refactor: Improve linux build for system-ocr (#9775)

* refactor(ocr): streamline OCR service registration and improve image preprocessing

- Simplified the registration of the system OCR service by removing the conditional check for Linux.
- Updated SystemOcrService to directly import necessary modules, enhancing clarity.
- Refactored image preprocessing to use a static import of the 'sharp' library for better performance.

* add patch for system-ocr

* add patch

* add patch again

* add patch

* delete setting

* delete i18n

* lint error

* add isLinux

* Revert "delete i18n"

This reverts commit 173e65bbd0.

* Revert "delete setting"

This reverts commit de39c76f83.

* fix: add system check for error message

---------

Co-authored-by: icarus <eurfelux@gmail.com>

.yarn/patches/@napi-rs-system-ocr-npm-1.0.2-59e7a78e8b.patch

@@ -0,0 +1,30 @@
+diff --git a/index.js b/index.js
+index dc071739e79876dff88e1be06a9168e294222d13..b9df7525c62bdf777e89e732e1b0c81f84d872f2 100644
+--- a/index.js
++++ b/index.js
+@@ -380,7 +380,7 @@ if (!nativeBinding || process.env.NAPI_RS_FORCE_WASI) {
+   }
+ }
+ 
+-if (!nativeBinding) {
++if (!nativeBinding && process.platform !== 'linux') {
+   if (loadErrors.length > 0) {
+     throw new Error(
+       `Cannot find native binding. ` +
+@@ -392,6 +392,13 @@ if (!nativeBinding) {
+   throw new Error(`Failed to load native binding`)
+ }
+ 
+-module.exports = nativeBinding
+-module.exports.OcrAccuracy = nativeBinding.OcrAccuracy
+-module.exports.recognize = nativeBinding.recognize
++if (process.platform === 'linux') {
++  module.exports = {OcrAccuracy: {
++    Fast: 0,
++    Accurate: 1
++  }, recognize: () => Promise.resolve({text: '', confidence: 1.0})}
++}else{
++  module.exports = nativeBinding
++  module.exports.OcrAccuracy = nativeBinding.OcrAccuracy
++  module.exports.recognize = nativeBinding.recognize
++}

package.json

@@ -72,7 +72,7 @@
   "dependencies": {
     "@libsql/client": "0.14.0",
     "@libsql/win32-x64-msvc": "^0.4.7",
-    "@napi-rs/system-ocr": "^1.0.2",
+    "@napi-rs/system-ocr": "patch:@napi-rs/system-ocr@npm%3A1.0.2#~/.yarn/patches/@napi-rs-system-ocr-npm-1.0.2-59e7a78e8b.patch",
     "@strongtz/win32-arm64-msvc": "^0.4.7",
     "graceful-fs": "^4.2.11",
     "jsdom": "26.1.0",

scripts/before-pack.js

@@ -7,15 +7,12 @@ const allArm64 = {
   '@img/sharp-darwin-arm64': '0.34.3',
   '@img/sharp-win32-arm64': '0.34.3',
   '@img/sharp-linux-arm64': '0.34.3',
-  '@img/sharp-linuxmusl-arm64': '0.34.3',
 
   '@img/sharp-libvips-darwin-arm64': '1.2.0',
   '@img/sharp-libvips-linux-arm64': '1.2.0',
-  '@img/sharp-libvips-linuxmusl-arm64': '1.2.0',
 
   '@libsql/darwin-arm64': '0.4.7',
   '@libsql/linux-arm64-gnu': '0.4.7',
-  '@libsql/linux-arm64-musl': '0.4.7',
   '@strongtz/win32-arm64-msvc': '0.4.7',
 
   '@napi-rs/system-ocr-darwin-arm64': '1.0.2',
@@ -25,16 +22,13 @@ const allArm64 = {
 const allX64 = {
   '@img/sharp-darwin-x64': '0.34.3',
   '@img/sharp-linux-x64': '0.34.3',
-  '@img/sharp-linuxmusl-x64': '0.34.3',
   '@img/sharp-win32-x64': '0.34.3',
 
   '@img/sharp-libvips-darwin-x64': '1.2.0',
   '@img/sharp-libvips-linux-x64': '1.2.0',
-  '@img/sharp-libvips-linuxmusl-x64': '1.2.0',
 
   '@libsql/darwin-x64': '0.4.7',
   '@libsql/linux-x64-gnu': '0.4.7',
-  '@libsql/linux-x64-musl': '0.4.7',
   '@libsql/win32-x64-msvc': '0.4.7',
 
   '@napi-rs/system-ocr-darwin-x64': '1.0.2',

src/main/services/ocr/OcrService.ts

@@ -2,6 +2,7 @@ import { loggerService } from '@logger'
 import { isLinux } from '@main/constant'
 import { BuiltinOcrProviderIds, OcrHandler, OcrProvider, OcrResult, SupportedOcrFile } from '@types'
 
+import { systemOcrService } from './builtin/SystemOcrService'
 import { tesseractService } from './builtin/TesseractService'
 
 const logger = loggerService.withContext('OcrService')
@@ -34,7 +35,4 @@ export const ocrService = new OcrService()
 // Register built-in providers
 ocrService.register(BuiltinOcrProviderIds.tesseract, tesseractService.ocr.bind(tesseractService))
 
-if (!isLinux) {
-  const { systemOcrService } = require('./builtin/SystemOcrService')
-  ocrService.register(BuiltinOcrProviderIds.system, systemOcrService.ocr.bind(systemOcrService))
-}
+!isLinux && ocrService.register(BuiltinOcrProviderIds.system, systemOcrService.ocr.bind(systemOcrService))

src/main/services/ocr/builtin/SystemOcrService.ts

@@ -1,5 +1,6 @@
 import { isLinux, isWin } from '@main/constant'
 import { loadOcrImage } from '@main/utils/ocr'
+import { OcrAccuracy, recognize } from '@napi-rs/system-ocr'
 import {
   ImageFileMetadata,
   isImageFileMetadata as isImageFileMetadata,
@@ -20,8 +21,6 @@ export class SystemOcrService extends OcrBaseService {
     if (isLinux) {
       return { text: '' }
     }
-
-    const { OcrAccuracy, recognize } = require('@napi-rs/system-ocr')
     const buffer = await loadOcrImage(file)
     const langs = isWin ? options?.langs : undefined
     const result = await recognize(buffer, OcrAccuracy.Accurate, langs)

src/main/utils/ocr.ts

@@ -1,8 +1,8 @@
 import { ImageFileMetadata } from '@types'
 import { readFile } from 'fs/promises'
+import sharp from 'sharp'
 
 const preprocessImage = async (buffer: Buffer): Promise<Buffer> => {
-  const sharp = require('sharp')
   return sharp(buffer)
     .grayscale() // 转为灰度
     .normalize()

src/renderer/src/pages/settings/DocProcessSettings/OcrImageSettings.tsx

@@ -47,12 +47,14 @@ const OcrImageSettings = ({ setProvider }: Props) => {
     }))
   }, [getOcrProviderName, imageProviders, platformSupport])
 
+  const isSystem = imageProvider.id === BuiltinOcrProviderIds.system
+
   return (
     <>
       <SettingRow>
         <SettingRowTitle>{t('settings.tool.ocr.image_provider')}</SettingRowTitle>
         <div style={{ display: 'flex', gap: '8px', alignItems: 'center' }}>
-          {!platformSupport && <ErrorTag message={t('settings.tool.ocr.error.not_system')} />}
+          {!platformSupport && isSystem && <ErrorTag message={t('settings.tool.ocr.error.not_system')} />}
           <Select
             value={imageProvider.id}
             style={{ width: '200px' }}

yarn.lock

@@ -4761,7 +4761,7 @@ __metadata:
   languageName: node
   linkType: hard
 
-"@napi-rs/system-ocr@npm:^1.0.2":
+"@napi-rs/system-ocr@npm:1.0.2":
   version: 1.0.2
   resolution: "@napi-rs/system-ocr@npm:1.0.2"
   dependencies:
@@ -4782,6 +4782,27 @@ __metadata:
   languageName: node
   linkType: hard
 
+"@napi-rs/system-ocr@patch:@napi-rs/system-ocr@npm%3A1.0.2#~/.yarn/patches/@napi-rs-system-ocr-npm-1.0.2-59e7a78e8b.patch":
+  version: 1.0.2
+  resolution: "@napi-rs/system-ocr@patch:@napi-rs/system-ocr@npm%3A1.0.2#~/.yarn/patches/@napi-rs-system-ocr-npm-1.0.2-59e7a78e8b.patch::version=1.0.2&hash=407396"
+  dependencies:
+    "@napi-rs/system-ocr-darwin-arm64": "npm:1.0.2"
+    "@napi-rs/system-ocr-darwin-x64": "npm:1.0.2"
+    "@napi-rs/system-ocr-win32-arm64-msvc": "npm:1.0.2"
+    "@napi-rs/system-ocr-win32-x64-msvc": "npm:1.0.2"
+  dependenciesMeta:
+    "@napi-rs/system-ocr-darwin-arm64":
+      optional: true
+    "@napi-rs/system-ocr-darwin-x64":
+      optional: true
+    "@napi-rs/system-ocr-win32-arm64-msvc":
+      optional: true
+    "@napi-rs/system-ocr-win32-x64-msvc":
+      optional: true
+  checksum: 10c0/c1e336b3d506dd771c72b1bddc94e4a9ddeae5292222a7485d66dd0c11eed5d2a37cc7ea338f229e7d4abad276966658bdb4a2b322c9d6a0349dad6e65fcea51
+  languageName: node
+  linkType: hard
+
 "@napi-rs/wasm-runtime@npm:^0.2.4":
   version: 0.2.12
   resolution: "@napi-rs/wasm-runtime@npm:0.2.12"
@@ -9406,7 +9427,7 @@ __metadata:
     "@mistralai/mistralai": "npm:^1.7.5"
     "@modelcontextprotocol/sdk": "npm:^1.17.0"
     "@mozilla/readability": "npm:^0.6.0"
-    "@napi-rs/system-ocr": "npm:^1.0.2"
+    "@napi-rs/system-ocr": "patch:@napi-rs/system-ocr@npm%3A1.0.2#~/.yarn/patches/@napi-rs-system-ocr-npm-1.0.2-59e7a78e8b.patch"
     "@notionhq/client": "npm:^2.2.15"
     "@opentelemetry/api": "npm:^1.9.0"
     "@opentelemetry/core": "npm:2.0.0"