Logstash处理json格式日志文件

假设日志文件中的每一行记录格式为json的，如：

{"Method":"JSAPI.JSTicket","Message":"JSTicket:kgt8ON7yVITDhtdwci0qeZg4L-Dj1O5WF42Nog47n_0aGF4WPJDIF2UA9MeS8GzLe6MPjyp2WlzvsL0nlvkohw","CreateTime":"2015/10/13 9:39:59","AppGUID":"cb54ba2d-1d38-45f2-9ed1-abff0bf7dd3d","_PartitionKey":"cb54ba2d-1d38-45f2-9ed1-abff0bf7dd3d","_RowKey":"1444700398710_ad4d33ce-a9d9-4d11-932e-e2ccebdb726c","_UnixTS":1444700398710}

默认配置下，logstash处理插入进elasticsearch后，查到的结果是这样的：

{
    "_index": "logstash-2015.10.16",
    "_type": "voip_feedback",
    "_id": "sheE9eXiQASMDVtRJ0EYcg",
    "_version": 1,
    "found": true,
    "_source": {
        "message": "{"Method":"JSAPI.JSTicket","Message":"JSTicket:kgt8ON7yVITDhtdwci0qeZg4L-Dj1O5WF42Nog47n_0aGF4WPJDIF2UA9MeS8GzLe6MPjyp2WlzvsL0nlvkohw","CreateTime":"2015/10/13 9:39:59","AppGUID":"cb54ba2d-1d38-45f2-9ed1-abff0bf7dd3d","_PartitionKey":"cb54ba2d-1d38-45f2-9ed1-abff0bf7dd3d","_RowKey":"1444700398710_ad4d33ce-a9d9-4d11-932e-e2ccebdb726c","_UnixTS":1444700398710}",
        "@version": "1",
        "@timestamp": "2015-10-16T00:39:51.252Z",
        "type": "voip_feedback",
        "host": "ipphone",
        "path": "/usr1/data/voip_feedback.txt"
    }
}

即会将json记录做为一个字符串放到”message”下，但是我是想让logstash自动解析json记录，将各字段放入elasticsearch中。有三种配置方式可以实现。

第一种，直接设置format => json

    file {
        type => "voip_feedback"
        path => ["/usr1/data/voip_feedback.txt"]  
        format => json
        sincedb_path => "/home/jfy/soft/logstash-1.4.2/voip_feedback.access"     
    }

这种方式查询出的结果是：

{
    "_index": "logstash-2015.10.16",
    "_type": "voip_feedback",
    "_id": "NrNX8HrxSzCvLl4ilKeyCQ",
    "_version": 1,
    "found": true,
    "_source": {
        "Method": "JSAPI.JSTicket",
        "Message": "JSTicket:kgt8ON7yVITDhtdwci0qeZg4L-Dj1O5WF42Nog47n_0aGF4WPJDIF2UA9MeS8GzLe6MPjyp2WlzvsL0nlvkohw",
        "CreateTime": "2015/10/13 9:39:59",
        "AppGUID": "cb54ba2d-1d38-45f2-9ed1-abff0bf7dd3d",
        "_PartitionKey": "cb54ba2d-1d38-45f2-9ed1-abff0bf7dd3d",
        "_RowKey": "1444700398710_ad4d33ce-a9d9-4d11-932e-e2ccebdb726c",
        "_UnixTS": 1444700398710,
        "@version": "1",
        "@timestamp": "2015-10-16T00:16:11.455Z",
        "type": "voip_feedback",
        "host": "ipphone",
        "path": "/usr1/data/voip_feedback.txt"
    }
}

可以看到，json记录已经被直接解析成各字段放入到了_source中，但是原始记录内容没有被保存

第二种，使用codec => json

    file {
        type => "voip_feedback"
        path => ["/usr1/data/voip_feedback.txt"]  
        sincedb_path => "/home/jfy/soft/logstash-1.4.2/voip_feedback.access"
        codec => json {
            charset => "UTF-8"
        }       
    }

这种方式查询出的结果与第一种一样，字段被解析，原始记录内容也没有保存

第三种，使用filter json

filter {
    if [type] == "voip_feedback" {
        json {
            source => "message"
            #target => "doc"
            #remove_field => ["message"]
        }        
    }
}

这种方式查询出的结果是这样的：

{
    "_index": "logstash-2015.10.16",
    "_type": "voip_feedback",
    "_id": "CUtesLCETAqhX73NKXZfug",
    "_version": 1,
    "found": true,
    "_source": {
        "message": "{"Method222":"JSAPI.JSTicket","Message":"JSTicket:kgt8ON7yVITDhtdwci0qeZg4L-Dj1O5WF42Nog47n_0aGF4WPJDIF2UA9MeS8GzLe6MPjyp2WlzvsL0nlvkohw","CreateTime":"2015/10/13 9:39:59","AppGUID":"cb54ba2d-1d38-45f2-9ed1-abff0bf7dd3d","_PartitionKey":"cb54ba2d-1d38-45f2-9ed1-abff0bf7dd3d","_RowKey":"1444700398710_ad4d33ce-a9d9-4d11-932e-e2ccebdb726c","_UnixTS":1444700398710}",
        "@version": "1",
        "@timestamp": "2015-10-16T00:28:20.018Z",
        "type": "voip_feedback",
        "host": "ipphone",
        "path": "/usr1/data/voip_feedback.txt",
        "Method222": "JSAPI.JSTicket",
        "Message": "JSTicket:kgt8ON7yVITDhtdwci0qeZg4L-Dj1O5WF42Nog47n_0aGF4WPJDIF2UA9MeS8GzLe6MPjyp2WlzvsL0nlvkohw",
        "CreateTime": "2015/10/13 9:39:59",
        "AppGUID": "cb54ba2d-1d38-45f2-9ed1-abff0bf7dd3d",
        "_PartitionKey": "cb54ba2d-1d38-45f2-9ed1-abff0bf7dd3d",
        "_RowKey": "1444700398710_ad4d33ce-a9d9-4d11-932e-e2ccebdb726c",
        "_UnixTS": 1444700398710,
        "tags": [
            "111",
            "222"
        ]
    }
}

可以看到，原始记录被保存，同时字段也被解析保存。如果确认不需要保存原始记录内容，可以加设置：remove_field => [“message”]

比较以上三种方法，最方便直接的就是在file中设置format => json

另外需要注意的是，logstash会在向es插入数据时默认会在_source下增加type,host,path三个字段，如果json内容中本身也含有type,host,path字段，那么解析后将覆盖掉logstash默认的这三个字段，尤其是type字段，这个同时也是做为index/type用的，覆盖掉后，插入进es中的index/type就是json数据记录中的内容，将不再是logstash config中配置的type值。

这时需要设置filter.json.target，设置该字段后json原始内容将不会放在_source下，而是放到设置的”doc”下：

{
    "_index": "logstash-2015.10.20",
    "_type": "3alogic_log",
    "_id": "xfj3ngd5S3iH2YABjyU6EA",
    "_version": 1,
    "found": true,
    "_source": {
        "@version": "1",
        "@timestamp": "2015-10-20T11:36:24.503Z",
        "type": "3alogic_log",
        "host": "server114",
        "path": "/usr1/app/log/mysql_3alogic_log.log",
        "doc": {
            "id": 633796,
            "identity": "13413602120",
            "type": "EAP_TYPE_PEAP",
            "apmac": "88-25-93-4E-1F-96",
            "usermac": "00-65-E0-31-62-5D",
            "time": "20151020-193624",
            "apmaccompany": "TP-LINK TECHNOLOGIES CO.,LTD",
            "usermaccompany": ""
        }
    }
}

这样就不会覆盖掉_source下的type,host,path值 
而且在kibana中显示时字段名称为doc.type,doc.id…

---

json中嵌套json：

上传的json：

{
    "indexName": "tv_app_default",
    "baseInfo": {
      "deviceId": "458ec202-e02e-4b82-a7ca-18e5cb4e3df1",
      "deviceModel": "PRO 7-H",
      "deviceSubModel": "",
      "devicePlatform": "Android",
      "appName": "IMetis",
      "appVersion": "1.0",
      "networkStatus": "wifi连接",
      "systemVersion": "24"
    },
    "event": {
      "id": "cd478c7b167a7a1030deaeb40036b0f9",
      "name": "TestFragment.java_com.italkbb.test.TestFragment_Bundle[{name=test1}]",
      "event_index": "tv_app_default",
      "event_level": "verbose",
      "timestamp": "2019-03-20T15:15:15.029+08:00",
      "duration": "13043968231158",
      "instant": "0",
      "line": -1
    }
  }

filter里面这么写，会把event和baseInfo里面的json字串解析出来。

filter {
   json {
      source => "message"
      remove_field => ["message"]
    }

    mutate {
      add_field => { "eventtmp" => "%{event}" }
    }
    json {
      source => "eventtmp"
      remove_field => ["eventtmp"]
    }

    mutate {
      add_field => { "baseInfotmp" => "%{baseInfo}" }
    }
    json {
      source => "baseInfotmp"
      remove_field => ["baseInfotmp" , "baseInfo"]   #只能加一个数组删除 remove_field => ["eventtmp"] 这句里面也加上就无法插入es了。
#其实没问题。是由于kibana按timestamp排序了。时间转换了不对。直接用search语句可以搜索到。

  } 

}

结果如下：

{
  "_index": "tv_app_default-2019.05.08",
  "_type": "doc",
  "_id": "k1aVlmoBZV0IMWE2odMF",
  "_version": 1,
  "_score": null,
  "_source": {
    "timestamp": "2019-05-08T14:10:47.340",
    "deviceId": "458ec202-e02e-4b82-a7ca-18e5cb4e3df1",
    "networkStatus": "wifi连接",
    "appName": "IMetis",
    "duration": "59960912157",
    "indexName": "tv_app_default",
    "id": "f353b68c07b661f2fdd42e2260e061d9",
    "deviceSubModel": "",
    "@timestamp": "2019-05-08T15:44:14.968Z",
    "systemVersion": "24",
    "deviceModel": "PRO 7-H",
    "event_level": "verbose",
    "appVersion": "1.0",
    "devicePlatform": "Android",
    "instant": "0",
    "@version": "1",
    "event_index": "tv_app_default",
    "event": {
      "instant": "0",
      "event_index": "tv_app_default",
      "name": "BaseActivity.java_com.italkbb.test.Main2Activity",
      "line": -1,
      "timestamp": "2019-05-08T14:10:47.340",
      "id": "f353b68c07b661f2fdd42e2260e061d9",
      "event_level": "verbose",
      "duration": "59960912157"
    },
    "line": -1,
    "type": "tv_app_log",
    "name": "BaseActivity.java_com.italkbb.test.Main2Activity"
  },
  "fields": {
    "event.timestamp": [
      "2019-05-08T14:10:47.340Z"
    ]
  },
  "sort": [
    1557324647340
  ]
}