模式分析器
编辑模式分析器
编辑pattern 分析器使用正则表达式将文本拆分为词条。正则表达式应该匹配 词条分隔符，而不是词条本身。正则表达式默认为 \W+ （或所有非单词字符）。
注意病态正则表达式
模式分析器使用 Java 正则表达式。
编写不佳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。
示例输出
编辑resp = client.indices.analyze(
analyzer="pattern",
text="The 2 QUICK Brown-Foxes jumped over the lazy dog's bone.",
)
print(resp)
response = client.indices.analyze(
body: {
analyzer: 'pattern',
text: "The 2 QUICK Brown-Foxes jumped over the lazy dog's bone."
}
)
puts response
const response = await client.indices.analyze({
analyzer: "pattern",
text: "The 2 QUICK Brown-Foxes jumped over the lazy dog's bone.",
});
console.log(response);
POST _analyze
{
"analyzer": "pattern",
"text": "The 2 QUICK Brown-Foxes jumped over the lazy dog's bone."
}
上面的句子会产生以下词条
[ the, 2, quick, brown, foxes, jumped, over, the, lazy, dog, s, bone ]
配置
编辑pattern 分析器接受以下参数
|
|
一个 Java 正则表达式，默认为 |
|
|
Java 正则表达式 标志。标志应该用管道符分隔，例如 |
|
|
词条是否应该小写。默认为 |
|
|
一个预定义的停用词列表，例如 |
|
|
包含停用词的文件路径。 |
有关停用词配置的更多信息，请参阅 停止词语过滤器。
示例配置
编辑在此示例中，我们将 pattern 分析器配置为根据非单词字符或下划线（\W|_）拆分电子邮件地址，并将结果小写
resp = client.indices.create(
index="my-index-000001",
settings={
"analysis": {
"analyzer": {
"my_email_analyzer": {
"type": "pattern",
"pattern": "\\W|_",
"lowercase": True
}
}
}
},
)
print(resp)
resp1 = client.indices.analyze(
index="my-index-000001",
analyzer="my_email_analyzer",
text="[email protected]",
)
print(resp1)
response = client.indices.create(
index: 'my-index-000001',
body: {
settings: {
analysis: {
analyzer: {
my_email_analyzer: {
type: 'pattern',
pattern: '\\W|_',
lowercase: true
}
}
}
}
}
)
puts response
response = client.indices.analyze(
index: 'my-index-000001',
body: {
analyzer: 'my_email_analyzer',
text: '[email protected]'
}
)
puts response
const response = await client.indices.create({
index: "my-index-000001",
settings: {
analysis: {
analyzer: {
my_email_analyzer: {
type: "pattern",
pattern: "\\W|_",
lowercase: true,
},
},
},
},
});
console.log(response);
const response1 = await client.indices.analyze({
index: "my-index-000001",
analyzer: "my_email_analyzer",
text: "[email protected]",
});
console.log(response1);
PUT my-index-000001
{
"settings": {
"analysis": {
"analyzer": {
"my_email_analyzer": {
"type": "pattern",
"pattern": "\\W|_",
"lowercase": true
}
}
}
}
}
POST my-index-000001/_analyze
{
"analyzer": "my_email_analyzer",
"text": "[email protected]"
}
上面的示例产生以下词条
[ john, smith, foo, bar, com ]
CamelCase 分词器
编辑以下更复杂的示例将 CamelCase 文本拆分为词条
resp = client.indices.create(
index="my-index-000001",
settings={
"analysis": {
"analyzer": {
"camel": {
"type": "pattern",
"pattern": "([^\\p{L}\\d]+)|(?<=\\D)(?=\\d)|(?<=\\d)(?=\\D)|(?<=[\\p{L}&&[^\\p{Lu}]])(?=\\p{Lu})|(?<=\\p{Lu})(?=\\p{Lu}[\\p{L}&&[^\\p{Lu}]])"
}
}
}
},
)
print(resp)
resp1 = client.indices.analyze(
index="my-index-000001",
analyzer="camel",
text="MooseX::FTPClass2_beta",
)
print(resp1)
response = client.indices.create(
index: 'my-index-000001',
body: {
settings: {
analysis: {
analyzer: {
camel: {
type: 'pattern',
pattern: '([^\\p{L}\\d]+)|(?<=\\D)(?=\\d)|(?<=\\d)(?=\\D)|(?<=[\\p{L}&&[^\\p{Lu}]])(?=\\p{Lu})|(?<=\\p{Lu})(?=\\p{Lu}[\\p{L}&&[^\\p{Lu}]])'
}
}
}
}
}
)
puts response
response = client.indices.analyze(
index: 'my-index-000001',
body: {
analyzer: 'camel',
text: 'MooseX::FTPClass2_beta'
}
)
puts response
const response = await client.indices.create({
index: "my-index-000001",
settings: {
analysis: {
analyzer: {
camel: {
type: "pattern",
pattern:
"([^\\p{L}\\d]+)|(?<=\\D)(?=\\d)|(?<=\\d)(?=\\D)|(?<=[\\p{L}&&[^\\p{Lu}]])(?=\\p{Lu})|(?<=\\p{Lu})(?=\\p{Lu}[\\p{L}&&[^\\p{Lu}]])",
},
},
},
},
});
console.log(response);
const response1 = await client.indices.analyze({
index: "my-index-000001",
analyzer: "camel",
text: "MooseX::FTPClass2_beta",
});
console.log(response1);
PUT my-index-000001
{
"settings": {
"analysis": {
"analyzer": {
"camel": {
"type": "pattern",
"pattern": "([^\\p{L}\\d]+)|(?<=\\D)(?=\\d)|(?<=\\d)(?=\\D)|(?<=[\\p{L}&&[^\\p{Lu}]])(?=\\p{Lu})|(?<=\\p{Lu})(?=\\p{Lu}[\\p{L}&&[^\\p{Lu}]])"
}
}
}
}
}
GET my-index-000001/_analyze
{
"analyzer": "camel",
"text": "MooseX::FTPClass2_beta"
}
上面的示例产生以下词条
[ moose, x, ftp, class, 2, beta ]
上面的正则表达式更容易理解为
([^\p{L}\d]+) # swallow non letters and numbers,
| (?<=\D)(?=\d) # or non-number followed by number,
| (?<=\d)(?=\D) # or number followed by non-number,
| (?<=[ \p{L} && [^\p{Lu}]]) # or lower case
(?=\p{Lu}) # followed by upper case,
| (?<=\p{Lu}) # or upper case
(?=\p{Lu} # followed by upper case
[\p{L}&&[^\p{Lu}]] # then lower case
)
定义
编辑pattern 分析器由以下部分组成
如果需要自定义 pattern 分析器，超出配置参数的范围，则需要将其重新创建为 custom 分析器并进行修改，通常是通过添加词条过滤器。这将重新创建内置的 pattern 分析器，您可以将其用作进一步自定义的起点
resp = client.indices.create(
index="pattern_example",
settings={
"analysis": {
"tokenizer": {
"split_on_non_word": {
"type": "pattern",
"pattern": "\\W+"
}
},
"analyzer": {
"rebuilt_pattern": {
"tokenizer": "split_on_non_word",
"filter": [
"lowercase"
]
}
}
}
},
)
print(resp)
response = client.indices.create(
index: 'pattern_example',
body: {
settings: {
analysis: {
tokenizer: {
split_on_non_word: {
type: 'pattern',
pattern: '\\W+'
}
},
analyzer: {
rebuilt_pattern: {
tokenizer: 'split_on_non_word',
filter: [
'lowercase'
]
}
}
}
}
}
)
puts response
const response = await client.indices.create({
index: "pattern_example",
settings: {
analysis: {
tokenizer: {
split_on_non_word: {
type: "pattern",
pattern: "\\W+",
},
},
analyzer: {
rebuilt_pattern: {
tokenizer: "split_on_non_word",
filter: ["lowercase"],
},
},
},
},
});
console.log(response);