Remove Punct

removepunct 过滤器会从词项流中移除包含标点符号或空白字符的词项。当您希望进行更干净的文本处理、专注于有意义的内容词而非标点时，可以使用该过滤器。

说明

• 该过滤器在 jieba、lindera 和 icu tokenizer 中最有效，因为这些 tokenizer 会将标点保留为独立的 token（例如 "Hello!" → ["Hello", "!"]）。

• standard 分词器会在分词阶段丢弃标点符号。whitespace 分词器会保留标点符号，包括词项内部的标点。与 whitespace 配合使用时，如果词项包含标点符号或空白字符，removepunct 会删除整个词项，而不是仅移除其中的个别字符。

配置

removepunct 过滤器已内置在 Zilliz Cloud 中。要使用它，只需在 analyzer_params 的 filter 部分指定其名称即可。

Python

python

analyzer_params = {
    "tokenizer": "jieba",
    "filter": ["removepunct"]
}

Java

java

Map<String, Object> analyzerParams = new HashMap<>();
analyzerParams.put("tokenizer", "jieba");
analyzerParams.put("filter", Collections.singletonList("removepunct"));

Go

go

analyzerParams := map[string]any{"tokenizer": "jieba", "filter": []any{"removepunct"}}

Rust

rust

use serde_json::json;

let analyzer_params = json!({
    "tokenizer": "jieba",
    "filter": ["removepunct"]
});

C++

c++

nlohmann::json analyzer_params = {
    {"tokenizer", "jieba"},
    {"filter", {"removepunct"}}
};

NodeJS

javascript

const analyzer_params = {
    "tokenizer": "jieba",
    "filter": ["removepunct"],
};

cURL

bash

# restful
analyzerParams='{
  "tokenizer": "jieba",
  "filter": [
    "removepunct"
  ]
}'

removepunct 过滤器作用于分词器生成的词项，因此必须与分词器结合使用。

定义 analyzer_params 后，您可以在定义 Collection Schema 时将其应用于 VARCHAR 字段。这使得 Zilliz Cloud 能够使用指定的分析器处理该字段中的文本，以实现高效的分词和过滤。更多信息，请参阅使用示例。

示例输出

在完成 Analyzer 配置后，您可以使用 run_analyzer 方法来验证分词效果是否符合预期。

Analyzer 配置

Python

python

analyzer_params = {
    "tokenizer": "icu",
    "filter": ["removepunct"]
}

Java

java

Map<String, Object> analyzerParams = new HashMap<>();
analyzerParams.put("tokenizer", "icu");
analyzerParams.put("filter", Collections.singletonList("removepunct"));

Go

go

analyzerParams := map[string]any{"tokenizer": "icu", "filter": []string{"removepunct"}}

Rust

rust

use serde_json::json;

let analyzer_params = json!({
    "tokenizer": "icu",
    "filter": ["removepunct"]
});

C++

c++

nlohmann::json analyzer_params = {
    {"tokenizer", "icu"},
    {"filter", {"removepunct"}}
};

NodeJS

javascript

const analyzer_params = {
    "tokenizer": "icu",
    "filter": ["removepunct"],
};

cURL

bash

# restful
analyzerParams='{
  "tokenizer": "icu",
  "filter": [
    "removepunct"
  ]
}'

使用 run_analyzer 验证效果

Python

python

from pymilvus import (
    MilvusClient,
)

client = MilvusClient(uri="YOUR_CLUSTER_ENDPOINT")

# Sample text to analyze
sample_text = "Привет! Как дела?"

# Run the standard analyzer with the defined configuration
result = client.run_analyzer(sample_text, analyzer_params)
print("Standard analyzer output:", result)

Java

java

import io.milvus.v2.client.ConnectConfig;
import io.milvus.v2.client.MilvusClientV2;
import io.milvus.v2.service.vector.request.RunAnalyzerReq;
import io.milvus.v2.service.vector.response.RunAnalyzerResp;

ConnectConfig config = ConnectConfig.builder()
        .uri("YOUR_CLUSTER_ENDPOINT")
        .build();
MilvusClientV2 client = new MilvusClientV2(config);

List<String> texts = new ArrayList<>();
texts.add("Привет! Как дела?");

RunAnalyzerResp resp = client.runAnalyzer(RunAnalyzerReq.builder()
        .texts(texts)
        .analyzerParams(analyzerParams)
        .build());
List<RunAnalyzerResp.AnalyzerResult> results = resp.getResults();

Go

go

import (
    "context"
    "fmt"

    "github.com/milvus-io/milvus/client/v3/milvusclient"
)

ctx := context.Background()

client, err := milvusclient.New(ctx, &milvusclient.ClientConfig{
    Address: "YOUR_CLUSTER_ENDPOINT",
    APIKey:  "YOUR_CLUSTER_TOKEN",
})
if err != nil {
    fmt.Println(err.Error())
    // handle error
}

texts := []string{"Привет! Как дела?"}
option := milvusclient.NewRunAnalyzerOption(texts...).
    WithAnalyzerParams(analyzerParams)

result, err := client.RunAnalyzer(ctx, option)
if err != nil {
    fmt.Println(err.Error())
    // handle error
}

Rust

rust

use milvus::v2::prelude::*;
use serde_json::json;

let text = "Привет! Как дела?";

let response = client
    .run_analyzer(
        RunAnalyzerRequest::builder()
            .texts([text])
            .analyzer_params(json!({"tokenizer": "icu", "filter": ["removepunct"]}))
            .build()?,
    )
    .await?;

for result in response.results() {
    for token in result.get_tokens() {
        println!("{}", token.get_text());
    }
}

C++

c++

#include "milvus/MilvusClientV2.h"

auto client = milvus::MilvusClientV2::Create();

milvus::ConnectParam connect_param{"YOUR_CLUSTER_ENDPOINT"};
auto status = client->Connect(connect_param);
if (!status.IsOk()) {
    std::cout << status.Message() << std::endl;
}

std::string text = "Привет! Как дела?";
auto request = milvus::RunAnalyzerRequest()
                       .AddText(text)
                       .WithAnalyzerParams(analyzer_params);

milvus::RunAnalyzerResponse response;
status = client->RunAnalyzer(request, response);
if (!status.IsOk()) {
    std::cout << status.Message() << std::endl;
}

NodeJS

javascript

import { MilvusClient } from "@zilliz/milvus2-sdk-node";

const sampleText = "Привет! Как дела?";

const client = new MilvusClient({
  address: "YOUR_CLUSTER_ENDPOINT",
});

const result = await client.runAnalyzer({
  analyzer_params: analyzerParams,
  text: sampleText,
});

cURL

bash

# restful
curl -X POST "YOUR_CLUSTER_ENDPOINT/v2/vectordb/common/run_analyzer" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_CLUSTER_TOKEN" \
  -d '{
    "analyzerParams": "{\"tokenizer\": \"icu\", \"filter\": [\"removepunct\"]}",
    "text": ["Привет! Как дела?"]
  }'

预期结果

python

['Привет', 'Как', 'дела']