azure-ai-formrecognizer-java

Name: azure-ai-formrecognizer-java
Author: sickn33

github.com/sickn33文档处理48.7k71 次安装今天更新

代码仓库

关于 azure-ai-formrecognizer-java

面向使用 Java 构建文档分析应用的开发者，介绍 Azure AI Document Intelligence SDK 的 OCR 与结构化提取。内容涵盖预构建和自定义模型、分类及模型管理，并说明示例针对预发布的旧版 API。

主要功能

01分析文本、表格和选择标记
02提取常见文档类型的字段
03构建并组合自定义模型
04构建并运行文档分类器
05使用管理客户端管理模型
06处理轮询和 HTTP 错误

适用场景

01从 PDF 提取文本和表格
02读取发票和收据字段
03按类型分类文档
04训练和应用自定义模型

安装

复制下面的命令，在终端中运行。

$npx skills add https://github.com/sickn33/agentic-awesome-skills --skill azure-ai-formrecognizer-java

安装后在 Claude Code 中输入/azure-ai-formrecognizer-java确认已加载。

详细介绍

Azure Document Intelligence（Form Recognizer）Java SDK

使用 Azure AI Document Intelligence Java SDK 构建文档分析应用程序。

版本和文档边界

这些示例面向旧版 azure-ai-formrecognizer API 和预发布依赖项；使用前请确认所选构件／服务 API 及支持的模型 ID，而不要假设它们与较新的 Document Intelligence SDK 完全一致。上传文档前请先获得许可，尤其是身份证明和财务记录；请使用短时有效、权限范围严格受限的 SAS URL，切勿记录其查询字符串或提取的内容。构建／删除模型操作会更改计费资源。OCR 字段及其置信度并不确定：调用每个嵌套 Items 字段的类型化 getter 前，请先检查其是否为 null 及其类型；根据源文档验证结果，并妥善处理轮询过程中的终态失败／超时以及启动错误。客户端声明是彼此独立的备选代码片段，并非可编译的单个文件。

安装

<dependency>
    <groupId>com.azure</groupId>
    <artifactId>azure-ai-formrecognizer</artifactId>
    <version>4.2.0-beta.1</version>
</dependency>

创建客户端

DocumentAnalysisClient

import com.azure.ai.formrecognizer.documentanalysis.DocumentAnalysisClient;
import com.azure.ai.formrecognizer.documentanalysis.DocumentAnalysisClientBuilder;
import com.azure.core.credential.AzureKeyCredential;

DocumentAnalysisClient client = new DocumentAnalysisClientBuilder()
    .credential(new AzureKeyCredential("{key}"))
    .endpoint("{endpoint}")
    .buildClient();

DocumentModelAdministrationClient

import com.azure.ai.formrecognizer.documentanalysis.administration.DocumentModelAdministrationClient;
import com.azure.ai.formrecognizer.documentanalysis.administration.DocumentModelAdministrationClientBuilder;

DocumentModelAdministrationClient adminClient = new DocumentModelAdministrationClientBuilder()
    .credential(new AzureKeyCredential("{key}"))
    .endpoint("{endpoint}")
    .buildClient();

使用 DefaultAzureCredential

import com.azure.identity.DefaultAzureCredentialBuilder;

DocumentAnalysisClient client = new DocumentAnalysisClientBuilder()
    .endpoint("{endpoint}")
    .credential(new DefaultAzureCredentialBuilder().build())
    .buildClient();

预构建模型

模型 ID	用途
`prebuilt-layout`	提取文本、表格和选择标记
`prebuilt-document`	提取包含键值对的一般文档
`prebuilt-receipt`	提取收据数据
`prebuilt-invoice`	提取发票字段
`prebuilt-businessCard`	解析名片
`prebuilt-idDocument`	身份证件（护照、驾照）
`prebuilt-tax.us.w2`	美国 W2 税表

核心模式

提取版面布局

import com.azure.ai.formrecognizer.documentanalysis.models.*;
import com.azure.core.util.BinaryData;
import com.azure.core.util.polling.SyncPoller;
import java.io.File;

File document = new File("document.pdf");
BinaryData documentData = BinaryData.fromFile(document.toPath());

SyncPoller<OperationResult, AnalyzeResult> poller = 
    client.beginAnalyzeDocument("prebuilt-layout", documentData);

AnalyzeResult result = poller.getFinalResult();

// Process pages
for (DocumentPage page : result.getPages()) {
    System.out.printf("Page %d: %.2f x %.2f %s%n",
        page.getPageNumber(),
        page.getWidth(),
        page.getHeight(),
        page.getUnit());
    
    // Lines
    for (DocumentLine line : page.getLines()) {
        System.out.println("Line: " + line.getContent());
    }
    
    // Selection marks (checkboxes)
    for (DocumentSelectionMark mark : page.getSelectionMarks()) {
        System.out.printf("Checkbox: %s (confidence: %.2f)%n",
            mark.getSelectionMarkState(),
            mark.getConfidence());
    }
}

// Tables
for (DocumentTable table : result.getTables()) {
    System.out.printf("Table: %d rows x %d columns%n",
        table.getRowCount(),
        table.getColumnCount());
    
    for (DocumentTableCell cell : table.getCells()) {
        System.out.printf("Cell[%d,%d]: %s%n",
            cell.getRowIndex(),
            cell.getColumnIndex(),
            cell.getContent());
    }
}

从 URL 分析

String documentUrl = "https://example.com/invoice.pdf";

SyncPoller<OperationResult, AnalyzeResult> poller = 
    client.beginAnalyzeDocumentFromUrl("prebuilt-invoice", documentUrl);

AnalyzeResult result = poller.getFinalResult();

分析收据

SyncPoller<OperationResult, AnalyzeResult> poller = 
    client.beginAnalyzeDocumentFromUrl("prebuilt-receipt", receiptUrl);

AnalyzeResult result = poller.getFinalResult();

for (AnalyzedDocument doc : result.getDocuments()) {
    Map<String, DocumentField> fields = doc.getFields();
    
    DocumentField merchantName = fields.get("MerchantName");
    if (merchantName != null && merchantName.getType() == DocumentFieldType.STRING) {
        System.out.printf("Merchant: %s (confidence: %.2f)%n",
            merchantName.getValueAsString(),
            merchantName.getConfidence());
    }
    
    DocumentField transactionDate = fields.get("TransactionDate");
    if (transactionDate != null && transactionDate.getType() == DocumentFieldType.DATE) {
        System.out.printf("Date: %s%n", transactionDate.getValueAsDate());
    }
    
    DocumentField items = fields.get("Items");
    if (items != null && items.getType() == DocumentFieldType.LIST) {
        for (DocumentField item : items.getValueAsList()) {
            Map<String, DocumentField> itemFields = item.getValueAsMap();
            System.out.printf("Item: %s, Price: %.2f%n",
                itemFields.get("Name").getValueAsString(),
                itemFields.get("Price").getValueAsDouble());
        }
    }
}

通用文档分析

SyncPoller<OperationResult, AnalyzeResult> poller = 
    client.beginAnalyzeDocumentFromUrl("prebuilt-document", documentUrl);

AnalyzeResult result = poller.getFinalResult();

// Key-value pairs
for (DocumentKeyValuePair kvp : result.getKeyValuePairs()) {
    System.out.printf("Key: %s => Value: %s%n",
        kvp.getKey().getContent(),
        kvp.getValue() != null ? kvp.getValue().getContent() : "null");
}

自定义模型

构建自定义模型

import com.azure.ai.formrecognizer.documentanalysis.administration.models.*;

String blobContainerUrl = "{SAS_URL_of_training_data}";
String prefix = "training-docs/";

SyncPoller<OperationResult, DocumentModelDetails> poller = adminClient.beginBuildDocumentModel(
    blobContainerUrl,
    DocumentModelBuildMode.TEMPLATE,
    prefix,
    new BuildDocumentModelOptions()
        .setModelId("my-custom-model")
        .setDescription("Custom invoice model"),
    Context.NONE);

DocumentModelDetails model = poller.getFinalResult();

System.out.println("Model ID: " + model.getModelId());
System.out.println("Created: " + model.getCreatedOn());

model.getDocumentTypes().forEach((docType, details) -> {
    System.out.println("Document type: " + docType);
    details.getFieldSchema().forEach((field, schema) -> {
        System.out.printf("  Field: %s (%s)%n", field, schema.getType());
    });
});

使用自定义模型分析

SyncPoller<OperationResult, AnalyzeResult> poller = 
    client.beginAnalyzeDocumentFromUrl("my-custom-model", documentUrl);

AnalyzeResult result = poller.getFinalResult();

for (AnalyzedDocument doc : result.getDocuments()) {
    System.out.printf("Document type: %s (confidence: %.2f)%n",
        doc.getDocType(),
        doc.getConfidence());
    
    doc.getFields().forEach((name, field) -> {
        System.out.printf("Field '%s': %s (confidence: %.2f)%n",
            name,
            field.getContent(),
            field.getConfidence());
    });
}

组合模型

List<String> modelIds = Arrays.asList("model-1", "model-2", "model-3");

SyncPoller<OperationResult, DocumentModelDetails> poller = 
    adminClient.beginComposeDocumentModel(
        modelIds,
        new ComposeDocumentModelOptions()
            .setModelId("composed-model")
            .setDescription("Composed from multiple models"));

DocumentModelDetails composedModel = poller.getFinalResult();

管理模型

// List models
PagedIterable<DocumentModelSummary> models = adminClient.listDocumentModels();
for (DocumentModelSummary summary : models) {
    System.out.printf("Model: %s, Created: %s%n",
        summary.getModelId(),
        summary.getCreatedOn());
}

// Get model details
DocumentModelDetails model = adminClient.getDocumentModel("model-id");

// Delete model
adminClient.deleteDocumentModel("model-id");

// Check resource limits
ResourceDetails resources = adminClient.getResourceDetails();
System.out.printf("Models: %d / %d%n",
    resources.getCustomDocumentModelCount(),
    resources.getCustomDocumentModelLimit());

文档分类

构建分类器

Map<String, ClassifierDocumentTypeDetails> docTypes = new HashMap<>();
docTypes.put("invoice", new ClassifierDocumentTypeDetails()
    .setAzureBlobSource(new AzureBlobContentSource(containerUrl).setPrefix("invoices/")));
docTypes.put("receipt", new ClassifierDocumentTypeDetails()
    .setAzureBlobSource(new AzureBlobContentSource(containerUrl).setPrefix("receipts/")));

SyncPoller<OperationResult, DocumentClassifierDetails> poller = 
    adminClient.beginBuildDocumentClassifier(docTypes,
        new BuildDocumentClassifierOptions().setClassifierId("my-classifier"));

DocumentClassifierDetails classifier = poller.getFinalResult();

对文档分类

SyncPoller<OperationResult, AnalyzeResult> poller = 
    client.beginClassifyDocumentFromUrl("my-classifier", documentUrl, Context.NONE);

AnalyzeResult result = poller.getFinalResult();

for (AnalyzedDocument doc : result.getDocuments()) {
    System.out.printf("Classified as: %s (confidence: %.2f)%n",
        doc.getDocType(),
        doc.getConfidence());
}

错误处理

import com.azure.core.exception.HttpResponseException;

try {
    client.beginAnalyzeDocumentFromUrl("prebuilt-receipt", "invalid-url");
} catch (HttpResponseException e) {
    System.out.println("Status: " + e.getResponse().getStatusCode());
    System.out.println("Error: " + e.getMessage());
}

环境变量

FORM_RECOGNIZER_ENDPOINT=https://<resource>.cognitiveservices.azure.com/
FORM_RECOGNIZER_KEY=<your-api-key>

触发短语

“document intelligence Java”
“form recognizer SDK”
“extract text from PDF”
“OCR document Java”
“analyze invoice receipt”
“custom document model”
“document classification”

适用场景

当任务符合概述中描述的工作流或操作时，可使用此技能。

限制

仅当任务明确符合上述范围时，才使用此技能。
请勿将输出视为针对特定环境进行验证、测试或专家审查的替代品。
如果缺少必需的输入、权限、安全边界或成功标准，请停止并请求澄清。

支持 Markdown

登录后评论

基本信息

作者: sickn33
仓库: sickn33/agentic-awesome-skills
分类: 文档处理
安装次数: 71
GitHub Stars: 48,675

报告问题