From 9eccd96b007dfb5f332a834afd5bba4c6775e283 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E6=9B=B9=E9=B9=8F=E9=A3=9E?= <rakor2010@gmail.com>
Date: Fri, 8 May 2026 09:03:02 +0800
Subject: [PATCH] =?UTF-8?q?feat(pdf-extract):=20=E6=96=B0=E5=A2=9EPDF?=
 =?UTF-8?q?=E5=B0=BA=E5=AF=B8=E5=8C=BA=E5=9F=9F=E6=8F=90=E5=8F=96=E5=8A=9F?=
 =?UTF-8?q?=E8=83=BD?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

- 在PdfExtractionService中实现从PDF URL中提取尺寸数据
- 通过URL读取PDF字节流并加载文档进行文本位置解析
- 利用文本分组和维度识别器提取尺寸信息列表
- 在QmsInspectionStandardController添加GET接口，支持通过URL参数提取尺寸数据
- 在QmsInspectionStandardControllerService中添加对应服务方法调用pdfExtractionService接口
---
 .../QmsInspectionStandardController.java      |  9 +++++++
 ...msInspectionStandardControllerService.java |  4 +++
 .../java/service/PdfExtractionService.java    | 25 +++++++++++++++++++
 3 files changed, 38 insertions(+)

diff --git a/nflg-qms-admin/src/main/java/com/nflg/qms/admin/controller/QmsInspectionStandardController.java b/nflg-qms-admin/src/main/java/com/nflg/qms/admin/controller/QmsInspectionStandardController.java
index 2065acae..3e4a53bb 100644
--- a/nflg-qms-admin/src/main/java/com/nflg/qms/admin/controller/QmsInspectionStandardController.java
+++ b/nflg-qms-admin/src/main/java/com/nflg/qms/admin/controller/QmsInspectionStandardController.java
@@ -13,6 +13,7 @@ import jakarta.annotation.Resource;
 import jakarta.validation.Valid;
 import jakarta.validation.constraints.NotNull;
 import model.DimensionResult;
+import org.springframework.http.ResponseEntity;
 import org.springframework.validation.annotation.Validated;
 import org.springframework.web.bind.annotation.*;
 
@@ -106,4 +107,12 @@ public class QmsInspectionStandardController extends BaseController {
     public ApiResult<List<DimensionResult>> pdfExtractRegion(@Valid @RequestBody QmsPdfExtractRegionQO request) throws IOException {
         return ApiResult.success(inspectionStandardControllerService.pdfExtractRegion(request));
     }
+
+    /**
+     * 提取PDF文件的所有区域数据
+     */
+    @GetMapping("/pdf/dimensions")
+    public ApiResult<List<DimensionResult>> extractDimensions(@RequestParam String url) throws IOException {
+        return ApiResult.success(inspectionStandardControllerService.extractDimensions(url));
+    }
 }
diff --git a/nflg-qms-admin/src/main/java/com/nflg/qms/admin/service/QmsInspectionStandardControllerService.java b/nflg-qms-admin/src/main/java/com/nflg/qms/admin/service/QmsInspectionStandardControllerService.java
index e75db1cd..273473ee 100644
--- a/nflg-qms-admin/src/main/java/com/nflg/qms/admin/service/QmsInspectionStandardControllerService.java
+++ b/nflg-qms-admin/src/main/java/com/nflg/qms/admin/service/QmsInspectionStandardControllerService.java
@@ -713,4 +713,8 @@ public class QmsInspectionStandardControllerService {
         );
         return regionFilterService.mergeRegionResults(filtered);
     }
+
+    public List<DimensionResult> extractDimensions(String url) throws IOException {
+        return pdfExtractionService.extractDimensions(url);
+    }
 }
diff --git a/nflg-qms-pdf-extract/src/main/java/service/PdfExtractionService.java b/nflg-qms-pdf-extract/src/main/java/service/PdfExtractionService.java
index d1c8d3e3..f7d1aa20 100644
--- a/nflg-qms-pdf-extract/src/main/java/service/PdfExtractionService.java
+++ b/nflg-qms-pdf-extract/src/main/java/service/PdfExtractionService.java
@@ -15,6 +15,7 @@ import java.io.File;
 import java.io.IOException;
 import java.io.InputStream;
 import java.io.StringWriter;
+import java.net.MalformedURLException;
 import java.net.URL;
 import java.nio.file.Path;
 import java.util.List;
@@ -80,6 +81,30 @@ public class PdfExtractionService {
         }
     }
 
+    public List<DimensionResult> extractDimensions(String pdfUrl) throws IOException {
+        byte[] pdfBytes;
+        try (InputStream in = new URL(pdfUrl).openStream();
+             ByteArrayOutputStream buffer = new ByteArrayOutputStream()) {
+            byte[] chunk = new byte[8192];
+            int len;
+            while ((len = in.read(chunk)) != -1) {
+                buffer.write(chunk, 0, len);
+            }
+            pdfBytes = buffer.toByteArray();
+        }
+        try (PDDocument document = Loader.loadPDF(pdfBytes)) {
+            int totalPages = document.getNumberOfPages();
+            PositionedTextStripper stripper = new PositionedTextStripper();
+            stripper.setSortByPosition(true);
+            StringWriter writer = new StringWriter();
+            stripper.writeText(document, writer);
+            List<TextElement> allElements = stripper.getElements();
+
+            List<TextGroup> groups = textGrouper.groupTextElements(allElements);
+            return dimensionIdentifier.identifyDimensions(groups);
+        }
+    }
+
     public static class ExtractionResult {
         private final List<DimensionResult> dimensions;
         private final int totalPages;