"id": 251, "contents": "打起黄莺儿，莫教枝上啼。啼时惊妾梦，不得到辽西。", "type": "五言绝句", "author": "金昌绪", "title": "春怨"

PUT _ingest/pipeline/indexed_at{ "description": "Adds timestamp to documents", "processors": [ { "set": { "field": "_source.timestamp", "value": "{{_ingest.timestamp}}" } }, { "script": { "source": "ctx.cont_length = ctx.contents.length();" } } ]}

PUT _template/my_template{ "index_patterns": [ "some_index*" ], "aliases": { "some_index": {} }, "settings": { "index.default_pipeline": "indexed_at", "number_of_replicas": 1, "refresh_interval": "30s" }, "mappings": { "properties": { "cont_length":{ "type":"long" }, "author": { "type": "text", "fields": { "field": { "type": "keyword" } }, "analyzer": "ik_max_word" }, "contents": { "type": "text", "fields": { "field": { "type": "keyword" } }, "analyzer": "ik_max_word", "fielddata": true }, "timestamp": { "type": "date" }, "title": { "type": "text", "fields": { "field": { "type": "keyword" } }, "analyzer": "ik_max_word" }, "type": { "type": "text", "fields": { "field": { "type": "keyword" } }, "analyzer": "ik_max_word" } } }}
PUT some_index_01

def read_and_write_index(): # define an empty list for the Elasticsearch docs doc_list = []
 # use Python's enumerate() function to iterate over list of doc strings input_file = open('300.json', encoding="utf8", errors='ignore') json_array = json.load(input_file)
 for item in json_array: try: # convert the string to a dict object # add a new field to the Elasticsearch doc dict_doc = {} # add a dict key called "_id" if you'd like to specify an ID for the doc dict_doc["_id"] = item['id'] dict_doc["contents"] = item['contents'] dict_doc["type"] = item['type'] dict_doc["author"] = item['author'] dict_doc["title"] = item['title']
 # append the dict object to the list [] doc_list += [dict_doc]
 except json.decoder.JSONDecodeError as err: # print the errors print("ERROR for num:", item['id'], "-- JSONDecodeError:", err, "for doc:", dict_doc) print("Dict docs length:", len(doc_list))


 try: print ("\nAttempting to index the list of docs using helpers.bulk()")
 # use the helpers library's Bulk API to index list of Elasticsearch docs resp = helpers.bulk( client, doc_list, index = "some_index", doc_type = "_doc" )
 # print the response returned by Elasticsearch print ("helpers.bulk() RESPONSE:", resp) print ("helpers.bulk() RESPONSE:", json.dumps(resp, indent=4)) except Exception as err: # print any errors returned w ## Prerequisiteshile making the helpers.bulk() API call print("Elasticsearch helpers.bulk() ERROR:", err) quit()

GET some_index/_search{ "query": { "match": { "contents": "铭" } }}
GET some_index/_search{ "query": { "match": { "contents": "毅" } }}
GET some_index/_search{ "query": { "match": { "contents": "天下" } }}

POST some_index/_search{ "query": { "match_phrase": { "author": "李白" } }, "sort": [ { "cont_length": { "order": "desc" } } ]}
POST some_index/_search{ "aggs": { "genres": { "terms": { "field": "author.keyword" } } }}

POST some_index/_search{ "sort": [ { "cont_length": { "order": "desc" } } ]}
POST some_index/_search{ "sort": [ { "cont_length": { "order": "asc" } } ]}