EFK 配置geo-ip落地實踐（三）經緯度數據查詢及格式化輸出

時間 2019-12-04

標籤 efk 配置 geo 落地實踐經緯度數據查詢格式化輸出简体版

原文原文鏈接

通過以前的工做，目前已經完成了數據地圖的數據格式化和錄入記錄，目前咱們的數據地圖項目已經進行到最後階段，因此如今須要一個接口，進行格式化數據並輸出，其中須要用到Elasticsearch的全文檢索，檢索出數據後，使用php接口格式化數據輸出php

1、全文檢索html

搜索條件（時間，空間）
輸出結果（用戶數量）

例如，一個小時內，在中國範圍內，各個經緯度座標的，有操做行爲的，用戶個數node

由此需求，能夠獲得相應的Elasticsearch的搜索語句，以下：json

{
"size": 0,
"aggs": {
    "filter_agg": {
        "filter": {
            "geo_bounding_box": {
                "location": {
                    "top_left": {
                        "lat": 90,
                        "lon": -34.453125
                    },
                    "bottom_right": {
                        "lat": -90,
                        "lon": 34.453125
                    }
                }
            }
        },
        "aggs": {
            "2": {
                "geohash_grid": {
                    "field": "location",
                    "precision": 2
                },
                "aggs": {
                    "3": {
                        "geo_centroid": {
                            "field": "location"
                        }
                    }
                }
            }
        }
    }
},
"stored_fields": [
    "*"
],
"docvalue_fields": [
    "@timestamp"
],
"query": {
    "bool": {
        "must": [
            {
                "range": {
                    "@timestamp": {
                        "gte": 1542692193461,
                        "lte": 1542695793461,
                        "format": "epoch_millis"
                    }
                }
            }
        ]
    }
}
}
複製代碼

size=0表示不分頁
query爲搜索主體，其中的必要條件爲時間參數，即，搜索此段時間內的全部數據
aggs中至關於spl中的where條件，而其中geo_bounding_box爲地理範圍，由左上角經緯度點到右下角經緯度點所界定的一個矩形方框。
aggs嵌套，即上層條件的結果上，繼續作篩選
geohash_grid表示，按照你定義的精度計算每個點的 geohash 值而將附近的位置聚合在一塊兒，其中field爲目前篩選的的字段， precision爲經度，單位爲km
最後，經過geo_centroid獲得key爲location的聚合數據

結果數據格式以下：api

{
"took": 428,
"timed_out": false,
"_shards": {
    "total": 131,
    "successful": 126,
    "skipped": 121,
    "failed": 5,
    "failures": [
        {
            "shard": 0,
            "index": "elastalert_status_status",
            "node": "w10b9zEBRpuUEQsWvNqEig",
            "reason": {
                "type": "query_shard_exception",
                "reason": "failed to find geo_point field [location]",
                "index_uuid": "Dm4dpUtTTHitYN-TZFC-1g",
                "index": "elastalert_status_status"
            }
        }
    ]
},
"hits": {
    "total": 360942,
    "max_score": 0,
    "hits": []
},
"aggregations": {
    "filter_agg": {
        "2": {
            "buckets": [
                {
                    "3": {
                        "location": {
                            "lat": 48.58949514372008,
                            "lon": 7.584022147181843
                        },
                        "count": 252
                    },
                    "key": "u0",
                    "doc_count": 252
                },
                {
                    "3": {
                        "location": {
                            "lat": 54.420127907268785,
                            "lon": -3.120888938036495
                        },
                        "count": 181
                    },
                    "key": "gc",
                    "doc_count": 181
                },
                {
                    "3": {
                        "location": {
                            "lat": 42.32862451614172,
                            "lon": 3.7518564593602917
                        },
                        "count": 67
                    },
                    "key": "sp",
                    "doc_count": 67
                },
                {
                    "3": {
                        "location": {
                            "lat": 45.40799999143928,
                            "lon": 11.88589995726943
                        },
                        "count": 21
                    },
                    "key": "u2",
                    "doc_count": 21
                },
                {
                    "3": {
                        "location": {
                            "lat": 46.65579996071756,
                            "lon": 32.61779992841184
                        },
                        "count": 1
                    },
                    "key": "u8",
                    "doc_count": 1
                }
            ]
        },
        "doc_count": 522
    }
}
}
複製代碼

aggregations中是咱們最終須要的數據
其中location爲聚合的經緯度座標，緊跟着的count則指的是，在此點2km*2km範圍以內的用戶數。

自此，咱們首先明白了，在Elasticsearch，如何書寫search語句查詢咱們想要的東西。接下來，咱們須要書寫相應的php接口，來格式化輸出數據bash

2、接口書寫數據結構

使用Elasticseach的PHP API
肯定輸入參數：時間範圍，空間範圍
肯定輸出數據結構，並格式化數據輸出

代碼以下，有註釋：elasticsearch

<?php
/**
 * Created by PhpStorm.
 * User: ekisong
 * Date: 2018/11/13
 * Time: 15:55
 */
require 'vendor/autoload.php';
ini_set('display_errors','on');
error_reporting(E_ALL);

use Elasticsearch\ClientBuilder;

//建立Elasticsearch 的搜索對象client
$client = ClientBuilder::create()->setHosts(["localhost:9200"])->build();

//須要被篩選的字段名，默認值爲location
$fieldName = isset($_GET['field']) ? $_GET['field'] : 'location';

//地理圍欄左上角緯度，默認值90
$topLeftLat = isset($_GET['top_left_lat']) ? $_GET['top_left_lat'] : 90;

//地理圍欄左上角經度，默認值-180
$topLeftLon = isset($_GET['top_left_lon']) ? $_GET['top_left_lon'] : -180;

//地理圍欄右下角緯度，默認值-90
$bottomRightLat = isset($_GET['bottom_right_lat']) ? $_GET['bottom_right_lat'] : -90;

//地理圍欄右下角經度，默認值180
$bottomRightLon = isset($_GET['bottom_right_lon']) ? $_GET['bottom_right_lon'] : 180;

//時間範圍結束時間，默認當前時間
$endTime = isset($_GET['end_time']) ? $_GET['end_time'] : time()*1000;

//時間範圍其實時間，默認當前時間前15分鐘
$startTime = isset($_GET['start_time']) ? $_GET['start_time'] : $endTime - 15*60*1000;

//建立查詢結構體
$body = [
    'size' => 0,
    'query' => [
        'bool' => [
            'must' => [
                [
                    'range' => [
                        '@timestamp' => [
                            'gte' => $startTime,
                            'lte' => $endTime,
                            'format' => 'epoch_millis'
                        ]
                    ]
                ]
            ]
        ]
    ],
    'aggs' => [
        'filter_agg' => [
            'filter' => [
                'geo_bounding_box' => [
                    'location' => [
                        'top_left' => [
                            'lat' => $topLeftLat,
                            'lon' => $topLeftLon
                        ],
                        'bottom_right' => [
                            'lat' => $bottomRightLat,
                            'lon' => $bottomRightLon
                        ]
                    ]
                ]
            ],
            'aggs' => [
                '2' => [
                    'geohash_grid' => [
                        'field' => $fieldName,
                        'precision' => 1
                    ],
                    'aggs' => [
                        '3' => [
                            'geo_centroid' => [
                                'field' => $fieldName
                            ]
                        ]
                    ]
                ]
            ]
        ]
    ],
    'stored_fields' => [
        '*'
    ],
    'docvalue_fields' => [
        '@timestamp'
    ]
];

//搜索參數
$params = [
    'index' => 'logstash-*',
    'body' => $body
];

//Elasticsearch搜索結果原始數據
$response = $client->search($params);

$resultTmp = $response['aggregations']['filter_agg']['2']['buckets'];

$data = array();

//格式化數據
foreach ($resultTmp as $doc)
{
    $lat = $doc['3'][$fieldName]['lat'];
    $lon = $doc['3'][$fieldName]['lon'];
    $count = $doc['doc_count'];
    $tmp = [
        'count' => $count,
        'geometry' => [
            'type' => 'Point',
            'coordinates' => [$lon,$lat]
        ]
    ];
    $data[] = $tmp;
}

$result = array('data'=>$data,'error_msg'=>'','flag'=>1);

if (empty($data))
{
    $result['error_msg'] = 'no data';
    $result['flag'] = 0;
}

//最終輸出
echo json_encode($result);
exit();
複製代碼

因爲H5頁面插件限制，因此須要特定的數據格式。因此最終輸出結果以下：ide

[{
    "count": 6,
    "geometry": {
        "type": "Point",
        "coordinates": ["116.395645", "39.929986"]
    }
}, {
    "count": 6,
    "geometry": {
        "type": "Point",
        "coordinates": ["121.487899", "31.249162"]
    }
}, {
    "count": 5,
    "geometry": {
        "type": "Point",
        "coordinates": ["117.210813", "39.14393"]
    }
}, {
    "count": 4,
    "geometry": {
        "type": "Point",
        "coordinates": ["106.530635", "29.544606"]
    }
}]
複製代碼