ElaticSearch 6.7.1 pdf、word、ppt、excel、txt文件查询

1. 安装插件
   es根目录下面执行命令，安装ingest-attachment插件。
    

   ./bin/elasticsearch-plugin install ingest-attachment

2. 建立自己的文本抽取管道pipeline。
    

   curl -X PUT "localhost:9200/_ingest/pipeline/attachment" -d '{
   	"description": "Extract attachment information",
   	"processors": [
   		{
   			"attachment": {
   				"field": "content",
   				"ignore_missing": true
   			}
   		},
   		{
   			"remove": {
   				"field": "content"
   			}
   		}
   	]
   }'

    

3. 创建新的索引
    

   curl -X PUT "localhost:9200/zxkfdetail_poc" '{
   	"settings": {
   		"index": {
   			"number_of_shards": 5,
   			"number_of_replicas": 2
   		}
   	}
   }'
   

   curl -X POST "http://localhost:9200/zxkfdetail_poc/zxkfdetail_poc/_mapping" '
   {
   	"zxkfdetail_poc": {
   		"properties": {
   			"agentName": {
   				"type": "text",
   				"fields": {
   					"keyword": {
   						"type": "keyword",
   						"ignore_above": 256
   					}
   				}
   			},
   			"agentid": {
   				"type": "long"
   			},
   			"annex": {
   				"type": "text",
   				"fields": {
   					"keyword": {
   						"type": "keyword",
   						"ignore_above": 256
   					}
   				}
   			},
   			"attachment": {
   				"properties": {
   					"author": {
   						"type": "text",
   						"fields": {
   							"keyword": {
   								"type": "keyword",
   								"ignore_above": 256
   							}
   						}
   					},
   					"content": {
   						"type": "text",
   						"fields": {
   							"keyword": {
   								"type": "keyword",
   								"ignore_above": 256
   							}
   						}
   					},
   					"content_length": {
   						"type": "long"
   					},
   					"content_type": {
   						"type": "text",
   						"fields": {
   							"keyword": {
   								"type": "keyword",
   								"ignore_above": 256
   							}
   						}
   					},
   					"date": {
   						"type": "date"
   					},
   					"language": {
   						"type": "text",
   						"fields": {
   							"keyword": {
   								"type": "keyword",
   								"ignore_above": 256
   							}
   						}
   					},
   					"title": {
   						"type": "text",
   						"fields": {
   							"keyword": {
   								"type": "keyword",
   								"ignore_above": 256
   							}
   						}
   					}
   				}
   			},
   			"category": {
   				"type": "text",
   				"fields": {
   					"keyword": {
   						"type": "keyword",
   						"ignore_above": 256
   					}
   				}
   			},
   			"check": {
   				"type": "long"
   			},
   			"content": {
   				"type": "text",
   				"fields": {
   					"keyword": {
   						"type": "keyword",
   						"ignore_above": 256
   					}
   				}
   			},
   			"createtime": {
   				"type": "date"
   			},
   			"filename": {
   				"type": "text",
   				"fields": {
   					"keyword": {
   						"type": "keyword",
   						"ignore_above": 256
   					}
   				}
   			},
   			"genre": {
   				"type": "long"
   			},
   			"id": {
   				"type": "text",
   				"fields": {
   					"keyword": {
   						"type": "keyword",
   						"ignore_above": 256
   					}
   				}
   			},
   			"lasttime": {
   				"type": "date"
   			},
   			"seeScope": {
   				"type": "long"
   			},
   			"similarQuestions": {
   				"type": "text",
   				"fields": {
   					"keyword": {
   						"type": "keyword",
   						"ignore_above": 256
   					}
   				}
   			},
   			"sort": {
   				"type": "long"
   			},
   			"stasts": {
   				"type": "text",
   				"fields": {
   					"keyword": {
   						"type": "keyword",
   						"ignore_above": 256
   					}
   				}
   			},
   			"tendid": {
   				"type": "long"
   			},
   			"title": {
   				"type": "text",
   				"fields": {
   					"keyword": {
   						"type": "keyword",
   						"ignore_above": 256
   					}
   				}
   			},
   			"type": {
   				"type": "long"
   			},
   			"updateman": {
   				"type": "text",
   				"fields": {
   					"keyword": {
   						"type": "keyword",
   						"ignore_above": 256
   					}
   				}
   			},
   			"zxkfId": {
   				"type": "text",
   				"fields": {
   					"keyword": {
   						"type": "keyword",
   						"ignore_above": 256
   					}
   				}
   			}
   		}
   	}
   }
   '

    

4. 载入数据
    

   curl -X PUT "localhost:9200/zxkfdetail_poc/zxkfdetail_poc/1?pipeline=attachment" -d '
   {
      "data":"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"
   }'