模式替换字符过滤器
编辑模式替换字符过滤器
编辑pattern_replace 字符过滤器使用正则表达式匹配应替换为指定替换字符串的字符。替换字符串可以引用正则表达式中的捕获组。
注意病态正则表达式
模式替换字符过滤器使用 Java 正则表达式。
编写不当的正则表达式可能会运行非常缓慢，甚至抛出 StackOverflowError 并导致其运行所在的节点突然退出。
阅读更多关于 病态正则表达式以及如何避免它们 的信息。
配置
编辑pattern_replace 字符过滤器接受以下参数
|
|
一个 Java 正则表达式。必填。 |
|
|
替换字符串，可以使用 |
|
|
Java 正则表达式 标志。标志应以管道分隔，例如 |
示例配置
编辑在此示例中，我们配置 pattern_replace 字符过滤器以将数字中的任何嵌入式短划线替换为下划线，即 123-456-789 → 123_456_789
resp = client.indices.create(
index="my-index-000001",
settings={
"analysis": {
"analyzer": {
"my_analyzer": {
"tokenizer": "standard",
"char_filter": [
"my_char_filter"
]
}
},
"char_filter": {
"my_char_filter": {
"type": "pattern_replace",
"pattern": "(\\d+)-(?=\\d)",
"replacement": "$1_"
}
}
}
},
)
print(resp)
resp1 = client.indices.analyze(
index="my-index-000001",
analyzer="my_analyzer",
text="My credit card is 123-456-789",
)
print(resp1)
response = client.indices.create(
index: 'my-index-000001',
body: {
settings: {
analysis: {
analyzer: {
my_analyzer: {
tokenizer: 'standard',
char_filter: [
'my_char_filter'
]
}
},
char_filter: {
my_char_filter: {
type: 'pattern_replace',
pattern: '(\\d+)-(?=\\d)',
replacement: '$1_'
}
}
}
}
}
)
puts response
response = client.indices.analyze(
index: 'my-index-000001',
body: {
analyzer: 'my_analyzer',
text: 'My credit card is 123-456-789'
}
)
puts response
const response = await client.indices.create({
index: "my-index-000001",
settings: {
analysis: {
analyzer: {
my_analyzer: {
tokenizer: "standard",
char_filter: ["my_char_filter"],
},
},
char_filter: {
my_char_filter: {
type: "pattern_replace",
pattern: "(\\d+)-(?=\\d)",
replacement: "$1_",
},
},
},
},
});
console.log(response);
const response1 = await client.indices.analyze({
index: "my-index-000001",
analyzer: "my_analyzer",
text: "My credit card is 123-456-789",
});
console.log(response1);
PUT my-index-000001
{
"settings": {
"analysis": {
"analyzer": {
"my_analyzer": {
"tokenizer": "standard",
"char_filter": [
"my_char_filter"
]
}
},
"char_filter": {
"my_char_filter": {
"type": "pattern_replace",
"pattern": "(\\d+)-(?=\\d)",
"replacement": "$1_"
}
}
}
}
}
POST my-index-000001/_analyze
{
"analyzer": "my_analyzer",
"text": "My credit card is 123-456-789"
}
上述示例生成以下术语
[ My, credit, card, is, 123_456_789 ]
使用更改原始文本长度的替换字符串将适用于搜索目的，但会导致高亮显示不正确，如下例所示。
此示例在遇到小写字母后跟大写字母时插入空格（即 fooBarBaz → foo Bar Baz），允许单独查询 camelCase 单词
resp = client.indices.create(
index="my-index-000001",
settings={
"analysis": {
"analyzer": {
"my_analyzer": {
"tokenizer": "standard",
"char_filter": [
"my_char_filter"
],
"filter": [
"lowercase"
]
}
},
"char_filter": {
"my_char_filter": {
"type": "pattern_replace",
"pattern": "(?<=\\p{Lower})(?=\\p{Upper})",
"replacement": " "
}
}
}
},
mappings={
"properties": {
"text": {
"type": "text",
"analyzer": "my_analyzer"
}
}
},
)
print(resp)
resp1 = client.indices.analyze(
index="my-index-000001",
analyzer="my_analyzer",
text="The fooBarBaz method",
)
print(resp1)
response = client.indices.create(
index: 'my-index-000001',
body: {
settings: {
analysis: {
analyzer: {
my_analyzer: {
tokenizer: 'standard',
char_filter: [
'my_char_filter'
],
filter: [
'lowercase'
]
}
},
char_filter: {
my_char_filter: {
type: 'pattern_replace',
pattern: '(?<=\\p{Lower})(?=\\p{Upper})',
replacement: ' '
}
}
}
},
mappings: {
properties: {
text: {
type: 'text',
analyzer: 'my_analyzer'
}
}
}
}
)
puts response
response = client.indices.analyze(
index: 'my-index-000001',
body: {
analyzer: 'my_analyzer',
text: 'The fooBarBaz method'
}
)
puts response
const response = await client.indices.create({
index: "my-index-000001",
settings: {
analysis: {
analyzer: {
my_analyzer: {
tokenizer: "standard",
char_filter: ["my_char_filter"],
filter: ["lowercase"],
},
},
char_filter: {
my_char_filter: {
type: "pattern_replace",
pattern: "(?<=\\p{Lower})(?=\\p{Upper})",
replacement: " ",
},
},
},
},
mappings: {
properties: {
text: {
type: "text",
analyzer: "my_analyzer",
},
},
},
});
console.log(response);
const response1 = await client.indices.analyze({
index: "my-index-000001",
analyzer: "my_analyzer",
text: "The fooBarBaz method",
});
console.log(response1);
PUT my-index-000001
{
"settings": {
"analysis": {
"analyzer": {
"my_analyzer": {
"tokenizer": "standard",
"char_filter": [
"my_char_filter"
],
"filter": [
"lowercase"
]
}
},
"char_filter": {
"my_char_filter": {
"type": "pattern_replace",
"pattern": "(?<=\\p{Lower})(?=\\p{Upper})",
"replacement": " "
}
}
}
},
"mappings": {
"properties": {
"text": {
"type": "text",
"analyzer": "my_analyzer"
}
}
}
}
POST my-index-000001/_analyze
{
"analyzer": "my_analyzer",
"text": "The fooBarBaz method"
}
上面返回以下术语
[ the, foo, bar, baz, method ]
查询 bar 将正确找到文档，但结果上的高亮显示将产生不正确的高亮显示，因为我们的字符过滤器更改了原始文本的长度
resp = client.index(
index="my-index-000001",
id="1",
refresh=True,
document={
"text": "The fooBarBaz method"
},
)
print(resp)
resp1 = client.search(
index="my-index-000001",
query={
"match": {
"text": "bar"
}
},
highlight={
"fields": {
"text": {}
}
},
)
print(resp1)
response = client.index(
index: 'my-index-000001',
id: 1,
refresh: true,
body: {
text: 'The fooBarBaz method'
}
)
puts response
response = client.search(
index: 'my-index-000001',
body: {
query: {
match: {
text: 'bar'
}
},
highlight: {
fields: {
text: {}
}
}
}
)
puts response
const response = await client.index({
index: "my-index-000001",
id: 1,
refresh: "true",
document: {
text: "The fooBarBaz method",
},
});
console.log(response);
const response1 = await client.search({
index: "my-index-000001",
query: {
match: {
text: "bar",
},
},
highlight: {
fields: {
text: {},
},
},
});
console.log(response1);
PUT my-index-000001/_doc/1?refresh
{
"text": "The fooBarBaz method"
}
GET my-index-000001/_search
{
"query": {
"match": {
"text": "bar"
}
},
"highlight": {
"fields": {
"text": {}
}
}
}
上面的输出为
{
"timed_out": false,
"took": $body.took,
"_shards": {
"total": 1,
"successful": 1,
"skipped" : 0,
"failed": 0
},
"hits": {
"total" : {
"value": 1,
"relation": "eq"
},
"max_score": 0.2876821,
"hits": [
{
"_index": "my-index-000001",
"_id": "1",
"_score": 0.2876821,
"_source": {
"text": "The fooBarBaz method"
},
"highlight": {
"text": [
"The foo<em>Ba</em>rBaz method"
]
}
}
]
}
}