feat: OCR 后端切换飞桨——RapidOCR ONNX(@gutenye/ocr-node,PaddleOCR v4 模型全离线)

This commit is contained in:
yu 2026-10-29 14:13:50 +08:00
parent 06886c5b31
commit 3b0883c80f
3 changed files with 716 additions and 47 deletions

676
package-lock.json generated
View File

@ -8,6 +8,8 @@
"name": "rpa-studio",
"version": "0.1.0",
"dependencies": {
"@gutenye/ocr-models": "^1.4.2",
"@gutenye/ocr-node": "^1.4.9",
"@xyflow/react": "^12.12.0",
"adm-zip": "^0.5.16",
"basic-ftp": "^6.2.3",
@ -628,6 +630,23 @@
"node": ">=14.14"
}
},
"node_modules/@emnapi/runtime": {
"version": "1.11.3",
"resolved": "https://registry.npmmirror.com/@emnapi/runtime/-/runtime-1.11.3.tgz",
"integrity": "sha512-Xz4Tpyki7XyrpbUK1jR1AhdAdaXyhhY4lZ3neLodmhpuWfy2PAQN5B46sAiU4liOXGLkHypn/qU+jvfWSCYYLA==",
"license": "MIT",
"optional": true,
"dependencies": {
"tslib": "^2.4.0"
}
},
"node_modules/@emnapi/runtime/node_modules/tslib": {
"version": "2.8.1",
"resolved": "https://registry.npmmirror.com/tslib/-/tslib-2.8.1.tgz",
"integrity": "sha512-oJFu94HQb+KVduSUQL7wnpmqnfmLsOA/nAh6b6EH0wCEoK0/mPeXU6c3wKDV83MkOuHPRHtSXKKU99IBazS/2w==",
"license": "0BSD",
"optional": true
},
"node_modules/@esbuild/aix-ppc64": {
"version": "0.28.2",
"resolved": "https://registry.npmmirror.com/@esbuild/aix-ppc64/-/aix-ppc64-0.28.2.tgz",
@ -1111,6 +1130,500 @@
"integrity": "sha512-fAtCfv4jJg+ExtXhvCkCqUKZ+4ok/JQk01qDKhL5BDDoS3AxKXhV5/MAVUZyQnSEd2GT92fkgZl0pz0Q0AzcIQ==",
"license": "MIT"
},
"node_modules/@gutenye/ocr-common": {
"version": "1.4.9",
"resolved": "https://registry.npmmirror.com/@gutenye/ocr-common/-/ocr-common-1.4.9.tgz",
"integrity": "sha512-1ry8Uw5fWZBZ/TsYB31x/YH04cOk7cO2PyLcauW9rmrK+0bxV0IeBRWngeje+fhdVJ99L1s+Y0BZwrjEVCxgOA==",
"license": "MIT",
"dependencies": {
"@techstark/opencv-js": "^4.9.0-release.3",
"js-clipper": "^1.0.1",
"tiny-invariant": "^1.3.3"
}
},
"node_modules/@gutenye/ocr-models": {
"version": "1.4.2",
"resolved": "https://registry.npmmirror.com/@gutenye/ocr-models/-/ocr-models-1.4.2.tgz",
"integrity": "sha512-y7cLEpGFOeroavopfCd/ejyZB/UeF6xdn0mBFqVHNOI5wQTv2My+/nKxvxKTtG4DVMBzt9TpOfaX7aZGbuciUw==",
"license": "MIT"
},
"node_modules/@gutenye/ocr-node": {
"version": "1.4.9",
"resolved": "https://registry.npmmirror.com/@gutenye/ocr-node/-/ocr-node-1.4.9.tgz",
"integrity": "sha512-D0cGYxld8l3ezhiZwE5WQNanPP3pqY99OBAA7dSNivxVNd7nLih7XqUIQ6vsf6jOeW0C4SO0PQWzzygt1g/Yng==",
"license": "MIT",
"dependencies": {
"@gutenye/ocr-common": "^1.2.0",
"@gutenye/ocr-models": "^1.2.2",
"onnxruntime-node": "^1.22.0-rev",
"sharp": "^0.34.3"
}
},
"node_modules/@img/colour": {
"version": "1.1.0",
"resolved": "https://registry.npmmirror.com/@img/colour/-/colour-1.1.0.tgz",
"integrity": "sha512-Td76q7j57o/tLVdgS746cYARfSyxk8iEfRxewL9h4OMzYhbW4TAcppl0mT4eyqXddh6L/jwoM75mo7ixa/pCeQ==",
"license": "MIT",
"engines": {
"node": ">=18"
}
},
"node_modules/@img/sharp-darwin-arm64": {
"version": "0.34.5",
"resolved": "https://registry.npmmirror.com/@img/sharp-darwin-arm64/-/sharp-darwin-arm64-0.34.5.tgz",
"integrity": "sha512-imtQ3WMJXbMY4fxb/Ndp6HBTNVtWCUI0WdobyheGf5+ad6xX8VIDO8u2xE4qc/fr08CKG/7dDseFtn6M6g/r3w==",
"cpu": [
"arm64"
],
"license": "Apache-2.0",
"optional": true,
"os": [
"darwin"
],
"engines": {
"node": "^18.17.0 || ^20.3.0 || >=21.0.0"
},
"funding": {
"url": "https://opencollective.com/libvips"
},
"optionalDependencies": {
"@img/sharp-libvips-darwin-arm64": "1.2.4"
}
},
"node_modules/@img/sharp-darwin-x64": {
"version": "0.34.5",
"resolved": "https://registry.npmmirror.com/@img/sharp-darwin-x64/-/sharp-darwin-x64-0.34.5.tgz",
"integrity": "sha512-YNEFAF/4KQ/PeW0N+r+aVVsoIY0/qxxikF2SWdp+NRkmMB7y9LBZAVqQ4yhGCm/H3H270OSykqmQMKLBhBJDEw==",
"cpu": [
"x64"
],
"license": "Apache-2.0",
"optional": true,
"os": [
"darwin"
],
"engines": {
"node": "^18.17.0 || ^20.3.0 || >=21.0.0"
},
"funding": {
"url": "https://opencollective.com/libvips"
},
"optionalDependencies": {
"@img/sharp-libvips-darwin-x64": "1.2.4"
}
},
"node_modules/@img/sharp-libvips-darwin-arm64": {
"version": "1.2.4",
"resolved": "https://registry.npmmirror.com/@img/sharp-libvips-darwin-arm64/-/sharp-libvips-darwin-arm64-1.2.4.tgz",
"integrity": "sha512-zqjjo7RatFfFoP0MkQ51jfuFZBnVE2pRiaydKJ1G/rHZvnsrHAOcQALIi9sA5co5xenQdTugCvtb1cuf78Vf4g==",
"cpu": [
"arm64"
],
"license": "LGPL-3.0-or-later",
"optional": true,
"os": [
"darwin"
],
"funding": {
"url": "https://opencollective.com/libvips"
}
},
"node_modules/@img/sharp-libvips-darwin-x64": {
"version": "1.2.4",
"resolved": "https://registry.npmmirror.com/@img/sharp-libvips-darwin-x64/-/sharp-libvips-darwin-x64-1.2.4.tgz",
"integrity": "sha512-1IOd5xfVhlGwX+zXv2N93k0yMONvUlANylbJw1eTah8K/Jtpi15KC+WSiaX/nBmbm2HxRM1gZ0nSdjSsrZbGKg==",
"cpu": [
"x64"
],
"license": "LGPL-3.0-or-later",
"optional": true,
"os": [
"darwin"
],
"funding": {
"url": "https://opencollective.com/libvips"
}
},
"node_modules/@img/sharp-libvips-linux-arm": {
"version": "1.2.4",
"resolved": "https://registry.npmmirror.com/@img/sharp-libvips-linux-arm/-/sharp-libvips-linux-arm-1.2.4.tgz",
"integrity": "sha512-bFI7xcKFELdiNCVov8e44Ia4u2byA+l3XtsAj+Q8tfCwO6BQ8iDojYdvoPMqsKDkuoOo+X6HZA0s0q11ANMQ8A==",
"cpu": [
"arm"
],
"license": "LGPL-3.0-or-later",
"optional": true,
"os": [
"linux"
],
"funding": {
"url": "https://opencollective.com/libvips"
}
},
"node_modules/@img/sharp-libvips-linux-arm64": {
"version": "1.2.4",
"resolved": "https://registry.npmmirror.com/@img/sharp-libvips-linux-arm64/-/sharp-libvips-linux-arm64-1.2.4.tgz",
"integrity": "sha512-excjX8DfsIcJ10x1Kzr4RcWe1edC9PquDRRPx3YVCvQv+U5p7Yin2s32ftzikXojb1PIFc/9Mt28/y+iRklkrw==",
"cpu": [
"arm64"
],
"license": "LGPL-3.0-or-later",
"optional": true,
"os": [
"linux"
],
"funding": {
"url": "https://opencollective.com/libvips"
}
},
"node_modules/@img/sharp-libvips-linux-ppc64": {
"version": "1.2.4",
"resolved": "https://registry.npmmirror.com/@img/sharp-libvips-linux-ppc64/-/sharp-libvips-linux-ppc64-1.2.4.tgz",
"integrity": "sha512-FMuvGijLDYG6lW+b/UvyilUWu5Ayu+3r2d1S8notiGCIyYU/76eig1UfMmkZ7vwgOrzKzlQbFSuQfgm7GYUPpA==",
"cpu": [
"ppc64"
],
"license": "LGPL-3.0-or-later",
"optional": true,
"os": [
"linux"
],
"funding": {
"url": "https://opencollective.com/libvips"
}
},
"node_modules/@img/sharp-libvips-linux-riscv64": {
"version": "1.2.4",
"resolved": "https://registry.npmmirror.com/@img/sharp-libvips-linux-riscv64/-/sharp-libvips-linux-riscv64-1.2.4.tgz",
"integrity": "sha512-oVDbcR4zUC0ce82teubSm+x6ETixtKZBh/qbREIOcI3cULzDyb18Sr/Wcyx7NRQeQzOiHTNbZFF1UwPS2scyGA==",
"cpu": [
"riscv64"
],
"license": "LGPL-3.0-or-later",
"optional": true,
"os": [
"linux"
],
"funding": {
"url": "https://opencollective.com/libvips"
}
},
"node_modules/@img/sharp-libvips-linux-s390x": {
"version": "1.2.4",
"resolved": "https://registry.npmmirror.com/@img/sharp-libvips-linux-s390x/-/sharp-libvips-linux-s390x-1.2.4.tgz",
"integrity": "sha512-qmp9VrzgPgMoGZyPvrQHqk02uyjA0/QrTO26Tqk6l4ZV0MPWIW6LTkqOIov+J1yEu7MbFQaDpwdwJKhbJvuRxQ==",
"cpu": [
"s390x"
],
"license": "LGPL-3.0-or-later",
"optional": true,
"os": [
"linux"
],
"funding": {
"url": "https://opencollective.com/libvips"
}
},
"node_modules/@img/sharp-libvips-linux-x64": {
"version": "1.2.4",
"resolved": "https://registry.npmmirror.com/@img/sharp-libvips-linux-x64/-/sharp-libvips-linux-x64-1.2.4.tgz",
"integrity": "sha512-tJxiiLsmHc9Ax1bz3oaOYBURTXGIRDODBqhveVHonrHJ9/+k89qbLl0bcJns+e4t4rvaNBxaEZsFtSfAdquPrw==",
"cpu": [
"x64"
],
"license": "LGPL-3.0-or-later",
"optional": true,
"os": [
"linux"
],
"funding": {
"url": "https://opencollective.com/libvips"
}
},
"node_modules/@img/sharp-libvips-linuxmusl-arm64": {
"version": "1.2.4",
"resolved": "https://registry.npmmirror.com/@img/sharp-libvips-linuxmusl-arm64/-/sharp-libvips-linuxmusl-arm64-1.2.4.tgz",
"integrity": "sha512-FVQHuwx1IIuNow9QAbYUzJ+En8KcVm9Lk5+uGUQJHaZmMECZmOlix9HnH7n1TRkXMS0pGxIJokIVB9SuqZGGXw==",
"cpu": [
"arm64"
],
"license": "LGPL-3.0-or-later",
"optional": true,
"os": [
"linux"
],
"funding": {
"url": "https://opencollective.com/libvips"
}
},
"node_modules/@img/sharp-libvips-linuxmusl-x64": {
"version": "1.2.4",
"resolved": "https://registry.npmmirror.com/@img/sharp-libvips-linuxmusl-x64/-/sharp-libvips-linuxmusl-x64-1.2.4.tgz",
"integrity": "sha512-+LpyBk7L44ZIXwz/VYfglaX/okxezESc6UxDSoyo2Ks6Jxc4Y7sGjpgU9s4PMgqgjj1gZCylTieNamqA1MF7Dg==",
"cpu": [
"x64"
],
"license": "LGPL-3.0-or-later",
"optional": true,
"os": [
"linux"
],
"funding": {
"url": "https://opencollective.com/libvips"
}
},
"node_modules/@img/sharp-linux-arm": {
"version": "0.34.5",
"resolved": "https://registry.npmmirror.com/@img/sharp-linux-arm/-/sharp-linux-arm-0.34.5.tgz",
"integrity": "sha512-9dLqsvwtg1uuXBGZKsxem9595+ujv0sJ6Vi8wcTANSFpwV/GONat5eCkzQo/1O6zRIkh0m/8+5BjrRr7jDUSZw==",
"cpu": [
"arm"
],
"license": "Apache-2.0",
"optional": true,
"os": [
"linux"
],
"engines": {
"node": "^18.17.0 || ^20.3.0 || >=21.0.0"
},
"funding": {
"url": "https://opencollective.com/libvips"
},
"optionalDependencies": {
"@img/sharp-libvips-linux-arm": "1.2.4"
}
},
"node_modules/@img/sharp-linux-arm64": {
"version": "0.34.5",
"resolved": "https://registry.npmmirror.com/@img/sharp-linux-arm64/-/sharp-linux-arm64-0.34.5.tgz",
"integrity": "sha512-bKQzaJRY/bkPOXyKx5EVup7qkaojECG6NLYswgktOZjaXecSAeCWiZwwiFf3/Y+O1HrauiE3FVsGxFg8c24rZg==",
"cpu": [
"arm64"
],
"license": "Apache-2.0",
"optional": true,
"os": [
"linux"
],
"engines": {
"node": "^18.17.0 || ^20.3.0 || >=21.0.0"
},
"funding": {
"url": "https://opencollective.com/libvips"
},
"optionalDependencies": {
"@img/sharp-libvips-linux-arm64": "1.2.4"
}
},
"node_modules/@img/sharp-linux-ppc64": {
"version": "0.34.5",
"resolved": "https://registry.npmmirror.com/@img/sharp-linux-ppc64/-/sharp-linux-ppc64-0.34.5.tgz",
"integrity": "sha512-7zznwNaqW6YtsfrGGDA6BRkISKAAE1Jo0QdpNYXNMHu2+0dTrPflTLNkpc8l7MUP5M16ZJcUvysVWWrMefZquA==",
"cpu": [
"ppc64"
],
"license": "Apache-2.0",
"optional": true,
"os": [
"linux"
],
"engines": {
"node": "^18.17.0 || ^20.3.0 || >=21.0.0"
},
"funding": {
"url": "https://opencollective.com/libvips"
},
"optionalDependencies": {
"@img/sharp-libvips-linux-ppc64": "1.2.4"
}
},
"node_modules/@img/sharp-linux-riscv64": {
"version": "0.34.5",
"resolved": "https://registry.npmmirror.com/@img/sharp-linux-riscv64/-/sharp-linux-riscv64-0.34.5.tgz",
"integrity": "sha512-51gJuLPTKa7piYPaVs8GmByo7/U7/7TZOq+cnXJIHZKavIRHAP77e3N2HEl3dgiqdD/w0yUfiJnII77PuDDFdw==",
"cpu": [
"riscv64"
],
"license": "Apache-2.0",
"optional": true,
"os": [
"linux"
],
"engines": {
"node": "^18.17.0 || ^20.3.0 || >=21.0.0"
},
"funding": {
"url": "https://opencollective.com/libvips"
},
"optionalDependencies": {
"@img/sharp-libvips-linux-riscv64": "1.2.4"
}
},
"node_modules/@img/sharp-linux-s390x": {
"version": "0.34.5",
"resolved": "https://registry.npmmirror.com/@img/sharp-linux-s390x/-/sharp-linux-s390x-0.34.5.tgz",
"integrity": "sha512-nQtCk0PdKfho3eC5MrbQoigJ2gd1CgddUMkabUj+rBevs8tZ2cULOx46E7oyX+04WGfABgIwmMC0VqieTiR4jg==",
"cpu": [
"s390x"
],
"license": "Apache-2.0",
"optional": true,
"os": [
"linux"
],
"engines": {
"node": "^18.17.0 || ^20.3.0 || >=21.0.0"
},
"funding": {
"url": "https://opencollective.com/libvips"
},
"optionalDependencies": {
"@img/sharp-libvips-linux-s390x": "1.2.4"
}
},
"node_modules/@img/sharp-linux-x64": {
"version": "0.34.5",
"resolved": "https://registry.npmmirror.com/@img/sharp-linux-x64/-/sharp-linux-x64-0.34.5.tgz",
"integrity": "sha512-MEzd8HPKxVxVenwAa+JRPwEC7QFjoPWuS5NZnBt6B3pu7EG2Ge0id1oLHZpPJdn3OQK+BQDiw9zStiHBTJQQQQ==",
"cpu": [
"x64"
],
"license": "Apache-2.0",
"optional": true,
"os": [
"linux"
],
"engines": {
"node": "^18.17.0 || ^20.3.0 || >=21.0.0"
},
"funding": {
"url": "https://opencollective.com/libvips"
},
"optionalDependencies": {
"@img/sharp-libvips-linux-x64": "1.2.4"
}
},
"node_modules/@img/sharp-linuxmusl-arm64": {
"version": "0.34.5",
"resolved": "https://registry.npmmirror.com/@img/sharp-linuxmusl-arm64/-/sharp-linuxmusl-arm64-0.34.5.tgz",
"integrity": "sha512-fprJR6GtRsMt6Kyfq44IsChVZeGN97gTD331weR1ex1c1rypDEABN6Tm2xa1wE6lYb5DdEnk03NZPqA7Id21yg==",
"cpu": [
"arm64"
],
"license": "Apache-2.0",
"optional": true,
"os": [
"linux"
],
"engines": {
"node": "^18.17.0 || ^20.3.0 || >=21.0.0"
},
"funding": {
"url": "https://opencollective.com/libvips"
},
"optionalDependencies": {
"@img/sharp-libvips-linuxmusl-arm64": "1.2.4"
}
},
"node_modules/@img/sharp-linuxmusl-x64": {
"version": "0.34.5",
"resolved": "https://registry.npmmirror.com/@img/sharp-linuxmusl-x64/-/sharp-linuxmusl-x64-0.34.5.tgz",
"integrity": "sha512-Jg8wNT1MUzIvhBFxViqrEhWDGzqymo3sV7z7ZsaWbZNDLXRJZoRGrjulp60YYtV4wfY8VIKcWidjojlLcWrd8Q==",
"cpu": [
"x64"
],
"license": "Apache-2.0",
"optional": true,
"os": [
"linux"
],
"engines": {
"node": "^18.17.0 || ^20.3.0 || >=21.0.0"
},
"funding": {
"url": "https://opencollective.com/libvips"
},
"optionalDependencies": {
"@img/sharp-libvips-linuxmusl-x64": "1.2.4"
}
},
"node_modules/@img/sharp-wasm32": {
"version": "0.34.5",
"resolved": "https://registry.npmmirror.com/@img/sharp-wasm32/-/sharp-wasm32-0.34.5.tgz",
"integrity": "sha512-OdWTEiVkY2PHwqkbBI8frFxQQFekHaSSkUIJkwzclWZe64O1X4UlUjqqqLaPbUpMOQk6FBu/HtlGXNblIs0huw==",
"cpu": [
"wasm32"
],
"license": "Apache-2.0 AND LGPL-3.0-or-later AND MIT",
"optional": true,
"dependencies": {
"@emnapi/runtime": "^1.7.0"
},
"engines": {
"node": "^18.17.0 || ^20.3.0 || >=21.0.0"
},
"funding": {
"url": "https://opencollective.com/libvips"
}
},
"node_modules/@img/sharp-win32-arm64": {
"version": "0.34.5",
"resolved": "https://registry.npmmirror.com/@img/sharp-win32-arm64/-/sharp-win32-arm64-0.34.5.tgz",
"integrity": "sha512-WQ3AgWCWYSb2yt+IG8mnC6Jdk9Whs7O0gxphblsLvdhSpSTtmu69ZG1Gkb6NuvxsNACwiPV6cNSZNzt0KPsw7g==",
"cpu": [
"arm64"
],
"license": "Apache-2.0 AND LGPL-3.0-or-later",
"optional": true,
"os": [
"win32"
],
"engines": {
"node": "^18.17.0 || ^20.3.0 || >=21.0.0"
},
"funding": {
"url": "https://opencollective.com/libvips"
}
},
"node_modules/@img/sharp-win32-ia32": {
"version": "0.34.5",
"resolved": "https://registry.npmmirror.com/@img/sharp-win32-ia32/-/sharp-win32-ia32-0.34.5.tgz",
"integrity": "sha512-FV9m/7NmeCmSHDD5j4+4pNI8Cp3aW+JvLoXcTUo0IqyjSfAZJ8dIUmijx1qaJsIiU+Hosw6xM5KijAWRJCSgNg==",
"cpu": [
"ia32"
],
"license": "Apache-2.0 AND LGPL-3.0-or-later",
"optional": true,
"os": [
"win32"
],
"engines": {
"node": "^18.17.0 || ^20.3.0 || >=21.0.0"
},
"funding": {
"url": "https://opencollective.com/libvips"
}
},
"node_modules/@img/sharp-win32-x64": {
"version": "0.34.5",
"resolved": "https://registry.npmmirror.com/@img/sharp-win32-x64/-/sharp-win32-x64-0.34.5.tgz",
"integrity": "sha512-+29YMsqY2/9eFEiW93eqWnuLcWcufowXewwSNIT6UwZdUUCrM3oFjMWH/Z6/TMmb4hlFenmfAVbpWeup2jryCw==",
"cpu": [
"x64"
],
"license": "Apache-2.0 AND LGPL-3.0-or-later",
"optional": true,
"os": [
"win32"
],
"engines": {
"node": "^18.17.0 || ^20.3.0 || >=21.0.0"
},
"funding": {
"url": "https://opencollective.com/libvips"
}
},
"node_modules/@isaacs/fs-minipass": {
"version": "4.0.1",
"resolved": "https://registry.npmjs.org/@isaacs/fs-minipass/-/fs-minipass-4.0.1.tgz",
@ -2258,6 +2771,12 @@
"node": ">=10"
}
},
"node_modules/@techstark/opencv-js": {
"version": "4.9.0-release.3",
"resolved": "https://registry.npmmirror.com/@techstark/opencv-js/-/opencv-js-4.9.0-release.3.tgz",
"integrity": "sha512-y+KoLLlkXVUHWozYlN1vmMD9TQMPJObqml5nPA5vPWgHtOgm8q5O74UtzM23eayidvmeFX6tF5e2gDdyxcpy3Q==",
"license": "Apache-2.0"
},
"node_modules/@types/adm-zip": {
"version": "0.5.8",
"resolved": "https://registry.npmmirror.com/@types/adm-zip/-/adm-zip-0.5.8.tgz",
@ -4203,6 +4722,15 @@
"node": ">=0.4.0"
}
},
"node_modules/detect-libc": {
"version": "2.1.2",
"resolved": "https://registry.npmmirror.com/detect-libc/-/detect-libc-2.1.2.tgz",
"integrity": "sha512-Btj2BOOO83o3WyH59e8MgXsxEQVcarkUOpEYrubB0urwnN10yQ364rsiByU11nZlqWYZm05i/of7io4mzihBtQ==",
"license": "Apache-2.0",
"engines": {
"node": ">=8"
}
},
"node_modules/detect-node": {
"version": "2.1.0",
"resolved": "https://registry.npmmirror.com/detect-node/-/detect-node-2.1.0.tgz",
@ -4889,9 +5417,7 @@
"version": "4.0.0",
"resolved": "https://registry.npmmirror.com/escape-string-regexp/-/escape-string-regexp-4.0.0.tgz",
"integrity": "sha512-TtpcNJ3XAzx3Gq8sWRzJaVajRs0uVxA2YAkdb1jm2YkPz4G6egUFAyA3n5vtEIZefPk5Wa4UXbKuS5fKkJWdgA==",
"dev": true,
"license": "MIT",
"optional": true,
"engines": {
"node": ">=10"
},
@ -6002,6 +6528,12 @@
"jiti": "lib/jiti-cli.mjs"
}
},
"node_modules/js-clipper": {
"version": "1.0.1",
"resolved": "https://registry.npmmirror.com/js-clipper/-/js-clipper-1.0.1.tgz",
"integrity": "sha512-0XYAS0ZoCki5K0fWwj8j8ug4mgxHXReW3ayPbVqr4zXPJuIs2pyvemL1sALadsEiAywZwW5Ify1XfU4bNJvokg==",
"license": "boost"
},
"node_modules/js-tokens": {
"version": "4.0.0",
"resolved": "https://registry.npmmirror.com/js-tokens/-/js-tokens-4.0.0.tgz",
@ -6723,6 +7255,95 @@
"wrappy": "1"
}
},
"node_modules/onnxruntime-common": {
"version": "1.31.1",
"resolved": "https://registry.npmmirror.com/onnxruntime-common/-/onnxruntime-common-1.31.1.tgz",
"integrity": "sha512-F+nnYNiQtmNJ95V6R/isBJqiVpdANCrsMEg1OaF+Bkbl3GAtzWLR7Ng17Ld0QtYtYJyotOHPJzOQn1Y6PLZjpg==",
"license": "MIT"
},
"node_modules/onnxruntime-node": {
"version": "1.31.1",
"resolved": "https://registry.npmmirror.com/onnxruntime-node/-/onnxruntime-node-1.31.1.tgz",
"integrity": "sha512-ijnSghbDHVWaQ2nDPmVccPlCHI8kH1Mx1aJ4a/qzRP16bBcVs4E3EqZQKZCkhWnbqN1tuQWxagimFtDpbPYYQw==",
"hasInstallScript": true,
"license": "MIT",
"os": [
"win32",
"darwin",
"linux"
],
"dependencies": {
"adm-zip": "^0.6.0",
"global-agent": "^4.1.3",
"onnxruntime-common": "1.31.1"
}
},
"node_modules/onnxruntime-node/node_modules/adm-zip": {
"version": "0.6.1",
"resolved": "https://registry.npmmirror.com/adm-zip/-/adm-zip-0.6.1.tgz",
"integrity": "sha512-Xwrja8nx9e5o2N1my4DsKCeKpdrnACyr1wtbPxBDgGzKzKyE9kRtBFA8mWldI+RVlD7CBZNWY/wQ2+ydwOR6kQ==",
"license": "MIT",
"engines": {
"node": ">=14.0"
}
},
"node_modules/onnxruntime-node/node_modules/global-agent": {
"version": "4.1.6",
"resolved": "https://registry.npmmirror.com/global-agent/-/global-agent-4.1.6.tgz",
"integrity": "sha512-V9u791atI/bS7RryfRTK2oixDWo6/RCrIikjwuQ4kADPRZZml1C6LUJXc7y6qRhaAF8geo3bIvE/siAGJCw38A==",
"license": "BSD-3-Clause",
"dependencies": {
"globalthis": "^1.0.2",
"matcher": "^4.0.0",
"semver": "^7.3.5",
"serialize-error": "^8.1.0"
},
"engines": {
"node": ">=10.0"
}
},
"node_modules/onnxruntime-node/node_modules/matcher": {
"version": "4.0.0",
"resolved": "https://registry.npmmirror.com/matcher/-/matcher-4.0.0.tgz",
"integrity": "sha512-S6x5wmcDmsDRRU/c2dkccDwQPXoFczc5+HpQ2lON8pnvHlnvHAHj5WlLVvw6n6vNyHuVugYrFohYxbS+pvFpKQ==",
"license": "MIT",
"dependencies": {
"escape-string-regexp": "^4.0.0"
},
"engines": {
"node": ">=10"
},
"funding": {
"url": "https://github.com/sponsors/sindresorhus"
}
},
"node_modules/onnxruntime-node/node_modules/serialize-error": {
"version": "8.1.0",
"resolved": "https://registry.npmmirror.com/serialize-error/-/serialize-error-8.1.0.tgz",
"integrity": "sha512-3NnuWfM6vBYoy5gZFvHiYsVbafvI9vZv/+jlIigFn4oP4zjNPK3LhcY0xSCgeb1a5L8jO71Mit9LlNoi2UfDDQ==",
"license": "MIT",
"dependencies": {
"type-fest": "^0.20.2"
},
"engines": {
"node": ">=10"
},
"funding": {
"url": "https://github.com/sponsors/sindresorhus"
}
},
"node_modules/onnxruntime-node/node_modules/type-fest": {
"version": "0.20.2",
"resolved": "https://registry.npmmirror.com/type-fest/-/type-fest-0.20.2.tgz",
"integrity": "sha512-Ne+eE4r0/iWnpAxD852z3A+N0Bt5RN//NjJwRd2VFHEmrywxf5vsZlh4R6lixl6B+wz/8d+maTSAkN1FIkI3LQ==",
"license": "(MIT OR CC0-1.0)",
"engines": {
"node": ">=10"
},
"funding": {
"url": "https://github.com/sponsors/sindresorhus"
}
},
"node_modules/opencollective-postinstall": {
"version": "2.0.3",
"resolved": "https://registry.npmmirror.com/opencollective-postinstall/-/opencollective-postinstall-2.0.3.tgz",
@ -7531,7 +8152,6 @@
"version": "7.8.5",
"resolved": "https://registry.npmmirror.com/semver/-/semver-7.8.5.tgz",
"integrity": "sha512-Y7/KDsb8LjooZpwaqGyulO6DQlksgCncchHGk+sZIY4SBvUocMBEFH5Ur1fI4dV+Jvl0w6cjvucaIi40puRioA==",
"dev": true,
"license": "ISC",
"bin": {
"semver": "bin/semver.js"
@ -7617,6 +8237,50 @@
"integrity": "sha512-MATJdZp8sLqDl/68LfQmbP8zKPLQNV6BIZoIgrscFDQ+RsvK/BxeDQOgyxKKoh0y/8h3BqVFnCqQ/gd+reiIXA==",
"license": "MIT"
},
"node_modules/sharp": {
"version": "0.34.5",
"resolved": "https://registry.npmmirror.com/sharp/-/sharp-0.34.5.tgz",
"integrity": "sha512-Ou9I5Ft9WNcCbXrU9cMgPBcCK8LiwLqcbywW3t4oDV37n1pzpuNLsYiAV8eODnjbtQlSDwZ2cUEeQz4E54Hltg==",
"hasInstallScript": true,
"license": "Apache-2.0",
"dependencies": {
"@img/colour": "^1.0.0",
"detect-libc": "^2.1.2",
"semver": "^7.7.3"
},
"engines": {
"node": "^18.17.0 || ^20.3.0 || >=21.0.0"
},
"funding": {
"url": "https://opencollective.com/libvips"
},
"optionalDependencies": {
"@img/sharp-darwin-arm64": "0.34.5",
"@img/sharp-darwin-x64": "0.34.5",
"@img/sharp-libvips-darwin-arm64": "1.2.4",
"@img/sharp-libvips-darwin-x64": "1.2.4",
"@img/sharp-libvips-linux-arm": "1.2.4",
"@img/sharp-libvips-linux-arm64": "1.2.4",
"@img/sharp-libvips-linux-ppc64": "1.2.4",
"@img/sharp-libvips-linux-riscv64": "1.2.4",
"@img/sharp-libvips-linux-s390x": "1.2.4",
"@img/sharp-libvips-linux-x64": "1.2.4",
"@img/sharp-libvips-linuxmusl-arm64": "1.2.4",
"@img/sharp-libvips-linuxmusl-x64": "1.2.4",
"@img/sharp-linux-arm": "0.34.5",
"@img/sharp-linux-arm64": "0.34.5",
"@img/sharp-linux-ppc64": "0.34.5",
"@img/sharp-linux-riscv64": "0.34.5",
"@img/sharp-linux-s390x": "0.34.5",
"@img/sharp-linux-x64": "0.34.5",
"@img/sharp-linuxmusl-arm64": "0.34.5",
"@img/sharp-linuxmusl-x64": "0.34.5",
"@img/sharp-wasm32": "0.34.5",
"@img/sharp-win32-arm64": "0.34.5",
"@img/sharp-win32-ia32": "0.34.5",
"@img/sharp-win32-x64": "0.34.5"
}
},
"node_modules/shebang-command": {
"version": "2.0.0",
"resolved": "https://registry.npmmirror.com/shebang-command/-/shebang-command-2.0.0.tgz",
@ -8078,6 +8742,12 @@
"semver": "bin/semver"
}
},
"node_modules/tiny-invariant": {
"version": "1.3.3",
"resolved": "https://registry.npmmirror.com/tiny-invariant/-/tiny-invariant-1.3.3.tgz",
"integrity": "sha512-+FbBPE1o9QAYvviau/qC5SE3caw21q3xkvWKBtja5vgqOWIHHJ3ioaq1VPfn/Szqctz2bU/oYeKd9/z5BL+PVg==",
"license": "MIT"
},
"node_modules/tinybench": {
"version": "2.9.0",
"resolved": "https://registry.npmmirror.com/tinybench/-/tinybench-2.9.0.tgz",

View File

@ -17,6 +17,8 @@
"test:e2e": "node scripts/demo-e2e.mjs"
},
"dependencies": {
"@gutenye/ocr-models": "^1.4.2",
"@gutenye/ocr-node": "^1.4.9",
"@xyflow/react": "^12.12.0",
"adm-zip": "^0.5.16",
"basic-ftp": "^6.2.3",

View File

@ -1,9 +1,18 @@
import Tesseract from "tesseract.js";
import fs from "node:fs";
import { register } from "../engine/registry";
import { RuntimeError } from "../engine/types";
interface OcrWord { text: string; x: number; y: number; width: number; height: number; confidence: number }
interface RapidOcrLine { text: string; mean: number; box?: number[][] }
let ocrInstance: unknown = null;
async function getOcr(): Promise<{ detect: (image: string) => Promise<{ texts: RapidOcrLine[] }> }> {
if (ocrInstance) return ocrInstance as { detect: (image: string) => Promise<{ texts: RapidOcrLine[] }> };
const mod = await import("@gutenye/ocr-node");
const instance = await mod.default.create();
ocrInstance = instance;
return instance;
}
function requireImage(args: Record<string, unknown>, nodeId: string): string {
for (const key of ["image_path", "imagePath", "file_path", "filePath", "path", "image", "pictureSource"]) {
@ -13,60 +22,48 @@ function requireImage(args: Record<string, unknown>, nodeId: string): string {
throw new RuntimeError("validation_error", "图片路径为空", { nodeId, componentId: nodeId, recommendation: "填写本地图片路径(png/jpg/bmp)" });
}
async function recognizeWithLayout(imagePath: string, nodeId: string): Promise<{ text: string; words: OcrWord[]; textLines: string[] }> {
if (!fs.existsSync(imagePath)) {
throw new RuntimeError("file_not_found", "图片不存在:" + imagePath, { nodeId, componentId: nodeId });
}
const worker = await Tesseract.createWorker("chi_sim+eng");
try {
const result = await worker.recognize(imagePath, {}, { text: true, blocks: true });
const data = result.data as {
text?: string;
blocks?: Array<{
paragraphs?: Array<{
lines?: Array<{
words?: Array<{ text: string; confidence: number; bbox: { x0: number; y0: number; x1: number; y1: number } }>;
}>;
}>;
}>;
};
const words: OcrWord[] = [];
const textLines: string[] = [];
for (const block of data.blocks ?? []) {
for (const para of block.paragraphs ?? []) {
for (const line of para.lines ?? []) {
const lineWords = line.words ?? [];
textLines.push(lineWords.map(w => w.text).join(" "));
for (const w of lineWords) {
words.push({ text: w.text, x: w.bbox.x0, y: w.bbox.y0, width: w.bbox.x1 - w.bbox.x0, height: w.bbox.y1 - w.bbox.y0, confidence: w.confidence });
}
}
}
}
return { text: (data.text ?? "").trim(), words, textLines };
} finally {
await worker.terminate();
}
function boxToRect(box: number[][] | undefined): { x: number; y: number; width: number; height: number } {
const points = box ?? [];
const xs = points.map(p => p[0]);
const ys = points.map(p => p[1]);
const minX = Math.min(...(xs.length ? xs : [0]));
const minY = Math.min(...(ys.length ? ys : [0]));
const maxX = Math.max(...(xs.length ? xs : [0]));
const maxY = Math.max(...(ys.length ? ys : [0]));
return { x: minX, y: minY, width: maxX - minX, height: maxY - minY };
}
register("OcrOffline_GetOcrTextNew", async (ctx, node, args) => {
const imagePath = requireImage(args, node.id);
const result = await recognizeWithLayout(imagePath, node.id);
ctx.log("OCR 识别完成:" + result.text.length + " 字符 / " + result.words.length + " 词", "info", node.id);
return result.text;
const ocr = await getOcr();
const result = await ocr.detect(imagePath);
const text = result.texts.map(t => t.text).join("\n");
ctx.log("OCR 识别完成:" + text.length + " 字符 / " + result.texts.length + " 行", "info", node.id);
return text;
});
register("OcrOffline_GetOcrTextPosition", async (ctx, node, args) => {
const imagePath = requireImage(args, node.id);
const result = await recognizeWithLayout(imagePath, node.id);
ctx.log("OCR 定位完成:" + result.words.length + " 个词", "info", node.id);
return result.words;
const ocr = await getOcr();
const result = await ocr.detect(imagePath);
const words = result.texts.map(t => {
const rect = boxToRect(t.box);
return { text: t.text, x: rect.x, y: rect.y, width: rect.width, height: rect.height, confidence: t.mean };
});
ctx.log("OCR 定位完成:" + words.length + " 行", "info", node.id);
return words;
});
register("OcrOffline_GetOcrTable", async (ctx, node, args) => {
const imagePath = requireImage(args, node.id);
const result = await recognizeWithLayout(imagePath, node.id);
const rows = result.textLines.map(line => line.split(/ {2,}/).filter(Boolean).join("\t"));
const ocr = await getOcr();
const result = await ocr.detect(imagePath);
const sorted = [...result.texts].sort((a, b) => {
const ay = a.box ? Math.min(...a.box.map(p => p[1])) : 0;
const by = b.box ? Math.min(...b.box.map(p => p[1])) : 0;
return ay - by;
});
const rows = sorted.map(t => t.text);
ctx.log("OCR 表格识别完成:" + rows.length + " 行", "info", node.id);
return rows;
});