refactor(ocr): 添加OCR图像预处理功能并优化TesseractService

Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>

src/main/services/ocr/tesseract/TesseractService.ts

@@ -1,5 +1,6 @@
 import { loggerService } from '@logger'
 import { getIpCountry } from '@main/utils/ipService'
+import { loadOcrImage } from '@main/utils/ocr'
 import { MB } from '@shared/config/constant'
 import { ImageFileMetadata, isImageFile, OcrResult, SupportedOcrFile } from '@types'
 import { app } from 'electron'
@@ -39,7 +40,7 @@ export class TesseractService {
     if (stat.size > MB_SIZE_THRESHOLD * MB) {
       throw new Error(`This image is too large (max ${MB_SIZE_THRESHOLD}MB)`)
     }
-    const buffer = await fs.promises.readFile(file.path)
+    const buffer = await loadOcrImage(file)
     const result = await worker.recognize(buffer)
     return { text: result.data.text }
   }

src/main/utils/image.ts

@@ -0,0 +1,11 @@
+import sharp from 'sharp'
+
+/**
+ * 将图片转换为灰度图
+ * @param image 输入的图片 Buffer
+ * @returns Promise<Buffer> 处理后的灰度图片 Buffer
+ * @throws {Error} 当图片处理失败时抛出错误
+ */
+export const greyScale = (image: Buffer): Promise<Buffer> => {
+  return sharp(image).greyscale().toBuffer()
+}

src/main/utils/ocr.ts

@@ -0,0 +1,26 @@
+import { ImageFileMetadata } from '@types'
+import { readFile } from 'fs/promises'
+
+import { greyScale } from './image'
+
+const preprocessImage = (buffer: Buffer) => {
+  return greyScale(buffer)
+}
+
+/**
+ * 加载并预处理OCR图像
+ * @param file - 图像文件元数据
+ * @returns 预处理后的图像Buffer
+ *
+ * 预处理步骤:
+ * 1. 读取图像文件
+ * 2. 转换为灰度图
+ * 3. 后续可扩展其他预处理步骤
+ */
+export const loadOcrImage = async (file: ImageFileMetadata): Promise<Buffer> => {
+  // 读取原始图像
+  const buffer = await readFile(file.path)
+
+  // 统一预处理流程
+  return preprocessImage(buffer)
+}