展平图标记过滤器
编辑展平图标记过滤器
编辑展平由图标记过滤器生成的标记图，例如 synonym_graph 或 word_delimiter_graph。
展平包含多位置标记的标记图，使该图适合索引。否则，索引不支持包含多位置标记的标记图。
展平图是一个有损的过程。
如果可能，请避免使用 flatten_graph 过滤器。相反，仅在搜索分析器中使用图标记过滤器。这消除了对 flatten_graph 过滤器的需求。
flatten_graph 过滤器使用 Lucene 的 FlattenGraphFilter。
示例
编辑要了解 flatten_graph 过滤器的工作原理，首先需要生成一个包含多位置标记的标记图。
以下 分析 API 请求使用 synonym_graph 过滤器将 dns 添加为文本 domain name system is fragile 中 domain name system 的多位置同义词
resp = client.indices.analyze(
tokenizer="standard",
filter=[
{
"type": "synonym_graph",
"synonyms": [
"dns, domain name system"
]
}
],
text="domain name system is fragile",
)
print(resp)
response = client.indices.analyze(
body: {
tokenizer: 'standard',
filter: [
{
type: 'synonym_graph',
synonyms: [
'dns, domain name system'
]
}
],
text: 'domain name system is fragile'
}
)
puts response
const response = await client.indices.analyze({
tokenizer: "standard",
filter: [
{
type: "synonym_graph",
synonyms: ["dns, domain name system"],
},
],
text: "domain name system is fragile",
});
console.log(response);
GET /_analyze
{
"tokenizer": "standard",
"filter": [
{
"type": "synonym_graph",
"synonyms": [ "dns, domain name system" ]
}
],
"text": "domain name system is fragile"
}
该过滤器生成以下标记图，其中 dns 为多位置标记。
索引不支持包含多位置标记的标记图。为了使此标记图适合索引，需要将其展平。
要展平标记图，请在之前的分析 API 请求中，在 synonym_graph 过滤器之后添加 flatten_graph 过滤器。
resp = client.indices.analyze(
tokenizer="standard",
filter=[
{
"type": "synonym_graph",
"synonyms": [
"dns, domain name system"
]
},
"flatten_graph"
],
text="domain name system is fragile",
)
print(resp)
response = client.indices.analyze(
body: {
tokenizer: 'standard',
filter: [
{
type: 'synonym_graph',
synonyms: [
'dns, domain name system'
]
},
'flatten_graph'
],
text: 'domain name system is fragile'
}
)
puts response
const response = await client.indices.analyze({
tokenizer: "standard",
filter: [
{
type: "synonym_graph",
synonyms: ["dns, domain name system"],
},
"flatten_graph",
],
text: "domain name system is fragile",
});
console.log(response);
GET /_analyze
{
"tokenizer": "standard",
"filter": [
{
"type": "synonym_graph",
"synonyms": [ "dns, domain name system" ]
},
"flatten_graph"
],
"text": "domain name system is fragile"
}
该过滤器生成以下展平的标记图，该图适合索引。
添加到分析器
编辑以下创建索引 API 请求使用 flatten_graph 标记过滤器来配置新的自定义分析器。
在此分析器中，自定义的 word_delimiter_graph 过滤器生成包含连接的多位置标记的标记图。flatten_graph 过滤器展平这些标记图，使其适合索引。
resp = client.indices.create(
index="my-index-000001",
settings={
"analysis": {
"analyzer": {
"my_custom_index_analyzer": {
"type": "custom",
"tokenizer": "standard",
"filter": [
"my_custom_word_delimiter_graph_filter",
"flatten_graph"
]
}
},
"filter": {
"my_custom_word_delimiter_graph_filter": {
"type": "word_delimiter_graph",
"catenate_all": True
}
}
}
},
)
print(resp)
response = client.indices.create(
index: 'my-index-000001',
body: {
settings: {
analysis: {
analyzer: {
my_custom_index_analyzer: {
type: 'custom',
tokenizer: 'standard',
filter: [
'my_custom_word_delimiter_graph_filter',
'flatten_graph'
]
}
},
filter: {
my_custom_word_delimiter_graph_filter: {
type: 'word_delimiter_graph',
catenate_all: true
}
}
}
}
}
)
puts response
const response = await client.indices.create({
index: "my-index-000001",
settings: {
analysis: {
analyzer: {
my_custom_index_analyzer: {
type: "custom",
tokenizer: "standard",
filter: ["my_custom_word_delimiter_graph_filter", "flatten_graph"],
},
},
filter: {
my_custom_word_delimiter_graph_filter: {
type: "word_delimiter_graph",
catenate_all: true,
},
},
},
},
});
console.log(response);
PUT /my-index-000001
{
"settings": {
"analysis": {
"analyzer": {
"my_custom_index_analyzer": {
"type": "custom",
"tokenizer": "standard",
"filter": [
"my_custom_word_delimiter_graph_filter",
"flatten_graph"
]
}
},
"filter": {
"my_custom_word_delimiter_graph_filter": {
"type": "word_delimiter_graph",
"catenate_all": true
}
}
}
}
}