}, + []string{"伊藤", "洋华堂", "总府", "店"}, + []string{"中国", "科学", "学院", "计算", "技术", "研究", "科学院", "研究所", "中国科学院计算技术研究所"}, + []string{"罗密欧", "与", "朱丽叶"}, + []string{"我", "购买", "了", "道具", "和", "服装"}, + []string{"PS", ":", " ", "我", "觉得", "开源", "有", "一个", "好处", ",", "就是", "能够", "敦促", "自己", "不断", "改进", "不断改进", ",", "避免", "敞帚", "自珍"}, + []string{"湖北", "湖北省", "石首", "石首市"}, + []string{"湖北", "湖北省", "十堰", "十堰市"}, + []string{"经理", "总经理", "完成", "了", "这件", "事情"}, + []string{"电脑", "修好", "了"}, + []string{"做好", "了", "这件", "事情", "就", "一了百了", "了"}, + []string{"人们", "审美", "的", "观点", "是", "不同", "的"}, + []string{"我们", "买", "了", "一个", "美的", "空调"}, + []string{"线程", "初始", "初始化", "时", "我们", "要", "注意"}, + []string{"一个", "分子", "是", "由", "好多", "原子", "组织", "成", "的"}, + []string{"祝", "你", "马到功成"}, + []string{"他", "掉", "进", "了", "无底", "无底洞", "里"}, + []string{"中国", "的", "首都", "是", "北京"}, + []string{"孙君意"}, + []string{"外交", "外交部", "发言", "发言人", "马朝旭"}, + []string{"领导", "领导人", "会议", "和", "第四", "四届", "第四届", "东亚", "峰会"}, + []string{"在", "过去", "的", "这", "五年"}, + []string{"还", "需要", "很长", "的", "路", "要", "走"}, + []string{"60", "周年", "首都", "阅兵"}, + []string{"你好", "人们", "审美", "的", "观点", "是", "不同", "的"}, + []string{"买", "水果", "然后", "来", "世博", "博园", "世博园"}, + []string{"买", "水果", "然后", "去", "世博", "博园", "世博园"}, + []string{"但是", "后来", "我", "才", "知道", "你", "是", "对", "的"}, + []string{"存在", "即", "合理"}, + []string{"的", "的", "的", "的", "的", "在", "的", "的", "的", "的", "就", "以", "和", "和", "和"}, + []string{"I", " ", "love", "你", ",", "不以", "以为", "不以为耻", ",", "反", "以为", "rong"}, + []string{"因"}, []string{}, - []string{"hello", "\u4f60\u597d", "\u4eba\u4eec", "\u5ba1\u7f8e", "\u7684", "\u89c2\u70b9", "\u662f", "\u4e0d\u540c", "\u7684"}, - []string{"\u5f88", "\u597d", "\u4f46", "\u4e3b\u8981", "\u662f", "\u57fa\u4e8e", "\u7f51\u9875", "\u5f62\u5f0f"}, - []string{"hello", "\u4f60\u597d", "\u4eba\u4eec", "\u5ba1\u7f8e", "\u7684", "\u89c2\u70b9", "\u662f", "\u4e0d\u540c", "\u7684"}, - []string{"\u4ec0\u4e48", "\u4e3a\u4ec0\u4e48", "\u6211", "\u4e0d\u80fd", "\u62e5\u6709", "\u60f3\u8981", "\u7684", "\u751f\u6d3b"}, - []string{"\u540e\u6765", "\u6211", "\u624d"}, - []string{"\u6b64\u6b21", "\u6765", "\u4e2d\u56fd", "\u662f", "\u4e3a\u4e86"}, - []string{"\u4f7f\u7528", "\u4e86", "\u5b83", "\u5c31", "\u53ef\u4ee5", "\u89e3\u51b3", "\u4e00\u4e9b", "\u95ee\u9898"}, - []string{",", "\u4f7f\u7528", "\u4e86", "\u5b83", "\u5c31", "\u53ef\u4ee5", "\u89e3\u51b3", "\u4e00\u4e9b", "\u95ee\u9898"}, - []string{"\u5176\u5b9e", "\u4f7f\u7528", "\u4e86", "\u5b83", "\u5c31", "\u53ef\u4ee5", "\u89e3\u51b3", "\u4e00\u4e9b", "\u95ee\u9898"}, - []string{"\u597d\u4eba", "\u4f7f\u7528", "\u4e86", "\u5b83", "\u5c31", "\u53ef\u4ee5", "\u89e3\u51b3", "\u4e00\u4e9b", "\u95ee\u9898"}, - []string{"\u56e0\u4e3a", "\u662f\u56e0\u4e3a", "\u548c", "\u56fd\u5bb6"}, - []string{"\u8001\u5e74", "\u641c\u7d22", "\u8fd8", "\u652f\u6301"}, - []string{"\u5e72\u8106", "\u5c31", "\u628a", "\u90a3\u90e8", "\u8499\u4eba", "\u7684", "\u95f2\u6cd5", "\u7ed9", "\u5e9f", "\u4e86", "\u62c9\u5012", "\uff01", "RT", " ", "@", "laoshipukong", " ", ":", " ", "27", "\u65e5", "\uff0c", "\u5168\u56fd", "\u56fd\u4eba", "\u4eba\u5927", "\u5e38\u59d4", "\u59d4\u4f1a", "\u5e38\u59d4\u4f1a", "\u5168\u56fd\u4eba\u5927\u5e38\u59d4\u4f1a", "\u7b2c\u4e09", "\u4e09\u6b21", "\u7b2c\u4e09\u6b21", "\u5ba1\u8bae", "\u4fb5\u6743", "\u8d23\u4efb", "\u8d23\u4efb\u6cd5", "\u8349\u6848", "\uff0c", "\u5220\u9664", "\u4e86", "\u6709\u5173", "\u533b\u7597", "\u635f\u5bb3", "\u8d23\u4efb", "\u201c", "\u4e3e\u8bc1", "\u5012\u7f6e", "\u201d", "\u7684", "\u89c4\u5b9a", "\u3002", "\u5728", "\u533b\u60a3", "\u7ea0\u7eb7", "\u4e2d\u672c", "\u5df2", "\u5904\u4e8e", "\u5f31\u52bf", "\u5730\u4f4d", "\u7684", "\u6d88\u8d39", "\u6d88\u8d39\u8005", "\u7531\u6b64", "\u5c06", "\u9677\u5165", "\u4e0d\u590d", "\u4e07\u52ab\u4e0d\u590d", "\u7684", "\u5883\u5730", "\u3002", " "}, - []string{"\u5927"}, + []string{"hello", "你好", "人们", "审美", "的", "观点", "是", "不同", "的"}, + []string{"很", "好", "但", "主要", "是", "基于", "网页", "形式"}, + []string{"hello", "你好", "人们", "审美", "的", "观点", "是", "不同", "的"}, + []string{"什么", "为什么", "我", "不能", "拥有", "想要", "的", "生活"}, + []string{"后来", "我", "才"}, + []string{"此次", "来", "中国", "是", "为了"}, + []string{"使用", "了", "它", "就", "可以", "解决", "一些", "问题"}, + []string{",", "使用", "了", "它", "就", "可以", "解决", "一些", "问题"}, + []string{"其实", "使用", "了", "它", "就", "可以", "解决", "一些", "问题"}, + []string{"好人", "使用", "了", "它", "就", "可以", "解决", "一些", "问题"}, + []string{"因为", "是因为", "和", "国家"}, + []string{"老年", "搜索", "还", "支持"}, + []string{"干脆", "就", "把", "那部", "蒙人", "的", "闲法", "给", "废", "了", "拉倒", "!", "RT", " ", "@", "laoshipukong", " ", ":", " ", "27", "日", ",", "全国", "国人", "人大", "常委", "委会", "常委会", "全国人大常委会", "第三", "三次", "第三次", "审议", "侵权", "责任", "责任法", "草案", ",", "删除", "了", "有关", "医疗", "损害", "责任", "“", "举证", "倒置", "”", "的", "规定", "。", "在", "医患", "纠纷", "中本", "已", "处于", "弱势", "地位", "的", "消费", "消费者", "由此", "将", "陷入", "不复", "万劫不复", "的", "境地", "。", " "}, + []string{"大"}, []string{}, - []string{"\u4ed6", "\u8bf4", "\u7684", "\u786e\u5b9e", "\u5728\u7406"}, - []string{"\u957f\u6625", "\u5e02\u957f", "\u6625\u8282", "\u8bb2\u8bdd"}, - []string{"\u7ed3\u5a5a", "\u7684", "\u548c", "\u5c1a\u672a", "\u7ed3\u5a5a", "\u7684"}, - []string{"\u7ed3\u5408", "\u6210", "\u5206\u5b50", "\u65f6"}, - []string{"\u65c5\u6e38", "\u548c", "\u670d\u52a1", "\u662f", "\u6700\u597d", "\u7684"}, - []string{"\u8fd9\u4ef6", "\u4e8b\u60c5", "\u7684\u786e", "\u662f", "\u6211", "\u7684", "\u9519"}, - []string{"\u4f9b", "\u5927\u5bb6", "\u53c2\u8003", "\u6307\u6b63"}, - []string{"\u54c8\u5c14", "\u54c8\u5c14\u6ee8", "\u653f\u5e9c", "\u516c\u5e03", "\u584c\u6865", "\u539f\u56e0"}, - []string{"\u6211", "\u5728", "\u673a\u573a", "\u5165\u53e3", "\u5165\u53e3\u5904"}, - []string{"\u90a2\u6c38\u81e3", "\u6444\u5f71", "\u62a5\u9053"}, - []string{"BP", "\u795e\u7ecf", "\u7f51\u7edc", "\u795e\u7ecf\u7f51", "\u795e\u7ecf\u7f51\u7edc", "\u5982\u4f55", "\u8bad\u7ec3", "\u624d\u80fd", "\u5728", "\u5206\u7c7b", "\u65f6", "\u589e\u52a0", "\u533a\u5206", "\u5206\u5ea6", "\u533a\u5206\u5ea6", "\uff1f"}, - []string{"\u5357\u4eac", "\u4eac\u5e02", "\u5357\u4eac\u5e02", "\u957f\u6c5f", "\u5927\u6865", "\u957f\u6c5f\u5927\u6865"}, - []string{"\u5e94", "\u4e00\u4e9b", "\u4f7f\u7528", "\u7528\u8005", "\u4f7f\u7528\u8005", "\u7684", "\u5efa\u8bae", "\uff0c", "\u4e5f", "\u4e3a\u4e86", "\u4fbf\u4e8e", "\u5229\u7528", "NiuTrans", "\u7528\u4e8e", "SMT", "\u7814\u7a76"}, - []string{"\u957f\u6625", "\u957f\u6625\u5e02", "\u957f\u6625", "\u836f\u5e97"}, - []string{"\u9093\u9896\u8d85", "\u751f\u524d", "\u6700", "\u559c\u6b22", "\u7684", "\u8863\u670d"}, - []string{"\u9526\u6d9b", "\u80e1\u9526\u6d9b", "\u662f", "\u70ed\u7231", "\u4e16\u754c", "\u548c\u5e73", "\u7684", "\u653f\u6cbb", "\u653f\u6cbb\u5c40", "\u5e38\u59d4"}, - []string{"\u7a0b\u5e8f", "\u7a0b\u5e8f\u5458", "\u795d", "\u6d77\u6797", "\u548c", "\u6731\u4f1a\u9707", "\u662f", "\u5728", "\u5b59\u5065", "\u7684", "\u5de6\u9762", "\u548c", "\u53f3\u9762", ",", " ", "\u8303\u51ef", "\u5728", "\u6700", "\u53f3\u9762", ".", "\u518d\u5f80", "\u5de6", "\u662f", "\u674e\u677e\u6d2a"}, - []string{"\u4e00\u6b21", "\u4e00\u6b21\u6027", "\u4ea4", "\u591a\u5c11", "\u94b1"}, - []string{"\u4e24\u5757", "\u4e94", "\u4e00\u5957", "\uff0c", "\u4e09\u5757", "\u516b", "\u4e00\u65a4", "\uff0c", "\u56db\u5757", "\u4e03", "\u4e00\u672c", "\uff0c", "\u4e94\u5757", "\u516d", "\u4e00\u6761"}, - []string{"\u5c0f", "\u548c\u5c1a", "\u7559", "\u4e86", "\u4e00\u4e2a", "\u50cf", "\u5927", "\u548c\u5c1a", "\u4e00\u6837", "\u7684", "\u548c\u5c1a", "\u548c\u5c1a\u5934"}, - []string{"\u6211", "\u662f", "\u4e2d\u534e", "\u534e\u4eba", "\u4eba\u6c11", "\u5171\u548c", "\u5171\u548c\u56fd", "\u4e2d\u534e\u4eba\u6c11\u5171\u548c\u56fd", "\u516c\u6c11", ";", "\u6211", "\u7238\u7238", "\u662f", "\u5171\u548c", "\u5171\u548c\u515a", "\u515a\u5458", ";", " ", "\u5730\u94c1", "\u548c\u5e73", "\u548c\u5e73\u95e8", "\u7ad9"}, - []string{"\u5f20\u6653\u6885", "\u53bb", "\u4eba\u6c11", "\u533b\u9662", "\u505a", "\u4e86", "\u4e2a", "B\u8d85", "\u7136\u540e", "\u53bb", "\u4e70", "\u4e86", "\u4ef6", "T\u6064"}, - []string{"AT&T", "\u662f", "\u4e00\u4ef6", "\u4e0d\u9519", "\u7684", "\u516c\u53f8", "\uff0c", "\u7ed9", "\u4f60", "\u53d1", "offer", "\u4e86", "\u5417", "\uff1f"}, - []string{"C++", "\u548c", "c#", "\u662f", "\u4ec0\u4e48", "\u5173\u7cfb", "\uff1f", "11", "+", "122", "=", "133", "\uff0c", "\u662f", "\u5417", "\uff1f", "PI", "=", "3.14159"}, - []string{"\u4f60", "\u8ba4\u8bc6", "\u90a3\u4e2a", "\u548c", "\u4e3b\u5e2d", "\u63e1\u624b", "\u7684", "\u7684\u54e5", "\u5417", "\uff1f", "\u4ed6\u5f00", "\u4e00\u8f86", "\u9ed1\u8272", "\u7684\u58eb", "\u3002"}, - []string{"\u67aa\u6746", "\u6746\u5b50", "\u67aa\u6746\u5b50", "\u4e2d", "\u51fa", "\u653f\u6743"}, + []string{"他", "说", "的", "确实", "在理"}, + []string{"长春", "市长", "春节", "讲话"}, + []string{"结婚", "的", "和", "尚未", "结婚", "的"}, + []string{"结合", "成", "分子", "时"}, + []string{"旅游", "和", "服务", "是", "最好", "的"}, + []string{"这件", "事情", "的确", "是", "我", "的", "错"}, + []string{"供", "大家", "参考", "指正"}, + []string{"哈尔", "哈尔滨", "政府", "公布", "塌桥", "原因"}, + []string{"我", "在", "机场", "入口", "入口处"}, + []string{"邢永臣", "摄影", "报道"}, + []string{"BP", "神经", "网络", "神经网", "神经网络", "如何", "训练", "才能", "在", "分类", "时", "增加", "区分", "分度", "区分度", "?"}, + []string{"南京", "京市", "南京市", "长江", "大桥", "长江大桥"}, + []string{"应", "一些", "使用", "用者", "使用者", "的", "建议", ",", "也", "为了", "便于", "利用", "NiuTrans", "用于", "SMT", "研究"}, + []string{"长春", "长春市", "长春", "药店"}, + []string{"邓颖超", "生前", "最", "喜欢", "的", "衣服"}, + []string{"锦涛", "胡锦涛", "是", "热爱", "世界", "和平", "的", "政治", "政治局", "常委"}, + []string{"程序", "程序员", "祝", "海林", "和", "朱会震", "是", "在", "孙健", "的", "左面", "和", "右面", ",", " ", "范凯", "在", "最", "右面", ".", "再往", "左", "是", "李松洪"}, + []string{"一次", "一次性", "交", "多少", "钱"}, + []string{"两块", "五", "一套", ",", "三块", "八", "一斤", ",", "四块", "七", "一本", ",", "五块", "六", "一条"}, + []string{"小", "和尚", "留", "了", "一个", "像", "大", "和尚", "一样", "的", "和尚", "和尚头"}, + []string{"我", "是", "中华", "华人", "人民", "共和", "共和国", "中华人民共和国", "公民", ";", "我", "爸爸", "是", "共和", "共和党", "党员", ";", " ", "地铁", "和平", "和平门", "站"}, + []string{"张晓梅", "去", "人民", "医院", "做", "了", "个", "B超", "然后", "去", "买", "了", "件", "T恤"}, + []string{"AT&T", "是", "一件", "不错", "的", "公司", ",", "给", "你", "发", "offer", "了", "吗", "?"}, + []string{"C++", "和", "c#", "是", "什么", "关系", "?", "11", "+", "122", "=", "133", ",", "是", "吗", "?", "PI", "=", "3.14159"}, + []string{"你", "认识", "那个", "和", "主席", "握手", "的", "的哥", "吗", "?", "他开", "一辆", "黑色", "的士", "。"}, + []string{"枪杆", "杆子", "枪杆子", "中", "出", "政权"}, } - cutForSearchNoHMMResult = [][]string{ - []string{"\u8fd9", "\u662f", "\u4e00\u4e2a", "\u4f38\u624b", "\u4e0d\u89c1", "\u4e94\u6307", "\u4f38\u624b\u4e0d\u89c1\u4e94\u6307", "\u7684", "\u9ed1\u591c", "\u3002", "\u6211", "\u53eb", "\u609f\u7a7a", "\u5b59\u609f\u7a7a", "\uff0c", "\u6211", "\u7231", "\u5317\u4eac", "\uff0c", "\u6211", "\u7231", "Python", "\u548c", "C++", "\u3002"}, - []string{"\u6211", "\u4e0d", "\u559c\u6b22", "\u65e5\u672c", "\u548c\u670d", "\u3002"}, - []string{"\u96f7\u7334", "\u56de\u5f52", "\u4eba\u95f4", "\u3002"}, - []string{"\u5de5\u4fe1\u5904", "\u5e72\u4e8b", "\u5973\u5e72\u4e8b", "\u6bcf\u6708", "\u7ecf\u8fc7", "\u4e0b\u5c5e", "\u79d1\u5ba4", "\u90fd", "\u8981", "\u4eb2\u53e3", "\u4ea4\u4ee3", "24", "\u53e3", "\u4ea4\u6362", "\u6362\u673a", "\u4ea4\u6362\u673a", "\u7b49", "\u6280\u672f", "\u6280\u672f\u6027", "\u5668\u4ef6", "\u7684", "\u5b89\u88c5", "\u5de5\u4f5c"}, - []string{"\u6211", "\u9700\u8981", "\u5ec9\u79df", "\u79df\u623f", "\u5ec9\u79df\u623f"}, - []string{"\u6c38\u548c", "\u670d\u88c5", "\u9970\u54c1", "\u6709\u9650", "\u516c\u53f8", "\u6709\u9650\u516c\u53f8"}, - []string{"\u6211", "\u7231", "\u5317\u4eac", "\u5929\u5b89", "\u5929\u5b89\u95e8"}, + cutForSearchNoHMMResult = [][]string{[]string{"这", "是", "一个", "伸手", "不见", "五指", "伸手不见五指", "的", "黑夜", "。", "我", "叫", "悟空", "孙悟空", ",", "我", "爱", "北京", ",", "我", "爱", "Python", "和", "C++", "。"}, + []string{"我", "不", "喜欢", "日本", "和服", "。"}, + []string{"雷猴", "回归", "人间", "。"}, + []string{"工信处", "干事", "女干事", "每月", "经过", "下属", "科室", "都", "要", "亲口", "交代", "24", "口", "交换", "换机", "交换机", "等", "技术", "技术性", "器件", "的", "安装", "工作"}, + []string{"我", "需要", "廉租", "租房", "廉租房"}, + []string{"永和", "服装", "饰品", "有限", "公司", "有限公司"}, + []string{"我", "爱", "北京", "天安", "天安门"}, []string{"abc"}, - []string{"\u9690", "\u53ef\u592b", "\u9a6c\u5c14\u53ef", "\u9a6c\u5c14\u53ef\u592b"}, - []string{"\u96f7\u7334", "\u662f", "\u4e2a", "\u597d", "\u7f51\u7ad9"}, - []string{"\u201c", "Microsoft", "\u201d", "\u4e00", "\u8bcd", "\u7531", "\u201c", "MICROcomputer", "\uff08", "\u5fae\u578b", "\u8ba1\u7b97", "\u7b97\u673a", "\u8ba1\u7b97\u673a", "\uff09", "\u201d", "\u548c", "\u201c", "SOFTware", "\uff08", "\u8f6f\u4ef6", "\uff09", "\u201d", "\u4e24", "\u90e8\u5206", "\u7ec4\u6210"}, - []string{"\u8349\u6ce5\u9a6c", "\u548c", "\u6b3a", "\u5b9e", "\u9a6c", "\u662f", "\u4eca\u5e74", "\u7684", "\u6d41\u884c", "\u8bcd\u6c47"}, - []string{"\u4f0a", "\u85e4", "\u6d0b\u534e\u5802", "\u603b\u5e9c", "\u5e97"}, - []string{"\u4e2d\u56fd", "\u79d1\u5b66", "\u5b66\u9662", "\u8ba1\u7b97", "\u6280\u672f", "\u7814\u7a76", "\u79d1\u5b66\u9662", "\u7814\u7a76\u6240", "\u4e2d\u56fd\u79d1\u5b66\u9662\u8ba1\u7b97\u6280\u672f\u7814\u7a76\u6240"}, - []string{"\u7f57\u5bc6\u6b27", "\u4e0e", "\u6731\u4e3d\u53f6"}, - []string{"\u6211", "\u8d2d\u4e70", "\u4e86", "\u9053\u5177", "\u548c", "\u670d\u88c5"}, - []string{"PS", ":", " ", "\u6211", "\u89c9\u5f97", "\u5f00\u6e90", "\u6709", "\u4e00\u4e2a", "\u597d\u5904", "\uff0c", "\u5c31\u662f", "\u80fd\u591f", "\u6566\u4fc3", "\u81ea\u5df1", "\u4e0d\u65ad", "\u6539\u8fdb", "\u4e0d\u65ad\u6539\u8fdb", "\uff0c", "\u907f\u514d", "\u655e", "\u5e1a", "\u81ea\u73cd"}, - []string{"\u6e56\u5317", "\u6e56\u5317\u7701", "\u77f3\u9996", "\u77f3\u9996\u5e02"}, - []string{"\u6e56\u5317", "\u6e56\u5317\u7701", "\u5341\u5830", "\u5341\u5830\u5e02"}, - []string{"\u7ecf\u7406", "\u603b\u7ecf\u7406", "\u5b8c\u6210", "\u4e86", "\u8fd9\u4ef6", "\u4e8b\u60c5"}, - []string{"\u7535\u8111", "\u4fee\u597d", "\u4e86"}, - []string{"\u505a\u597d", "\u4e86", "\u8fd9\u4ef6", "\u4e8b\u60c5", "\u5c31", "\u4e00\u4e86\u767e\u4e86", "\u4e86"}, - []string{"\u4eba\u4eec", "\u5ba1\u7f8e", "\u7684", "\u89c2\u70b9", "\u662f", "\u4e0d\u540c", "\u7684"}, - []string{"\u6211\u4eec", "\u4e70", "\u4e86", "\u4e00\u4e2a", "\u7f8e\u7684", "\u7a7a\u8c03"}, - []string{"\u7ebf\u7a0b", "\u521d\u59cb", "\u521d\u59cb\u5316", "\u65f6", "\u6211\u4eec", "\u8981", "\u6ce8\u610f"}, - []string{"\u4e00\u4e2a", "\u5206\u5b50", "\u662f", "\u7531", "\u597d\u591a", "\u539f\u5b50", "\u7ec4\u7ec7", "\u6210", "\u7684"}, - []string{"\u795d", "\u4f60", "\u9a6c\u5230\u529f\u6210"}, - []string{"\u4ed6", "\u6389", "\u8fdb", "\u4e86", "\u65e0\u5e95", "\u65e0\u5e95\u6d1e", "\u91cc"}, - []string{"\u4e2d\u56fd", "\u7684", "\u9996\u90fd", "\u662f", "\u5317\u4eac"}, - []string{"\u5b59", "\u541b", "\u610f"}, - []string{"\u5916\u4ea4", "\u5916\u4ea4\u90e8", "\u53d1\u8a00", "\u53d1\u8a00\u4eba", "\u9a6c\u671d\u65ed"}, - []string{"\u9886\u5bfc", "\u9886\u5bfc\u4eba", "\u4f1a\u8bae", "\u548c", "\u7b2c\u56db", "\u56db\u5c4a", "\u7b2c\u56db\u5c4a", "\u4e1c\u4e9a", "\u5cf0\u4f1a"}, - []string{"\u5728", "\u8fc7\u53bb", "\u7684", "\u8fd9", "\u4e94\u5e74"}, - []string{"\u8fd8", "\u9700\u8981", "\u5f88", "\u957f", "\u7684", "\u8def", "\u8981", "\u8d70"}, - []string{"60", "\u5468\u5e74", "\u9996\u90fd", "\u9605\u5175"}, - []string{"\u4f60\u597d", "\u4eba\u4eec", "\u5ba1\u7f8e", "\u7684", "\u89c2\u70b9", "\u662f", "\u4e0d\u540c", "\u7684"}, - []string{"\u4e70", "\u6c34\u679c", "\u7136\u540e", "\u6765", "\u4e16\u535a", "\u535a\u56ed", "\u4e16\u535a\u56ed"}, - []string{"\u4e70", "\u6c34\u679c", "\u7136\u540e", "\u53bb", "\u4e16\u535a", "\u535a\u56ed", "\u4e16\u535a\u56ed"}, - []string{"\u4f46\u662f", "\u540e\u6765", "\u6211", "\u624d", "\u77e5\u9053", "\u4f60", "\u662f", "\u5bf9", "\u7684"}, - []string{"\u5b58\u5728", "\u5373", "\u5408\u7406"}, - []string{"\u7684", "\u7684", "\u7684", "\u7684", "\u7684", "\u5728", "\u7684", "\u7684", "\u7684", "\u7684", "\u5c31", "\u4ee5", "\u548c", "\u548c", "\u548c"}, - []string{"I", " ", "love", "\u4f60", "\uff0c", "\u4e0d\u4ee5", "\u4ee5\u4e3a", "\u4e0d\u4ee5\u4e3a\u803b", "\uff0c", "\u53cd", "\u4ee5\u4e3a", "rong"}, - []string{"\u56e0"}, + []string{"隐", "可夫", "马尔可", "马尔可夫"}, + []string{"雷猴", "是", "个", "好", "网站"}, + []string{"“", "Microsoft", "”", "一", "词", "由", "“", "MICROcomputer", "(", "微型", "计算", "算机", "计算机", ")", "”", "和", "“", "SOFTware", "(", "软件", ")", "”", "两", "部分", "组成"}, + []string{"草泥马", "和", "欺", "实", "马", "是", "今年", "的", "流行", "词汇"}, + []string{"伊", "藤", "洋华堂", "总府", "店"}, + []string{"中国", "科学", "学院", "计算", "技术", "研究", "科学院", "研究所", "中国科学院计算技术研究所"}, + []string{"罗密欧", "与", "朱丽叶"}, + []string{"我", "购买", "了", "道具", "和", "服装"}, + []string{"PS", ":", " ", "我", "觉得", "开源", "有", "一个", "好处", ",", "就是", "能够", "敦促", "自己", "不断", "改进", "不断改进", ",", "避免", "敞", "帚", "自珍"}, + []string{"湖北", "湖北省", "石首", "石首市"}, + []string{"湖北", "湖北省", "十堰", "十堰市"}, + []string{"经理", "总经理", "完成", "了", "这件", "事情"}, + []string{"电脑", "修好", "了"}, + []string{"做好", "了", "这件", "事情", "就", "一了百了", "了"}, + []string{"人们", "审美", "的", "观点", "是", "不同", "的"}, + []string{"我们", "买", "了", "一个", "美的", "空调"}, + []string{"线程", "初始", "初始化", "时", "我们", "要", "注意"}, + []string{"一个", "分子", "是", "由", "好多", "原子", "组织", "成", "的"}, + []string{"祝", "你", "马到功成"}, + []string{"他", "掉", "进", "了", "无底", "无底洞", "里"}, + []string{"中国", "的", "首都", "是", "北京"}, + []string{"孙", "君", "意"}, + []string{"外交", "外交部", "发言", "发言人", "马朝旭"}, + []string{"领导", "领导人", "会议", "和", "第四", "四届", "第四届", "东亚", "峰会"}, + []string{"在", "过去", "的", "这", "五年"}, + []string{"还", "需要", "很", "长", "的", "路", "要", "走"}, + []string{"60", "周年", "首都", "阅兵"}, + []string{"你好", "人们", "审美", "的", "观点", "是", "不同", "的"}, + []string{"买", "水果", "然后", "来", "世博", "博园", "世博园"}, + []string{"买", "水果", "然后", "去", "世博", "博园", "世博园"}, + []string{"但是", "后来", "我", "才", "知道", "你", "是", "对", "的"}, + []string{"存在", "即", "合理"}, + []string{"的", "的", "的", "的", "的", "在", "的", "的", "的", "的", "就", "以", "和", "和", "和"}, + []string{"I", " ", "love", "你", ",", "不以", "以为", "不以为耻", ",", "反", "以为", "rong"}, + []string{"因"}, []string{}, - []string{"hello", "\u4f60\u597d", "\u4eba\u4eec", "\u5ba1\u7f8e", "\u7684", "\u89c2\u70b9", "\u662f", "\u4e0d\u540c", "\u7684"}, - []string{"\u5f88", "\u597d", "\u4f46", "\u4e3b\u8981", "\u662f", "\u57fa\u4e8e", "\u7f51\u9875", "\u5f62\u5f0f"}, - []string{"hello", "\u4f60\u597d", "\u4eba\u4eec", "\u5ba1\u7f8e", "\u7684", "\u89c2\u70b9", "\u662f", "\u4e0d\u540c", "\u7684"}, - []string{"\u4ec0\u4e48", "\u4e3a\u4ec0\u4e48", "\u6211", "\u4e0d\u80fd", "\u62e5\u6709", "\u60f3\u8981", "\u7684", "\u751f\u6d3b"}, - []string{"\u540e\u6765", "\u6211", "\u624d"}, - []string{"\u6b64\u6b21", "\u6765", "\u4e2d\u56fd", "\u662f", "\u4e3a\u4e86"}, - []string{"\u4f7f\u7528", "\u4e86", "\u5b83", "\u5c31", "\u53ef\u4ee5", "\u89e3\u51b3", "\u4e00\u4e9b", "\u95ee\u9898"}, - []string{",", "\u4f7f\u7528", "\u4e86", "\u5b83", "\u5c31", "\u53ef\u4ee5", "\u89e3\u51b3", "\u4e00\u4e9b", "\u95ee\u9898"}, - []string{"\u5176\u5b9e", "\u4f7f\u7528", "\u4e86", "\u5b83", "\u5c31", "\u53ef\u4ee5", "\u89e3\u51b3", "\u4e00\u4e9b", "\u95ee\u9898"}, - []string{"\u597d\u4eba", "\u4f7f\u7528", "\u4e86", "\u5b83", "\u5c31", "\u53ef\u4ee5", "\u89e3\u51b3", "\u4e00\u4e9b", "\u95ee\u9898"}, - []string{"\u56e0\u4e3a", "\u662f\u56e0\u4e3a", "\u548c", "\u56fd\u5bb6"}, - []string{"\u8001\u5e74", "\u641c\u7d22", "\u8fd8", "\u652f\u6301"}, - []string{"\u5e72\u8106", "\u5c31", "\u628a", "\u90a3", "\u90e8", "\u8499", "\u4eba", "\u7684", "\u95f2", "\u6cd5", "\u7ed9", "\u5e9f", "\u4e86", "\u62c9\u5012", "\uff01", "RT", " ", "@", "laoshipukong", " ", ":", " ", "27", "\u65e5", "\uff0c", "\u5168\u56fd", "\u56fd\u4eba", "\u4eba\u5927", "\u5e38\u59d4", "\u59d4\u4f1a", "\u5e38\u59d4\u4f1a", "\u5168\u56fd\u4eba\u5927\u5e38\u59d4\u4f1a", "\u7b2c\u4e09", "\u4e09\u6b21", "\u7b2c\u4e09\u6b21", "\u5ba1\u8bae", "\u4fb5\u6743", "\u8d23\u4efb", "\u8d23\u4efb\u6cd5", "\u8349\u6848", "\uff0c", "\u5220\u9664", "\u4e86", "\u6709\u5173", "\u533b\u7597", "\u635f\u5bb3", "\u8d23\u4efb", "\u201c", "\u4e3e\u8bc1", "\u5012\u7f6e", "\u201d", "\u7684", "\u89c4\u5b9a", "\u3002", "\u5728", "\u533b\u60a3", "\u7ea0\u7eb7", "\u4e2d", "\u672c", "\u5df2", "\u5904\u4e8e", "\u5f31\u52bf", "\u5730\u4f4d", "\u7684", "\u6d88\u8d39", "\u6d88\u8d39\u8005", "\u7531\u6b64", "\u5c06", "\u9677\u5165", "\u4e0d\u590d", "\u4e07\u52ab\u4e0d\u590d", "\u7684", "\u5883\u5730", "\u3002", " "}, - []string{"\u5927"}, + []string{"hello", "你好", "人们", "审美", "的", "观点", "是", "不同", "的"}, + []string{"很", "好", "但", "主要", "是", "基于", "网页", "形式"}, + []string{"hello", "你好", "人们", "审美", "的", "观点", "是", "不同", "的"}, + []string{"什么", "为什么", "我", "不能", "拥有", "想要", "的", "生活"}, + []string{"后来", "我", "才"}, + []string{"此次", "来", "中国", "是", "为了"}, + []string{"使用", "了", "它", "就", "可以", "解决", "一些", "问题"}, + []string{",", "使用", "了", "它", "就", "可以", "解决", "一些", "问题"}, + []string{"其实", "使用", "了", "它", "就", "可以", "解决", "一些", "问题"}, + []string{"好人", "使用", "了", "它", "就", "可以", "解决", "一些", "问题"}, + []string{"因为", "是因为", "和", "国家"}, + []string{"老年", "搜索", "还", "支持"}, + []string{"干脆", "就", "把", "那", "部", "蒙", "人", "的", "闲", "法", "给", "废", "了", "拉倒", "!", "RT", " ", "@", "laoshipukong", " ", ":", " ", "27", "日", ",", "全国", "国人", "人大", "常委", "委会", "常委会", "全国人大常委会", "第三", "三次", "第三次", "审议", "侵权", "责任", "责任法", "草案", ",", "删除", "了", "有关", "医疗", "损害", "责任", "“", "举证", "倒置", "”", "的", "规定", "。", "在", "医患", "纠纷", "中", "本", "已", "处于", "弱势", "地位", "的", "消费", "消费者", "由此", "将", "陷入", "不复", "万劫不复", "的", "境地", "。", " "}, + []string{"大"}, []string{}, - []string{"\u4ed6", "\u8bf4", "\u7684", "\u786e\u5b9e", "\u5728", "\u7406"}, - []string{"\u957f\u6625", "\u5e02\u957f", "\u6625\u8282", "\u8bb2\u8bdd"}, - []string{"\u7ed3\u5a5a", "\u7684", "\u548c", "\u5c1a\u672a", "\u7ed3\u5a5a", "\u7684"}, - []string{"\u7ed3\u5408", "\u6210", "\u5206\u5b50", "\u65f6"}, - []string{"\u65c5\u6e38", "\u548c", "\u670d\u52a1", "\u662f", "\u6700\u597d", "\u7684"}, - []string{"\u8fd9\u4ef6", "\u4e8b\u60c5", "\u7684\u786e", "\u662f", "\u6211", "\u7684", "\u9519"}, - []string{"\u4f9b", "\u5927\u5bb6", "\u53c2\u8003", "\u6307\u6b63"}, - []string{"\u54c8\u5c14", "\u54c8\u5c14\u6ee8", "\u653f\u5e9c", "\u516c\u5e03", "\u584c", "\u6865", "\u539f\u56e0"}, - []string{"\u6211", "\u5728", "\u673a\u573a", "\u5165\u53e3", "\u5165\u53e3\u5904"}, - []string{"\u90a2", "\u6c38", "\u81e3", "\u6444\u5f71", "\u62a5\u9053"}, - []string{"BP", "\u795e\u7ecf", "\u7f51\u7edc", "\u795e\u7ecf\u7f51", "\u795e\u7ecf\u7f51\u7edc", "\u5982\u4f55", "\u8bad\u7ec3", "\u624d\u80fd", "\u5728", "\u5206\u7c7b", "\u65f6", "\u589e\u52a0", "\u533a\u5206", "\u5206\u5ea6", "\u533a\u5206\u5ea6", "\uff1f"}, - []string{"\u5357\u4eac", "\u4eac\u5e02", "\u5357\u4eac\u5e02", "\u957f\u6c5f", "\u5927\u6865", "\u957f\u6c5f\u5927\u6865"}, - []string{"\u5e94", "\u4e00\u4e9b", "\u4f7f\u7528", "\u7528\u8005", "\u4f7f\u7528\u8005", "\u7684", "\u5efa\u8bae", "\uff0c", "\u4e5f", "\u4e3a\u4e86", "\u4fbf\u4e8e", "\u5229\u7528", "NiuTrans", "\u7528\u4e8e", "SMT", "\u7814\u7a76"}, - []string{"\u957f\u6625", "\u957f\u6625\u5e02", "\u957f\u6625", "\u836f\u5e97"}, - []string{"\u9093\u9896\u8d85", "\u751f\u524d", "\u6700", "\u559c\u6b22", "\u7684", "\u8863\u670d"}, - []string{"\u9526\u6d9b", "\u80e1\u9526\u6d9b", "\u662f", "\u70ed\u7231", "\u4e16\u754c", "\u548c\u5e73", "\u7684", "\u653f\u6cbb", "\u653f\u6cbb\u5c40", "\u5e38\u59d4"}, - []string{"\u7a0b\u5e8f", "\u7a0b\u5e8f\u5458", "\u795d", "\u6d77\u6797", "\u548c", "\u6731", "\u4f1a", "\u9707", "\u662f", "\u5728", "\u5b59", "\u5065", "\u7684", "\u5de6\u9762", "\u548c", "\u53f3\u9762", ",", " ", "\u8303", "\u51ef", "\u5728", "\u6700", "\u53f3\u9762", ".", "\u518d", "\u5f80", "\u5de6", "\u662f", "\u674e", "\u677e", "\u6d2a"}, - []string{"\u4e00\u6b21", "\u4e00\u6b21\u6027", "\u4ea4", "\u591a\u5c11", "\u94b1"}, - []string{"\u4e24\u5757", "\u4e94", "\u4e00\u5957", "\uff0c", "\u4e09\u5757", "\u516b", "\u4e00\u65a4", "\uff0c", "\u56db\u5757", "\u4e03", "\u4e00\u672c", "\uff0c", "\u4e94\u5757", "\u516d", "\u4e00\u6761"}, - []string{"\u5c0f", "\u548c\u5c1a", "\u7559", "\u4e86", "\u4e00\u4e2a", "\u50cf", "\u5927", "\u548c\u5c1a", "\u4e00\u6837", "\u7684", "\u548c\u5c1a", "\u548c\u5c1a\u5934"}, - []string{"\u6211", "\u662f", "\u4e2d\u534e", "\u534e\u4eba", "\u4eba\u6c11", "\u5171\u548c", "\u5171\u548c\u56fd", "\u4e2d\u534e\u4eba\u6c11\u5171\u548c\u56fd", "\u516c\u6c11", ";", "\u6211", "\u7238\u7238", "\u662f", "\u5171\u548c", "\u5171\u548c\u515a", "\u515a\u5458", ";", " ", "\u5730\u94c1", "\u548c\u5e73", "\u548c\u5e73\u95e8", "\u7ad9"}, - []string{"\u5f20\u6653\u6885", "\u53bb", "\u4eba\u6c11", "\u533b\u9662", "\u505a", "\u4e86", "\u4e2a", "B\u8d85", "\u7136\u540e", "\u53bb", "\u4e70", "\u4e86", "\u4ef6", "T\u6064"}, - []string{"AT&T", "\u662f", "\u4e00\u4ef6", "\u4e0d\u9519", "\u7684", "\u516c\u53f8", "\uff0c", "\u7ed9", "\u4f60", "\u53d1", "offer", "\u4e86", "\u5417", "\uff1f"}, - []string{"C++", "\u548c", "c#", "\u662f", "\u4ec0\u4e48", "\u5173\u7cfb", "\uff1f", "11", "+", "122", "=", "133", "\uff0c", "\u662f", "\u5417", "\uff1f", "PI", "=", "3", ".", "14159"}, - []string{"\u4f60", "\u8ba4\u8bc6", "\u90a3\u4e2a", "\u548c", "\u4e3b\u5e2d", "\u63e1\u624b", "\u7684", "\u7684\u54e5", "\u5417", "\uff1f", "\u4ed6", "\u5f00", "\u4e00\u8f86", "\u9ed1\u8272", "\u7684\u58eb", "\u3002"}, - []string{"\u67aa\u6746", "\u6746\u5b50", "\u67aa\u6746\u5b50", "\u4e2d", "\u51fa", "\u653f\u6743"}, + []string{"他", "说", "的", "确实", "在", "理"}, + []string{"长春", "市长", "春节", "讲话"}, + []string{"结婚", "的", "和", "尚未", "结婚", "的"}, + []string{"结合", "成", "分子", "时"}, + []string{"旅游", "和", "服务", "是", "最好", "的"}, + []string{"这件", "事情", "的确", "是", "我", "的", "错"}, + []string{"供", "大家", "参考", "指正"}, + []string{"哈尔", "哈尔滨", "政府", "公布", "塌", "桥", "原因"}, + []string{"我", "在", "机场", "入口", "入口处"}, + []string{"邢", "永", "臣", "摄影", "报道"}, + []string{"BP", "神经", "网络", "神经网", "神经网络", "如何", "训练", "才能", "在", "分类", "时", "增加", "区分", "分度", "区分度", "?"}, + []string{"南京", "京市", "南京市", "长江", "大桥", "长江大桥"}, + []string{"应", "一些", "使用", "用者", "使用者", "的", "建议", ",", "也", "为了", "便于", "利用", "NiuTrans", "用于", "SMT", "研究"}, + []string{"长春", "长春市", "长春", "药店"}, + []string{"邓颖超", "生前", "最", "喜欢", "的", "衣服"}, + []string{"锦涛", "胡锦涛", "是", "热爱", "世界", "和平", "的", "政治", "政治局", "常委"}, + []string{"程序", "程序员", "祝", "海林", "和", "朱", "会", "震", "是", "在", "孙", "健", "的", "左面", "和", "右面", ",", " ", "范", "凯", "在", "最", "右面", ".", "再", "往", "左", "是", "李", "松", "洪"}, + []string{"一次", "一次性", "交", "多少", "钱"}, + []string{"两块", "五", "一套", ",", "三块", "八", "一斤", ",", "四块", "七", "一本", ",", "五块", "六", "一条"}, + []string{"小", "和尚", "留", "了", "一个", "像", "大", "和尚", "一样", "的", "和尚", "和尚头"}, + []string{"我", "是", "中华", "华人", "人民", "共和", "共和国", "中华人民共和国", "公民", ";", "我", "爸爸", "是", "共和", "共和党", "党员", ";", " ", "地铁", "和平", "和平门", "站"}, + []string{"张晓梅", "去", "人民", "医院", "做", "了", "个", "B超", "然后", "去", "买", "了", "件", "T恤"}, + []string{"AT&T", "是", "一件", "不错", "的", "公司", ",", "给", "你", "发", "offer", "了", "吗", "?"}, + []string{"C++", "和", "c#", "是", "什么", "关系", "?", "11", "+", "122", "=", "133", ",", "是", "吗", "?", "PI", "=", "3", ".", "14159"}, + []string{"你", "认识", "那个", "和", "主席", "握手", "的", "的哥", "吗", "?", "他", "开", "一辆", "黑色", "的士", "。"}, + []string{"枪杆", "杆子", "枪杆子", "中", "出", "政权"}, } userDictCutResult = [][]string{ - []string{"\u8fd9\u662f", "\u4e00\u4e2a", "\u4f38\u624b", "\u4e0d\u89c1", "\u4e94\u6307", "\u7684", "\u9ed1\u591c", "\u3002", "\u6211", "\u53eb", "\u5b59\u609f\u7a7a", "\uff0c", "\u6211", "\u7231\u5317\u4eac", "\uff0c", "\u6211", "\u7231", "Python", "\u548c", "C", "++", "\u3002"}, - []string{"\u6211", "\u4e0d", "\u559c\u6b22", "\u65e5\u672c", "\u548c", "\u670d", "\u3002"}, - []string{"\u96f7\u7334", "\u56de\u5f52\u4eba\u95f4", "\u3002"}, - []string{"\u5de5\u4fe1", "\u5904\u5973", "\u5e72\u4e8b", "\u6bcf", "\u6708", "\u7ecf\u8fc7", "\u4e0b", "\u5c5e", "\u79d1\u5ba4", "\u90fd", "\u8981", "\u4eb2\u53e3", "\u4ea4\u4ee3", "24", "\u53e3\u4ea4\u6362\u673a", "\u7b49", "\u6280\u672f\u6027", "\u5668\u4ef6", "\u7684", "\u5b89\u88c5", "\u5de5\u4f5c"}, - []string{"\u6211", "\u9700\u8981", "\u5ec9\u79df\u623f"}, - []string{"\u6c38\u548c\u670d", "\u88c5\u9970\u54c1", "\u6709", "\u9650\u516c\u53f8"}, - []string{"\u6211", "\u7231\u5317\u4eac", "\u5929\u5b89\u95e8"}, + []string{"这是", "一个", "伸手", "不见", "五指", "的", "黑夜", "。", "我", "叫", "孙悟空", ",", "我", "爱北京", ",", "我", "爱", "Python", "和", "C", "++", "。"}, + []string{"我", "不", "喜欢", "日本", "和", "服", "。"}, + []string{"雷猴", "回归人间", "。"}, + []string{"工信", "处女", "干事", "每", "月", "经过", "下", "属", "科室", "都", "要", "亲口", "交代", "24", "口交换机", "等", "技术性", "器件", "的", "安装", "工作"}, + []string{"我", "需要", "廉租房"}, + []string{"永和服", "装饰品", "有", "限公司"}, + []string{"我", "爱北京", "天安门"}, []string{"abc"}, - []string{"\u9690\u9a6c\u5c14", "\u53ef\u592b"}, - []string{"\u96f7\u7334", "\u662f", "\u4e2a", "\u597d", "\u7f51\u7ad9"}, - []string{"\u201c", "Microsoft", "\u201d", "\u4e00\u8bcd", "\u7531", "\u201c", "MICROcomputer", "\uff08", "\u5fae\u578b", "\u8ba1\u7b97\u673a", "\uff09", "\u201d", "\u548c", "\u201c", "SOFTware", "\uff08", "\u8f6f\u4ef6", "\uff09", "\u201d", "\u4e24\u90e8\u5206", "\u7ec4\u6210"}, - []string{"\u8349\u6ce5", "\u9a6c", "\u548c", "\u6b3a\u5b9e", "\u9a6c", "\u662f", "\u4eca", "\u5e74", "\u7684", "\u6d41\u884c", "\u8bcd\u6c47"}, - []string{"\u4f0a\u85e4\u6d0b\u534e\u5802", "\u603b\u5e9c", "\u5e97"}, - []string{"\u4e2d\u56fd", "\u79d1\u5b66\u9662", "\u8ba1\u7b97", "\u6280\u672f", "\u7814\u7a76", "\u6240"}, - []string{"\u7f57\u5bc6\u6b27", "\u4e0e", "\u6731\u4e3d\u53f6"}, - []string{"\u6211\u8d2d", "\u4e70", "\u4e86", "\u9053", "\u5177", "\u548c", "\u670d\u88c5"}, - []string{"PS", ":", " ", "\u6211\u89c9", "\u5f97", "\u5f00\u6e90", "\u6709", "\u4e00\u4e2a", "\u597d", "\u5904", "\uff0c", "\u5c31", "\u662f", "\u80fd\u591f", "\u6566\u4fc3", "\u81ea\u5df1", "\u4e0d\u65ad", "\u6539\u8fdb", "\uff0c", "\u907f\u514d", "\u655e\u5e1a", "\u81ea\u73cd"}, - []string{"\u6e56\u5317\u7701", "\u77f3\u9996\u5e02"}, - []string{"\u6e56\u5317\u7701", "\u5341\u5830\u5e02"}, - []string{"\u603b\u7ecf\u7406", "\u5b8c\u6210", "\u4e86", "\u8fd9\u4ef6", "\u4e8b\u60c5"}, - []string{"\u7535\u8111", "\u4fee\u597d", "\u4e86"}, - []string{"\u505a", "\u597d", "\u4e86", "\u8fd9\u4ef6", "\u4e8b\u60c5", "\u5c31", "\u4e00", "\u4e86", "\u767e", "\u4e86", "\u4e86"}, - []string{"\u4eba\u4eec", "\u5ba1\u7f8e", "\u7684", "\u89c2\u70b9", "\u662f", "\u4e0d\u540c", "\u7684"}, - []string{"\u6211\u4eec", "\u4e70", "\u4e86", "\u4e00\u4e2a", "\u7f8e", "\u7684", "\u7a7a\u8c03"}, - []string{"\u7ebf\u7a0b", "\u521d\u59cb", "\u5316\u65f6", "\u6211\u4eec", "\u8981", "\u6ce8\u610f"}, - []string{"\u4e00\u4e2a", "\u5206\u5b50", "\u662f", "\u7531", "\u597d", "\u591a", "\u539f\u5b50", "\u7ec4\u7ec7\u6210", "\u7684"}, - []string{"\u795d", "\u4f60", "\u9a6c\u5230", "\u529f\u6210"}, - []string{"\u4ed6", "\u6389", "\u8fdb", "\u4e86", "\u65e0\u5e95", "\u6d1e\u91cc"}, - []string{"\u4e2d\u56fd", "\u7684", "\u9996", "\u90fd", "\u662f", "\u5317\u4eac"}, - []string{"\u5b59\u541b\u610f"}, - []string{"\u5916\u4ea4\u90e8", "\u53d1\u8a00\u4eba", "\u9a6c\u671d\u65ed"}, - []string{"\u9886\u5bfc", "\u4eba\u4f1a\u8bae", "\u548c", "\u7b2c\u56db\u5c4a", "\u4e1c\u4e9a\u5cf0", "\u4f1a"}, - []string{"\u5728", "\u8fc7", "\u53bb", "\u7684", "\u8fd9\u4e94\u5e74"}, - []string{"\u8fd8", "\u9700\u8981", "\u5f88\u957f", "\u7684", "\u8def", "\u8981", "\u8d70"}, - []string{"60", "\u5468\u5e74\u9996", "\u90fd", "\u9605\u5175"}, - []string{"\u4f60", "\u597d\u4eba", "\u4eec", "\u5ba1\u7f8e", "\u7684", "\u89c2\u70b9", "\u662f", "\u4e0d\u540c", "\u7684"}, - []string{"\u4e70\u6c34\u679c", "\u7136\u540e", "\u6765", "\u4e16\u535a\u56ed"}, - []string{"\u4e70\u6c34\u679c", "\u7136\u540e", "\u53bb", "\u4e16\u535a\u56ed"}, - []string{"\u4f46", "\u662f", "\u540e", "\u6765", "\u6211", "\u624d", "\u77e5\u9053", "\u4f60", "\u662f", "\u5bf9", "\u7684"}, - []string{"\u5b58\u5728", "\u5373", "\u5408\u7406"}, - []string{"\u7684", "\u7684", "\u7684", "\u7684", "\u7684", "\u5728", "\u7684", "\u7684", "\u7684", "\u7684", "\u5c31", "\u4ee5", "\u548c", "\u548c", "\u548c"}, - []string{"I", " ", "love", "\u4f60", "\uff0c", "\u4e0d\u4ee5", "\u4e3a\u803b", "\uff0c", "\u53cd\u4ee5", "\u4e3a", "rong"}, - []string{"\u56e0"}, + []string{"隐马尔", "可夫"}, + []string{"雷猴", "是", "个", "好", "网站"}, + []string{"“", "Microsoft", "”", "一词", "由", "“", "MICROcomputer", "(", "微型", "计算机", ")", "”", "和", "“", "SOFTware", "(", "软件", ")", "”", "两部分", "组成"}, + []string{"草泥", "马", "和", "欺实", "马", "是", "今", "年", "的", "流行", "词汇"}, + []string{"伊藤洋华堂", "总府", "店"}, + []string{"中国", "科学院", "计算", "技术", "研究", "所"}, + []string{"罗密欧", "与", "朱丽叶"}, + []string{"我购", "买", "了", "道", "具", "和", "服装"}, + []string{"PS", ":", " ", "我觉", "得", "开源", "有", "一个", "好", "处", ",", "就", "是", "能够", "敦促", "自己", "不断", "改进", ",", "避免", "敞帚", "自珍"}, + []string{"湖北省", "石首市"}, + []string{"湖北省", "十堰市"}, + []string{"总经理", "完成", "了", "这件", "事情"}, + []string{"电脑", "修好", "了"}, + []string{"做", "好", "了", "这件", "事情", "就", "一", "了", "百", "了", "了"}, + []string{"人们", "审美", "的", "观点", "是", "不同", "的"}, + []string{"我们", "买", "了", "一个", "美", "的", "空调"}, + []string{"线程", "初始", "化时", "我们", "要", "注意"}, + []string{"一个", "分子", "是", "由", "好", "多", "原子", "组织成", "的"}, + []string{"祝", "你", "马到", "功成"}, + []string{"他", "掉", "进", "了", "无底", "洞里"}, + []string{"中国", "的", "首", "都", "是", "北京"}, + []string{"孙君意"}, + []string{"外交部", "发言人", "马朝旭"}, + []string{"领导", "人会议", "和", "第四届", "东亚峰", "会"}, + []string{"在", "过", "去", "的", "这五年"}, + []string{"还", "需要", "很长", "的", "路", "要", "走"}, + []string{"60", "周年首", "都", "阅兵"}, + []string{"你", "好人", "们", "审美", "的", "观点", "是", "不同", "的"}, + []string{"买水果", "然后", "来", "世博园"}, + []string{"买水果", "然后", "去", "世博园"}, + []string{"但", "是", "后", "来", "我", "才", "知道", "你", "是", "对", "的"}, + []string{"存在", "即", "合理"}, + []string{"的", "的", "的", "的", "的", "在", "的", "的", "的", "的", "就", "以", "和", "和", "和"}, + []string{"I", " ", "love", "你", ",", "不以", "为耻", ",", "反以", "为", "rong"}, + []string{"因"}, []string{}, - []string{"hello", "\u4f60", "\u597d\u4eba", "\u4eec", "\u5ba1\u7f8e", "\u7684", "\u89c2\u70b9", "\u662f", "\u4e0d\u540c", "\u7684"}, - []string{"\u5f88", "\u597d", "\u4f46", "\u4e3b\u8981", "\u662f", "\u57fa\u4e8e", "\u7f51\u9875", "\u5f62\u5f0f"}, - []string{"hello", "\u4f60", "\u597d\u4eba", "\u4eec", "\u5ba1\u7f8e", "\u7684", "\u89c2\u70b9", "\u662f", "\u4e0d\u540c", "\u7684"}, - []string{"\u4e3a", "\u4ec0\u4e48", "\u6211", "\u4e0d\u80fd", "\u62e5\u6709", "\u60f3", "\u8981", "\u7684", "\u751f\u6d3b"}, - []string{"\u540e\u6765", "\u6211", "\u624d"}, - []string{"\u6b64\u6b21", "\u6765", "\u4e2d\u56fd", "\u662f", "\u4e3a", "\u4e86"}, - []string{"\u4f7f\u7528", "\u4e86", "\u5b83", "\u5c31", "\u53ef\u4ee5", "\u89e3\u51b3", "\u4e00\u4e9b", "\u95ee\u9898"}, - []string{",", "\u4f7f\u7528", "\u4e86", "\u5b83", "\u5c31", "\u53ef\u4ee5", "\u89e3\u51b3", "\u4e00\u4e9b", "\u95ee\u9898"}, - []string{"\u5176\u5b9e", "\u4f7f", "\u7528", "\u4e86", "\u5b83", "\u5c31", "\u53ef\u4ee5", "\u89e3\u51b3", "\u4e00\u4e9b", "\u95ee\u9898"}, - []string{"\u597d\u4eba", "\u4f7f\u7528", "\u4e86", "\u5b83", "\u5c31", "\u53ef\u4ee5", "\u89e3\u51b3", "\u4e00\u4e9b", "\u95ee\u9898"}, - []string{"\u662f", "\u56e0\u4e3a", "\u548c", "\u56fd\u5bb6"}, - []string{"\u8001\u5e74", "\u641c\u7d22", "\u8fd8", "\u652f\u6301"}, - []string{"\u5e72\u8106", "\u5c31", "\u628a", "\u90a3\u90e8", "\u8499\u4eba", "\u7684", "\u95f2\u6cd5", "\u7ed9", "\u5e9f", "\u4e86", "\u62c9", "\u5012", "\uff01", "RT", " ", "@", "laoshipukong", " ", ":", " ", "27", "\u65e5", "\uff0c", "\u5168\u56fd\u4eba", "\u5927\u5e38\u59d4\u4f1a", "\u7b2c\u4e09\u6b21", "\u5ba1\u8bae", "\u4fb5\u6743\u8d23", "\u4efb\u6cd5", "\u8349\u6848", "\uff0c", "\u5220\u9664", "\u4e86", "\u6709", "\u5173\u533b\u7597", "\u635f\u5bb3", "\u8d23\u4efb", "\u201c", "\u4e3e\u8bc1", "\u5012", "\u7f6e", "\u201d", "\u7684", "\u89c4\u5b9a", "\u3002", "\u5728", "\u533b\u60a3", "\u7ea0\u7eb7", "\u4e2d\u672c", "\u5df2", "\u5904\u4e8e", "\u5f31\u52bf", "\u5730\u4f4d", "\u7684", "\u6d88\u8d39\u8005", "\u7531", "\u6b64", "\u5c06", "\u9677\u5165", "\u4e07\u52ab", "\u4e0d\u590d", "\u7684", "\u5883\u5730", "\u3002", " "}, - []string{"\u5927"}, + []string{"hello", "你", "好人", "们", "审美", "的", "观点", "是", "不同", "的"}, + []string{"很", "好", "但", "主要", "是", "基于", "网页", "形式"}, + []string{"hello", "你", "好人", "们", "审美", "的", "观点", "是", "不同", "的"}, + []string{"为", "什么", "我", "不能", "拥有", "想", "要", "的", "生活"}, + []string{"后来", "我", "才"}, + []string{"此次", "来", "中国", "是", "为", "了"}, + []string{"使用", "了", "它", "就", "可以", "解决", "一些", "问题"}, + []string{",", "使用", "了", "它", "就", "可以", "解决", "一些", "问题"}, + []string{"其实", "使", "用", "了", "它", "就", "可以", "解决", "一些", "问题"}, + []string{"好人", "使用", "了", "它", "就", "可以", "解决", "一些", "问题"}, + []string{"是", "因为", "和", "国家"}, + []string{"老年", "搜索", "还", "支持"}, + []string{"干脆", "就", "把", "那部", "蒙人", "的", "闲法", "给", "废", "了", "拉", "倒", "!", "RT", " ", "@", "laoshipukong", " ", ":", " ", "27", "日", ",", "全国人", "大常委会", "第三次", "审议", "侵权责", "任法", "草案", ",", "删除", "了", "有", "关医疗", "损害", "责任", "“", "举证", "倒", "置", "”", "的", "规定", "。", "在", "医患", "纠纷", "中本", "已", "处于", "弱势", "地位", "的", "消费者", "由", "此", "将", "陷入", "万劫", "不复", "的", "境地", "。", " "}, + []string{"大"}, []string{}, - []string{"\u4ed6", "\u8bf4", "\u7684", "\u786e\u5b9e", "\u5728", "\u7406"}, - []string{"\u957f\u6625\u5e02", "\u957f\u6625\u8282", "\u8bb2\u8bdd"}, - []string{"\u7ed3\u5a5a", "\u7684", "\u548c", "\u5c1a\u672a", "\u7ed3\u5a5a", "\u7684"}, - []string{"\u7ed3\u5408\u6210", "\u5206\u5b50", "\u65f6"}, - []string{"\u65c5\u6e38", "\u548c", "\u670d\u52a1", "\u662f", "\u6700", "\u597d", "\u7684"}, - []string{"\u8fd9\u4ef6", "\u4e8b\u60c5", "\u7684", "\u786e\u662f", "\u6211", "\u7684", "\u9519"}, - []string{"\u4f9b\u5927\u5bb6", "\u53c2\u8003", "\u6307\u6b63"}, - []string{"\u54c8\u5c14\u6ee8", "\u653f\u5e9c", "\u516c\u5e03\u584c\u6865", "\u539f\u56e0"}, - []string{"\u6211", "\u5728", "\u673a\u573a", "\u5165\u53e3", "\u5904"}, - []string{"\u90a2\u6c38\u81e3", "\u6444\u5f71", "\u62a5\u9053"}, - []string{"BP", "\u795e\u7ecf", "\u7f51\u7edc", "\u5982\u4f55", "\u8bad\u7ec3", "\u624d", "\u80fd", "\u5728", "\u5206\u7c7b", "\u65f6", "\u589e\u52a0\u533a", "\u5206\u5ea6", "\uff1f"}, - []string{"\u5357\u4eac\u5e02", "\u957f\u6c5f\u5927\u6865"}, - []string{"\u5e94\u4e00\u4e9b", "\u4f7f", "\u7528\u8005", "\u7684", "\u5efa\u8bae", "\uff0c", "\u4e5f", "\u4e3a", "\u4e86", "\u4fbf", "\u4e8e", "\u5229\u7528", "NiuTrans", "\u7528\u4e8e", "SMT", "\u7814\u7a76"}, - []string{"\u957f\u6625\u5e02", "\u957f\u6625\u836f\u5e97"}, - []string{"\u9093\u9896", "\u8d85\u751f", "\u524d", "\u6700", "\u559c\u6b22", "\u7684", "\u8863\u670d"}, - []string{"\u80e1\u9526\u6d9b", "\u662f", "\u70ed\u7231\u4e16\u754c", "\u548c", "\u5e73", "\u7684", "\u653f\u6cbb\u5c40", "\u5e38\u59d4"}, - []string{"\u7a0b\u5e8f\u5458", "\u795d\u6d77\u6797", "\u548c", "\u6731\u4f1a\u9707", "\u662f", "\u5728", "\u5b59\u5065", "\u7684", "\u5de6\u9762", "\u548c", "\u53f3\u9762", ",", " ", "\u8303\u51ef", "\u5728", "\u6700\u53f3\u9762", ".", "\u518d\u5f80", "\u5de6", "\u662f", "\u674e\u677e\u6d2a"}, - []string{"\u4e00\u6b21\u6027", "\u4ea4\u591a\u5c11", "\u94b1"}, - []string{"\u4e24\u5757", "\u4e94\u4e00\u5957", "\uff0c", "\u4e09\u5757", "\u516b\u4e00\u65a4", "\uff0c", "\u56db\u5757", "\u4e03", "\u4e00\u672c", "\uff0c", "\u4e94\u5757", "\u516d", "\u4e00\u6761"}, - []string{"\u5c0f", "\u548c", "\u5c1a\u7559", "\u4e86", "\u4e00\u4e2a", "\u50cf", "\u5927", "\u548c", "\u5c1a", "\u4e00\u6837", "\u7684", "\u548c", "\u5c1a\u5934"}, - []string{"\u6211", "\u662f", "\u4e2d\u534e\u4eba\u6c11\u5171\u548c\u56fd", "\u516c\u6c11", ";", "\u6211", "\u7238\u7238", "\u662f", "\u5171", "\u548c", "\u515a", "\u515a\u5458", ";", " ", "\u5730\u94c1", "\u548c", "\u5e73\u95e8", "\u7ad9"}, - []string{"\u5f20\u6653\u6885", "\u53bb", "\u4eba\u6c11\u533b\u9662", "\u505a", "\u4e86", "\u4e2a", "B", "\u8d85\u7136", "\u540e", "\u53bb", "\u4e70", "\u4e86", "\u4ef6", "T", "\u6064"}, - []string{"AT", "&", "T", "\u662f", "\u4e00\u4ef6", "\u4e0d\u9519", "\u7684", "\u516c\u53f8", "\uff0c", "\u7ed9", "\u4f60", "\u53d1", "offer", "\u4e86", "\u5417", "\uff1f"}, - []string{"C", "++", "\u548c", "c", "#", "\u662f", "\u4ec0\u4e48", "\u5173\u7cfb", "\uff1f", "11", "+", "122", "=", "133", "\uff0c", "\u662f", "\u5417", "\uff1f", "PI", "=", "3.14159"}, - []string{"\u4f60", "\u8ba4\u8bc6", "\u90a3\u4e2a", "\u548c", "\u4e3b\u5e2d\u63e1", "\u624b", "\u7684", "\u7684", "\u54e5", "\u5417", "\uff1f", "\u4ed6\u5f00", "\u4e00\u8f86", "\u9ed1\u8272", "\u7684", "\u58eb", "\u3002"}, - []string{"\u67aa\u6746\u5b50", "\u4e2d", "\u51fa\u653f\u6743"}, + []string{"他", "说", "的", "确实", "在", "理"}, + []string{"长春市", "长春节", "讲话"}, + []string{"结婚", "的", "和", "尚未", "结婚", "的"}, + []string{"结合成", "分子", "时"}, + []string{"旅游", "和", "服务", "是", "最", "好", "的"}, + []string{"这件", "事情", "的", "确是", "我", "的", "错"}, + []string{"供大家", "参考", "指正"}, + []string{"哈尔滨", "政府", "公布塌桥", "原因"}, + []string{"我", "在", "机场", "入口", "处"}, + []string{"邢永臣", "摄影", "报道"}, + []string{"BP", "神经", "网络", "如何", "训练", "才", "能", "在", "分类", "时", "增加区", "分度", "?"}, + []string{"南京市", "长江大桥"}, + []string{"应一些", "使", "用者", "的", "建议", ",", "也", "为", "了", "便", "于", "利用", "NiuTrans", "用于", "SMT", "研究"}, + []string{"长春市", "长春药店"}, + []string{"邓颖", "超生", "前", "最", "喜欢", "的", "衣服"}, + []string{"胡锦涛", "是", "热爱世界", "和", "平", "的", "政治局", "常委"}, + []string{"程序员", "祝海林", "和", "朱会震", "是", "在", "孙健", "的", "左面", "和", "右面", ",", " ", "范凯", "在", "最右面", ".", "再往", "左", "是", "李松洪"}, + []string{"一次性", "交多少", "钱"}, + []string{"两块", "五一套", ",", "三块", "八一斤", ",", "四块", "七", "一本", ",", "五块", "六", "一条"}, + []string{"小", "和", "尚留", "了", "一个", "像", "大", "和", "尚", "一样", "的", "和", "尚头"}, + []string{"我", "是", "中华人民共和国", "公民", ";", "我", "爸爸", "是", "共", "和", "党", "党员", ";", " ", "地铁", "和", "平门", "站"}, + []string{"张晓梅", "去", "人民医院", "做", "了", "个", "B", "超然", "后", "去", "买", "了", "件", "T", "恤"}, + []string{"AT", "&", "T", "是", "一件", "不错", "的", "公司", ",", "给", "你", "发", "offer", "了", "吗", "?"}, + []string{"C", "++", "和", "c", "#", "是", "什么", "关系", "?", "11", "+", "122", "=", "133", ",", "是", "吗", "?", "PI", "=", "3.14159"}, + []string{"你", "认识", "那个", "和", "主席握", "手", "的", "的", "哥", "吗", "?", "他开", "一辆", "黑色", "的", "士", "。"}, + []string{"枪杆子", "中", "出政权"}, } ) @@ -751,7 +746,7 @@ func TestLoadUserDict(t *testing.T) { LoadUserDict("userdict.txt") sentence := "李小福是创新办主任也是云计算方面的专家; 什么是八一双鹿例如我输入一个带“韩玉赏鉴”的标题,在自定义词库中也增加了此词为N类型" - result := []string{"\u674e\u5c0f\u798f", "\u662f", "\u521b\u65b0\u529e", "\u4e3b\u4efb", "\u4e5f", "\u662f", "\u4e91\u8ba1\u7b97", "\u65b9\u9762", "\u7684", "\u4e13\u5bb6", ";", " ", "\u4ec0\u4e48", "\u662f", "\u516b\u4e00\u53cc\u9e7f", "\u4f8b\u5982", "\u6211", "\u8f93\u5165", "\u4e00\u4e2a", "\u5e26", "\u201c", "\u97e9\u7389\u8d4f\u9274", "\u201d", "\u7684", "\u6807\u9898", "\uff0c", "\u5728", "\u81ea\u5b9a\u4e49\u8bcd", "\u5e93\u4e2d", "\u4e5f", "\u589e\u52a0", "\u4e86", "\u6b64", "\u8bcd\u4e3a", "N", "\u7c7b\u578b"} + result := []string{"李小福", "是", "创新办", "主任", "也", "是", "云计算", "方面", "的", "专家", ";", " ", "什么", "是", "八一双鹿", "例如", "我", "输入", "一个", "带", "“", "韩玉赏鉴", "”", "的", "标题", ",", "在", "自定义词", "库中", "也", "增加", "了", "此", "词为", "N", "类型"} words := Cut(sentence, false, true) if len(words) != len(result) { @@ -776,7 +771,7 @@ func TestLoadUserDict(t *testing.T) { } sentence = "python 的正则表达式是好用的" - result = []string{"python", " ", "\u7684", "\u6b63\u5219\u8868\u8fbe\u5f0f", "\u662f", "\u597d\u7528", "\u7684"} + result = []string{"python", " ", "的", "正则表达式", "是", "好用", "的"} words = Cut(sentence, false, true) if len(words) != len(result) { t.Error(words)