elasticsearch - Elastic 没有找到 1 个单词的结果
问题描述
我不太了解使用 elasticsearch 得到的结果。我的研究结果似乎不一致。
通过这个搜索
{"query": {
"multi_match" : {
"query" : "tarif new",
"fields" : [ "titles^3", "texts" ]
}
}}
我有 2 个结果：
"titles": "Tarif New 208 (07/2019), Tarif New 208, Tarif New 208 , FREDERIC, f.mignon@lab360.be, , ",
和
"titles": "Tarif Traveller (07/2019), Traveller, Tarif New Traveller, , , , ",
但是通过这个搜索：
{
"query": {
"multi_match" : {
"query" : "tarif",
"fields" : [ "titles^3", "texts" ]
}
}
}
我只有 1 个结果：
"titles": "Tarif Traveller (07/2019), Traveller, Tarif New Traveller, , , , ",
我的索引是由 Elasticsearch .NET 创建的
var indexDescriptor = new CreateIndexDescriptor(indexName)
.Mappings(ms => ms
.Map<EsContent>(m => m.AutoMap()
.Properties(p => p
.Text(t => t
.Name(n => n.Titles)
.Fields(ff => ff
.Keyword(k => k
.Name("keyword")
.IgnoreAbove(256)
)
)
)
.Text(t => t
.Name(n => n.Texts)
.Fields(ff => ff
.Keyword(k => k
.Name("keyword")
.IgnoreAbove(256)
)
)
)
.Text(t => t
.Name(n => n.Tags)
.Fields(ff => ff
.Keyword(k => k
.Name("keyword")
.IgnoreAbove(256)
)
)
)
)
));
我真的不明白这些结果。当我使用“关税”一词进行搜索时，为什么没有出现“Price New 208 (07/2019)”作为结果？
你可以在这里找到 http://localhost:9200/content_1_be_fr?pretty的结果：
{
"content_1_be_fr": {
"aliases": {},
"mappings": {
"escontent": {
"properties": {
"attachment": {
"properties": {
"author": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"containsMetadata": {
"type": "boolean"
},
"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"
},
"detect_language": {
"type": "boolean"
},
"indexed_chars": {
"type": "long"
},
"keywords": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"language": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"name": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"title": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
}
}
},
"content": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"content_Id": {
"type": "integer"
},
"country_Id": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"createdAt": {
"type": "date"
},
"documents": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"id": {
"type": "integer"
},
"language_Id": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"path": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"suggest": {
"type": "completion",
"analyzer": "simple",
"preserve_separators": true,
"preserve_position_increments": true,
"max_input_length": 50
},
"tags": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"texts": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"titles": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
}
}
}
},
"settings": {
"index": {
"creation_date": "1562573917609",
"number_of_shards": "5",
"number_of_replicas": "1",
"uuid": "dVTg6anYTKuqOhaSW68pvw",
"version": {
"created": "6050099"
},
"provided_name": "content_1_be_fr"
}
}
}
}
"tarif" 词搜索的结果 => http://localhost:9200/content_1_be_fr/_search?q=tarif
{
"took": 4,
"timed_out": false,
"_shards": {
"total": 5,
"successful": 5,
"skipped": 0,
"failed": 0
},
"hits": {
"total": 106,
"max_score": 6.665128,
"hits": [
{
"_index": "content_1_be_fr",
"_type": "escontent",
"_id": "515",
"_score": 6.665128,
"_source": {
"id": 515,
"titles": "Tarif VP (07/2019), Tarif VP, Tarif VP, , , , ",
"texts": "Tarif VP, , , , , , ",
"createdAt": "2017-05-16T16:41:37.727",
"tags": [
"Tarif",
"Fleet"
],
"content_Id": 0
}
},
{
"_index": "content_1_be_fr",
"_type": "escontent",
"_id": "5024",
"_score": 6.1476207,
"_source": {
"id": 5024,
"titles": "Tarif Rifter (07/2019), Rifter, Tarif Rifter, , , , ",
"texts": "Tarif Rifter, , , , , , ",
"createdAt": "2018-05-30T12:14:37.677",
"tags": [
"Tarif",
"Rifter"
],
"content_Id": 0
}
},
{
"_index": "content_1_be_fr",
"_type": "escontent",
"_id": "621",
"_score": 5.9972153,
"_source": {
"id": 621,
"titles": "Tarif Traveller (07/2019), Traveller, Tarif New Traveller, , , , ",
"texts": "Tarif New Traveller, , , , , , ",
"createdAt": "2017-05-16T17:13:44.04",
"tags": [
"Tarif",
"Fleet",
"Traveller"
],
"content_Id": 0
}
},
{
"_index": "content_1_be_fr",
"_type": "escontent",
"_id": "544",
"_score": 5.9037256,
"_source": {
"id": 544,
"titles": "Tarif 208 GT (07/2019), tarif 208, Tarif 208 GT, , , , ",
"texts": "Tarif 208 GT, , , , , , ",
"createdAt": "2017-05-16T16:52:25.883",
"tags": [
"Tarif",
"Fleet",
"208",
"GT"
],
"content_Id": 0
}
},
{
"_index": "content_1_be_fr",
"_type": "escontent",
"_id": "545",
"_score": 5.8449397,
"_source": {
"id": 545,
"titles": "Tarif VU (07/2019), Tarif VU, Tarif VU, , , , ",
"texts": "Tarif VU, , , , , , ",
"createdAt": "2017-05-16T16:52:45.26",
"tags": [
"Tarif",
"Fleet",
"VU"
],
"content_Id": 0
}
},
{
"_index": "content_1_be_fr",
"_type": "escontent",
"_id": "510",
"_score": 5.717454,
"_source": {
"id": 510,
"titles": "Tarif Expert VU (07/2019), Expert VU, Tarif Expert VU, , , , ",
"texts": "Tarif Expert VU, , , , , , ",
"createdAt": "2017-05-16T16:40:11.43",
"tags": [
"Tarif",
"Fleet",
"Expert"
],
"content_Id": 0
}
},
{
"_index": "content_1_be_fr",
"_type": "escontent",
"_id": "512",
"_score": 5.659007,
"_source": {
"id": 512,
"titles": "Tarif Utility (05/2019), Utility, Tarif Utility, , , , ",
"texts": "Tarif Utility, , , , , , ",
"createdAt": "2017-05-16T16:40:49.82",
"tags": [
"Tarif",
"Fleet",
"Utility"
],
"content_Id": 0
}
},
{
"_index": "content_1_be_fr",
"_type": "escontent",
"_id": "520",
"_score": 5.659007,
"_source": {
"id": 520,
"titles": "Tarif 508 (07/2019), 508, Tarif 508, , , , ",
"texts": "Tarif 508, , , , , , ",
"createdAt": "2017-05-16T16:43:08.4",
"tags": [
"Tarif",
"Fleet",
"508"
],
"content_Id": 0
}
},
{
"_index": "content_1_be_fr",
"_type": "escontent",
"_id": "526",
"_score": 5.659007,
"_source": {
"id": 526,
"titles": "Tarif 108 (07/2019), 108, Tarif 108, , , , ",
"texts": "Tarif 108, , , , , , ",
"createdAt": "2017-05-16T16:45:04.447",
"tags": [
"Tarif",
"Fleet",
"108"
],
"content_Id": 0
}
},
{
"_index": "content_1_be_fr",
"_type": "escontent",
"_id": "516",
"_score": 5.6427865,
"_source": {
"id": 516,
"titles": "Tarif iOn (07/2019), iOn, Tarif iOn, , , , ",
"texts": "Tarif iOn, , , , , , ",
"createdAt": "2017-05-16T16:41:49.867",
"tags": [
"Tarif",
"Fleet",
"iOn",
"Electric"
],
"content_Id": 0
}
}
]
}
}
对于“新关税”=> http://localhost:9200/content_1_be_fr/_search?q=tarif new
{
"took": 3,
"timed_out": false,
"_shards": {
"total": 5,
"successful": 5,
"skipped": 0,
"failed": 0
},
"hits": {
"total": 296,
"max_score": 10.11692,
"hits": [
{
"_index": "content_1_be_fr",
"_type": "escontent",
"_id": "5200",
"_score": 10.11692,
"_source": {
"id": 5200,
"titles": "Tarif Partner VU (07/2019), Partner VU, Tarif Partner VU, , , , ",
"texts": "Tarif NEW Partner VU, , , , , , ",
"createdAt": "2018-08-28T14:51:25.41",
"tags": [
"Tarif",
"Fleet",
"Partner"
],
"content_Id": 0
}
},
{
"_index": "content_1_be_fr",
"_type": "escontent",
"_id": "522",
"_score": 9.818497,
"_source": {
"id": 522,
"titles": "Tarif 3008 (07/2019), 3008, Tarif New 3008, , , , ",
"texts": "Tarif New 3008, , , , , , ",
"createdAt": "2017-05-16T16:43:46.463",
"tags": [
"Tarif",
"Fleet",
"3008"
],
"content_Id": 0
}
},
{
"_index": "content_1_be_fr",
"_type": "escontent",
"_id": "5816",
"_score": 9.40431,
"_source": {
"id": 5816,
"titles": "Tarif New 208 (07/2019), Tarif New 208, Tarif New 208 , FREDERIC, f.mignon@lab360.be, , ",
"texts": "Tarif, , , MIGNON, , , ",
"createdAt": "2019-07-01T08:36:19.583",
"tags": [
"Tarif",
"Fleet",
"208",
"NEW 208"
],
"content_Id": 0
}
},
{
"_index": "content_1_be_fr",
"_type": "escontent",
"_id": "550",
"_score": 9.044639,
"_source": {
"id": 550,
"titles": "Tarif 2008 (07/2019), 2008, Tarif New 2008, , , , ",
"texts": "Tarif New 2008, , , , , , ",
"createdAt": "2017-05-16T16:54:07.163",
"tags": [
"Tarif",
"Fleet",
"2008"
],
"content_Id": 0
}
},
{
"_index": "content_1_be_fr",
"_type": "escontent",
"_id": "621",
"_score": 8.852159,
"_source": {
"id": 621,
"titles": "Tarif Traveller (07/2019), Traveller, Tarif New Traveller, , , , ",
"texts": "Tarif New Traveller, , , , , , ",
"createdAt": "2017-05-16T17:13:44.04",
"tags": [
"Tarif",
"Fleet",
"Traveller"
],
"content_Id": 0
}
},
{
"_index": "content_1_be_fr",
"_type": "escontent",
"_id": "5572",
"_score": 8.2428465,
"_source": {
"id": 5572,
"titles": "Tarif New Partner 15/03/2019, Tarif New Partner 15/03/2019, , DAVID, david.delpercio@mpsa.com, , ",
"texts": ", , , DEL PERCIO, 003223884093, , ",
"createdAt": "2019-03-15T17:27:55.623",
"tags": [],
"content_Id": 0
}
},
{
"_index": "content_1_be_fr",
"_type": "escontent",
"_id": "625",
"_score": 8.189293,
"_source": {
"id": 625,
"titles": "Tarif 5008 (07/2019), 5008, Tarif New 5008, , , , ",
"texts": "Tarif New 5008, , , , , , ",
"createdAt": "2017-05-16T17:14:57.087",
"tags": [
"Tarif",
"5008"
],
"content_Id": 0
}
},
{
"_index": "content_1_be_fr",
"_type": "escontent",
"_id": "5277",
"_score": 7.9583516,
"_source": {
"id": 5277,
"titles": "Tarif 508 SW (07/2019), 508 SW, Tarif 508 SW (07/2019), MARTIN, martin.want@peugeot.com, , ",
"texts": "Tarif New 508 SW , , , WANT, 003223884092, , ",
"createdAt": "2018-10-03T11:07:32.933",
"tags": [
"508 SW"
],
"content_Id": 0
}
},
{
"_index": "content_1_be_fr",
"_type": "escontent",
"_id": "620",
"_score": 7.922105,
"_source": {
"id": 620,
"titles": "Tarif Expert VP (07/2019), Expert VP, Tarif New Expert VP, , , , ",
"texts": "Tarif New Expert VP, , , , , , ",
"createdAt": "2017-05-16T17:13:20.587",
"tags": [
"Tarif",
"Fleet",
"Expert"
],
"content_Id": 0
}
},
{
"_index": "content_1_be_fr",
"_type": "escontent",
"_id": "5689",
"_score": 7.673352,
"_source": {
"id": 5689,
"titles": "New Partner : Tarif 01/05/2019, New Partner : Tarif 01/05/2019, , DAVID, david.delpercio@mpsa.com, , ",
"texts": ", , , DEL PERCIO, 003223884093, , ",
"createdAt": "2019-05-03T16:20:59.047",
"tags": [],
"content_Id": 0
}
}
]
}
}
我不明白为什么文档 id: 5816 在我搜索“关税”一词时不会出现，而如果我用“新关税”搜索则看起来不错。如果我按单词“new”和单词“208”搜索，它也会出现在结果中。
我也尝试使用此映射，但结果相同：
... "titles": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
},
"analyzer": "jaf_Custom"
}
}
}
},
"settings": {
"index": {
"number_of_shards": "5",
"provided_name": "content_1_be_fr",
"creation_date": "1562575529961",
"analysis": {
"analyzer": {
"jaf_Custom": {
"filter": [
"lowercase",
"stop",
"standard",
"snowball"
],
"type": "custom",
"tokenizer": "standard"
}
}
},
"number_of_replicas": "1",
"uuid": "o0Iz7hnXQTa_ZgM3AxqYpA",
"version": {
"created": "6050099"
}
}
}
并完成 http://localhost:9200/content_1_be_fr/_termvectors/5816?fields=titles 给：
{
"_index": "content_1_be_fr",
"_type": "_doc",
"_id": "5816",
"_version": 1,
"found": true,
"took": 15,
"term_vectors": {
"titles": {
"field_statistics": {
"sum_doc_freq": 22882,
"doc_count": 1995,
"sum_ttf": 25409
},
"terms": {
"208": {
"term_freq": 3,
"tokens": [
{
"position": 2,
"start_offset": 10,
"end_offset": 13
},
{
"position": 7,
"start_offset": 35,
"end_offset": 38
},
{
"position": 10,
"start_offset": 50,
"end_offset": 53
}
]
},
"2019": {
"term_freq": 1,
"tokens": [
{
"position": 4,
"start_offset": 18,
"end_offset": 22
}
]
},
"07": {
"term_freq": 1,
"tokens": [
{
"position": 3,
"start_offset": 15,
"end_offset": 17
}
]
},
"be": {
"term_freq": 1,
"tokens": [
{
"position": 14,
"start_offset": 82,
"end_offset": 84
}
]
},
"f.mignon": {
"term_freq": 1,
"tokens": [
{
"position": 12,
"start_offset": 66,
"end_offset": 74
}
]
},
"frederic": {
"term_freq": 1,
"tokens": [
{
"position": 11,
"start_offset": 56,
"end_offset": 64
}
]
},
"lab360": {
"term_freq": 1,
"tokens": [
{
"position": 13,
"start_offset": 75,
"end_offset": 81
}
]
},
"new": {
"term_freq": 3,
"tokens": [
{
"position": 1,
"start_offset": 6,
"end_offset": 9
},
{
"position": 6,
"start_offset": 31,
"end_offset": 34
},
{
"position": 9,
"start_offset": 46,
"end_offset": 49
}
]
},
"tarif": {
"term_freq": 3,
"tokens": [
{
"position": 0,
"start_offset": 0,
"end_offset": 5
},
{
"position": 5,
"start_offset": 25,
"end_offset": 30
},
{
"position": 8,
"start_offset": 40,
"end_offset": 45
}
]
}
}
}
}
}
我想，这意味着“关税”一词已被很好地索引。
解决方案
我通过添加自定义分析器来解决我的问题：
"titles": {
"type": "text",
"analyzer": "jaf_Custom"
}
}
}
},
"settings": {
"index": {
"number_of_shards": "5",
"provided_name": "content_1_be_fr",
"creation_date": "1562655737479",
"analysis": {
"filter": {
"NG": {
"type": "ngram",
"min_gram": "2",
"max_gram": "10"
},
"lg": {
"type": "stemmer",
"language": "french"
}
},
"analyzer": {
"jaf_Custom": {
"filter": [
"lowercase",
"stop",
"standard",
"snowball",
"lg",
"NG"
],
"type": "custom",
"tokenizer": "keyword"
}
}
},
"number_of_replicas": "1",
"uuid": "YGBuNh7jQ2-9VMlI5gpOEg",
"version": {
"created": "6050099"
}
}
}
推荐阅读
- reactjs - 为什么当 tsconfig target 设置为 es5 时 instanceof check 返回 false 而设置为 esnext 时返回 true？
- javascript - 将对象键添加到 href url 链接的末尾？
- swift - Swift 5 UICollectionViewCell 如何改变它的内容
- mysql - sql 按不同的列分组并计算不同的列
- flutter - Flutter：如何通过按钮以编程方式更改文本字段中文本的对齐方式？
- reactjs - 将 useMachine 与 useContext 结合使用
- reactjs - 尝试使用 React 计算带有价格的日期
- ldap - Spring security LDAP-错误 LDAP：错误代码 50-访问权限不足
- email - 如何强制 Google App Script MailApp.sendEmail 在循环中为每封电子邮件使用新线程？
- python - 编写一个接收字符串列表并返回列表列表的函数