feat: 新增tesseract OCR demo

klp-wms/src/main/java/com/klp/controller/Application.java

@@ -8,10 +8,15 @@ import javax.imageio.ImageIO;
 import java.awt.*;
 import java.awt.image.BufferedImage;
 import java.io.File;
+import java.io.FileNotFoundException;
 import java.io.IOException;
+import java.io.InputStream;
+import java.net.URL;
+import java.nio.file.Files;
+import java.nio.file.StandardCopyOption;
 
 public class Application {
-    
+
     /**
      * @Description: 识别图片中的文字
      * @param args
@@ -19,41 +24,47 @@ public class Application {
     public static void main(String[] args) {
         try {
             // 获取本地图片
-            File file = new File("D:\\桌面\\照片\\11.png");
+            // File file = new File("D:\\test.png");
-            
+
-            if (!file.exists()) {
+            String imageUrl = "http://47.117.71.33:11296/api/v1/buckets/fadapp-update/objects/download?preview=true&prefix=%E5%BE%AE%E4%BF%A1%E5%9B%BE%E7%89%87_20250731172707.png&version_id=null";
-                System.err.println("图片文件不存在: " + file.getAbsolutePath());
+            // 读取网络图片为 BufferedImage
-                return;
+            URL url = new URL(imageUrl);
-            }
+            InputStream inputStream = url.openStream();
-            
+            BufferedImage image = ImageIO.read(inputStream);
+            inputStream.close();
+            // 预处理图片
+            BufferedImage bufferedImage = preprocessImage(image);
+
             System.out.println("开始OCR识别...");
-            System.out.println("图片路径: " + file.getAbsolutePath());
+
-            
             // 创建Tesseract对象
             ITesseract tesseract = new Tesseract();
-            
+
-            // 设置字体库路径
+            // 设置字体库路径（绝对路径）
-            tesseract.setDatapath("D:\\front");
+            tesseract.setDatapath("D:\\tessdata");
-            
+
+/*            File tessdataDir = exportTessdataToTemp(); // 从 classpath 复制到临时目录
+            tesseract.setDatapath(tessdataDir.getAbsolutePath());*/
+
             // 设置语言简体中文
             tesseract.setLanguage("chi_sim");
-            
+
             // 优化OCR配置
             tesseract.setPageSegMode(6); // 假设统一的文本块
             tesseract.setOcrEngineMode(3); // 使用默认引擎
-            
+
             // 执行OCR识别图片
-            String result = tesseract.doOCR(file);
+            String result = tesseract.doOCR(bufferedImage);
-            
+
             System.out.println("\n=== 原始识别结果 ===");
             System.out.println(result);
-            
+
             // 清理和格式化结果
             String cleanedResult = cleanOcrResult(result);
-            
+
             System.out.println("\n=== 清理后的结果 ===");
             System.out.println(cleanedResult);
-            
+
             // 分行显示结果
             System.out.println("\n=== 分行显示结果 ===");
             String[] lines = cleanedResult.split("-");
@@ -62,7 +73,7 @@ public class Application {
                     System.out.println((i + 1) + ". " + lines[i].trim());
                 }
             }
-            
+
         } catch (TesseractException e) {
             System.err.println("Tesseract OCR错误: " + e.getMessage());
             e.printStackTrace();
@@ -71,7 +82,7 @@ public class Application {
             e.printStackTrace();
         }
     }
-    
+
     /**
      * 清理OCR识别结果
      * @param result 原始识别结果
@@ -81,7 +92,7 @@ public class Application {
         if (result == null || result.trim().isEmpty()) {
             return "";
         }
-        
+
         // 替换常见的OCR错误
         String cleaned = result
             // 替换回车和换行
@@ -117,10 +128,10 @@ public class Application {
             .replaceAll("调教", "调整")
             // 移除多余的空格
             .trim();
-        
+
         return cleaned;
     }
-    
+
     /**
      * 图片预处理（可选）
      * @param inputFile 输入图片
@@ -129,22 +140,61 @@ public class Application {
     private static void preprocessImage(File inputFile, File outputFile) {
         try {
             BufferedImage image = ImageIO.read(inputFile);
-            
+
             // 转换为灰度图
             BufferedImage grayImage = new BufferedImage(
                 image.getWidth(), image.getHeight(), BufferedImage.TYPE_BYTE_GRAY);
-            
+
             Graphics2D g2d = grayImage.createGraphics();
             g2d.drawImage(image, 0, 0, null);
             g2d.dispose();
-            
+
             // 保存预处理后的图片
             ImageIO.write(grayImage, "png", outputFile);
-            
+
             System.out.println("图片预处理完成: " + outputFile.getAbsolutePath());
-            
+
         } catch (IOException e) {
             System.err.println("图片预处理失败: " + e.getMessage());
         }
     }
+
+    /**
+     * 灰度化图像（直接处理 BufferedImage）
+     * @param image 原始图片
+     * @return 灰度图
+     */
+    private static BufferedImage preprocessImage(BufferedImage image) {
+        BufferedImage grayImage = new BufferedImage(
+            image.getWidth(), image.getHeight(), BufferedImage.TYPE_BYTE_GRAY);
+
+        Graphics2D g2d = grayImage.createGraphics();
+        g2d.drawImage(image, 0, 0, null);
+        g2d.dispose();
+
+        return grayImage;
+    }
+
+    public static File exportTessdataToTemp() throws IOException {
+        String[] languageFiles = {"chi_sim.traineddata","chi_sim_vert.traineddata"};
+        // 明确指定临时目录路径（避免路径分隔符问题）
+        File tempTessdataDir = new File(System.getProperty("java.io.tmpdir"), "tessdata");
+        if (!tempTessdataDir.exists()) {
+            tempTessdataDir.mkdirs();
+        }
+
+        ClassLoader classLoader = Application.class.getClassLoader();
+        for (String filename : languageFiles) {
+            // 使用正确的资源路径（注意开头的/）
+            try (InputStream in = classLoader.getResourceAsStream("\\tessdata\\" + filename)) {
+                if (in == null) {
+                    throw new FileNotFoundException("语言包未找到: /tessdata/" + filename);
+                }
+                File outFile = new File(tempTessdataDir, filename);
+                Files.copy(in, outFile.toPath(), StandardCopyOption.REPLACE_EXISTING);
+            }
+        }
+        return tempTessdataDir; // 返回的是 tessdata 目录本身
+    }
+
 }