混合精确搜索与词干提取
编辑混合精确搜索与词干提取
编辑在构建搜索应用程序时，词干提取通常是必不可少的，因为希望对 skiing 的查询能够匹配包含 ski 或 skis 的文档。但是，如果用户想要专门搜索 skiing 呢？通常的做法是使用多字段，以便以两种不同的方式索引相同的内容
resp = client.indices.create(
index="index",
settings={
"analysis": {
"analyzer": {
"english_exact": {
"tokenizer": "standard",
"filter": [
"lowercase"
]
}
}
}
},
mappings={
"properties": {
"body": {
"type": "text",
"analyzer": "english",
"fields": {
"exact": {
"type": "text",
"analyzer": "english_exact"
}
}
}
}
},
)
print(resp)
resp1 = client.index(
index="index",
id="1",
document={
"body": "Ski resort"
},
)
print(resp1)
resp2 = client.index(
index="index",
id="2",
document={
"body": "A pair of skis"
},
)
print(resp2)
resp3 = client.indices.refresh(
index="index",
)
print(resp3)
response = client.indices.create(
index: 'index',
body: {
settings: {
analysis: {
analyzer: {
english_exact: {
tokenizer: 'standard',
filter: [
'lowercase'
]
}
}
}
},
mappings: {
properties: {
body: {
type: 'text',
analyzer: 'english',
fields: {
exact: {
type: 'text',
analyzer: 'english_exact'
}
}
}
}
}
}
)
puts response
response = client.index(
index: 'index',
id: 1,
body: {
body: 'Ski resort'
}
)
puts response
response = client.index(
index: 'index',
id: 2,
body: {
body: 'A pair of skis'
}
)
puts response
response = client.indices.refresh(
index: 'index'
)
puts response
const response = await client.indices.create({
index: "index",
settings: {
analysis: {
analyzer: {
english_exact: {
tokenizer: "standard",
filter: ["lowercase"],
},
},
},
},
mappings: {
properties: {
body: {
type: "text",
analyzer: "english",
fields: {
exact: {
type: "text",
analyzer: "english_exact",
},
},
},
},
},
});
console.log(response);
const response1 = await client.index({
index: "index",
id: 1,
document: {
body: "Ski resort",
},
});
console.log(response1);
const response2 = await client.index({
index: "index",
id: 2,
document: {
body: "A pair of skis",
},
});
console.log(response2);
const response3 = await client.indices.refresh({
index: "index",
});
console.log(response3);
PUT index
{
"settings": {
"analysis": {
"analyzer": {
"english_exact": {
"tokenizer": "standard",
"filter": [
"lowercase"
]
}
}
}
},
"mappings": {
"properties": {
"body": {
"type": "text",
"analyzer": "english",
"fields": {
"exact": {
"type": "text",
"analyzer": "english_exact"
}
}
}
}
}
}
PUT index/_doc/1
{
"body": "Ski resort"
}
PUT index/_doc/2
{
"body": "A pair of skis"
}
POST index/_refresh
通过这样的设置，在 body 上搜索 ski 会返回两个文档
resp = client.search(
index="index",
query={
"simple_query_string": {
"fields": [
"body"
],
"query": "ski"
}
},
)
print(resp)
response = client.search(
index: 'index',
body: {
query: {
simple_query_string: {
fields: [
'body'
],
query: 'ski'
}
}
}
)
puts response
const response = await client.search({
index: "index",
query: {
simple_query_string: {
fields: ["body"],
query: "ski",
},
},
});
console.log(response);
GET index/_search
{
"query": {
"simple_query_string": {
"fields": [ "body" ],
"query": "ski"
}
}
}
{
"took": 2,
"timed_out": false,
"_shards": {
"total": 1,
"successful": 1,
"skipped" : 0,
"failed": 0
},
"hits": {
"total" : {
"value": 2,
"relation": "eq"
},
"max_score": 0.18232156,
"hits": [
{
"_index": "index",
"_id": "1",
"_score": 0.18232156,
"_source": {
"body": "Ski resort"
}
},
{
"_index": "index",
"_id": "2",
"_score": 0.18232156,
"_source": {
"body": "A pair of skis"
}
}
]
}
}
另一方面，在 body.exact 上搜索 ski 只会返回文档 1，因为 body.exact 的分析链不执行词干提取。
resp = client.search(
index="index",
query={
"simple_query_string": {
"fields": [
"body.exact"
],
"query": "ski"
}
},
)
print(resp)
response = client.search(
index: 'index',
body: {
query: {
simple_query_string: {
fields: [
'body.exact'
],
query: 'ski'
}
}
}
)
puts response
const response = await client.search({
index: "index",
query: {
simple_query_string: {
fields: ["body.exact"],
query: "ski",
},
},
});
console.log(response);
GET index/_search
{
"query": {
"simple_query_string": {
"fields": [ "body.exact" ],
"query": "ski"
}
}
}
{
"took": 1,
"timed_out": false,
"_shards": {
"total": 1,
"successful": 1,
"skipped" : 0,
"failed": 0
},
"hits": {
"total" : {
"value": 1,
"relation": "eq"
},
"max_score": 0.8025915,
"hits": [
{
"_index": "index",
"_id": "1",
"_score": 0.8025915,
"_source": {
"body": "Ski resort"
}
}
]
}
}
这不容易暴露给最终用户，因为我们需要找到一种方法来确定他们是否正在寻找精确匹配，并相应地重定向到适当的字段。而且，如果只有部分查询需要精确匹配，而其他部分仍然应该考虑词干提取，该怎么办？
幸运的是，query_string 和 simple_query_string 查询具有一个可以解决此确切问题的特性：quote_field_suffix。这告诉 Elasticsearch，出现在引号之间的单词将被重定向到不同的字段，如下所示
resp = client.search(
index="index",
query={
"simple_query_string": {
"fields": [
"body"
],
"quote_field_suffix": ".exact",
"query": "\"ski\""
}
},
)
print(resp)
response = client.search(
index: 'index',
body: {
query: {
simple_query_string: {
fields: [
'body'
],
quote_field_suffix: '.exact',
query: '"ski"'
}
}
}
)
puts response
const response = await client.search({
index: "index",
query: {
simple_query_string: {
fields: ["body"],
quote_field_suffix: ".exact",
query: '"ski"',
},
},
});
console.log(response);
GET index/_search
{
"query": {
"simple_query_string": {
"fields": [ "body" ],
"quote_field_suffix": ".exact",
"query": "\"ski\""
}
}
}
{
"took": 2,
"timed_out": false,
"_shards": {
"total": 1,
"successful": 1,
"skipped" : 0,
"failed": 0
},
"hits": {
"total" : {
"value": 1,
"relation": "eq"
},
"max_score": 0.8025915,
"hits": [
{
"_index": "index",
"_id": "1",
"_score": 0.8025915,
"_source": {
"body": "Ski resort"
}
}
]
}
}
在上面的例子中，由于 ski 在引号之间，因此由于 quote_field_suffix 参数，它在 body.exact 字段上进行搜索，所以只有文档 1 匹配。这允许用户根据需要混合精确搜索和词干搜索。
如果在 quote_field_suffix 中传递的字段选择不存在，则搜索将回退到使用查询字符串的默认字段。