egg/OCR
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: implement layout-preserving PDF generation with table reconstruction

Browse Source 
Major Features:
- Add PDF generation service with Chinese font support
- Parse HTML tables from PP-StructureV3 and rebuild with ReportLab
- Extract table text for translation purposes
- Auto-filter text regions inside tables to avoid overlaps

Backend Changes:
1. pdf_generator_service.py (NEW)
   - HTMLTableParser: Parse HTML tables to extract structure
   - PDFGeneratorService: Generate layout-preserving PDFs
   - Coordinate transformation: OCR (top-left) → PDF (bottom-left)
   - Font size heuristics: 75% of bbox height with width checking
   - Table reconstruction: Parse HTML → ReportLab Table
   - Image embedding: Extract bbox from filenames

2. ocr_service.py
   - Add _extract_table_text() for translation support
   - Add output_dir parameter to save images to result directory
   - Extract bbox from image filenames (img_in_table_box_x1_y1_x2_y2.jpg)

3. tasks.py
   - Update process_task_ocr to use save_results() with PDF generation
   - Fix download_pdf endpoint to use database-stored PDF paths
   - Support on-demand PDF generation from JSON

4. config.py
   - Add chinese_font_path configuration
   - Add pdf_enable_bbox_debug flag

Frontend Changes:
1. PDFViewer.tsx (NEW)
   - React PDF viewer with zoom and pagination
   - Memoized file config to prevent unnecessary reloads

2. TaskDetailPage.tsx & ResultsPage.tsx
   - Integrate PDF preview and download

3. main.tsx
   - Configure PDF.js worker via CDN

4. vite.config.ts
   - Add host: '0.0.0.0' for network access
   - Use VITE_API_URL environment variable for backend proxy

Dependencies:
- reportlab: PDF generation library
- Noto Sans SC font: Chinese character support

🤖 Generated with Claude Code
https://claude.com/claude-code

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
egg
2025-11-17 20:21:56 +08:00
parent 012da1abc4
commit fa1abcd8e6
16 changed files with 1427 additions and 57 deletions
Download Patch File Download Diff File Expand all files Collapse all files

277
frontend/package-lock.json generated
View File

@@ -19,6 +19,7 @@
"react-dropzone": "^14.3.8",
"react-i18next": "^16.3.0",
"react-markdown": "^9.0.1",
"react-pdf": "^10.2.0",
"react-router-dom": "^7.9.5",
"tailwind-merge": "^3.4.0",
"zustand": "^5.0.8"
@@ -1048,6 +1049,191 @@
"@jridgewell/sourcemap-codec": "^1.4.14"
}
},
"node_modules/@napi-rs/canvas": {
"version": "0.1.82",
"resolved": "https://registry.npmjs.org/@napi-rs/canvas/-/canvas-0.1.82.tgz",
"integrity": "sha512-FGjyUBoF0sl1EenSiE4UV2WYu76q6F9GSYedq5EiOCOyGYoQ/Owulcv6rd7v/tWOpljDDtefXXIaOCJrVKem4w==",
"license": "MIT",
"optional": true,
"workspaces": [
"e2e/*"
],
"engines": {
"node": ">= 10"
},
"optionalDependencies": {
"@napi-rs/canvas-android-arm64": "0.1.82",
"@napi-rs/canvas-darwin-arm64": "0.1.82",
"@napi-rs/canvas-darwin-x64": "0.1.82",
"@napi-rs/canvas-linux-arm-gnueabihf": "0.1.82",
"@napi-rs/canvas-linux-arm64-gnu": "0.1.82",
"@napi-rs/canvas-linux-arm64-musl": "0.1.82",
"@napi-rs/canvas-linux-riscv64-gnu": "0.1.82",
"@napi-rs/canvas-linux-x64-gnu": "0.1.82",
"@napi-rs/canvas-linux-x64-musl": "0.1.82",
"@napi-rs/canvas-win32-x64-msvc": "0.1.82"
}
},
"node_modules/@napi-rs/canvas-android-arm64": {
"version": "0.1.82",
"resolved": "https://registry.npmjs.org/@napi-rs/canvas-android-arm64/-/canvas-android-arm64-0.1.82.tgz",
"integrity": "sha512-bvZhN0iI54ouaQOrgJV96H2q7J3ZoufnHf4E1fUaERwW29Rz4rgicohnAg4venwBJZYjGl5Yl3CGmlAl1LZowQ==",
"cpu": [
"arm64"
],
"license": "MIT",
"optional": true,
"os": [
"android"
],
"engines": {
"node": ">= 10"
}
},
"node_modules/@napi-rs/canvas-darwin-arm64": {
"version": "0.1.82",
"resolved": "https://registry.npmjs.org/@napi-rs/canvas-darwin-arm64/-/canvas-darwin-arm64-0.1.82.tgz",
"integrity": "sha512-InuBHKCyuFqhNwNr4gpqazo5Xp6ltKflqOLiROn4hqAS8u21xAHyYCJRgHwd+a5NKmutFTaRWeUIT/vxWbU/iw==",
"cpu": [
"arm64"
],
"license": "MIT",
"optional": true,
"os": [
"darwin"
],
"engines": {
"node": ">= 10"
}
},
"node_modules/@napi-rs/canvas-darwin-x64": {
"version": "0.1.82",
"resolved": "https://registry.npmjs.org/@napi-rs/canvas-darwin-x64/-/canvas-darwin-x64-0.1.82.tgz",
"integrity": "sha512-aQGV5Ynn96onSXcuvYb2y7TRXD/t4CL2EGmnGqvLyeJX1JLSNisKQlWN/1bPDDXymZYSdUqbXehj5qzBlOx+RQ==",
"cpu": [
"x64"
],
"license": "MIT",
"optional": true,
"os": [
"darwin"
],
"engines": {
"node": ">= 10"
}
},
"node_modules/@napi-rs/canvas-linux-arm-gnueabihf": {
"version": "0.1.82",
"resolved": "https://registry.npmjs.org/@napi-rs/canvas-linux-arm-gnueabihf/-/canvas-linux-arm-gnueabihf-0.1.82.tgz",
"integrity": "sha512-YIUpmHWeHGGRhWitT1KJkgj/JPXPfc9ox8oUoyaGPxolLGPp5AxJkq8wIg8CdFGtutget968dtwmx71m8o3h5g==",
"cpu": [
"arm"
],
"license": "MIT",
"optional": true,
"os": [
"linux"
],
"engines": {
"node": ">= 10"
}
},
"node_modules/@napi-rs/canvas-linux-arm64-gnu": {
"version": "0.1.82",
"resolved": "https://registry.npmjs.org/@napi-rs/canvas-linux-arm64-gnu/-/canvas-linux-arm64-gnu-0.1.82.tgz",
"integrity": "sha512-AwLzwLBgmvk7kWeUgItOUor/QyG31xqtD26w1tLpf4yE0hiXTGp23yc669aawjB6FzgIkjh1NKaNS52B7/qEBQ==",
"cpu": [
"arm64"
],
"license": "MIT",
"optional": true,
"os": [
"linux"
],
"engines": {
"node": ">= 10"
}
},
"node_modules/@napi-rs/canvas-linux-arm64-musl": {
"version": "0.1.82",
"resolved": "https://registry.npmjs.org/@napi-rs/canvas-linux-arm64-musl/-/canvas-linux-arm64-musl-0.1.82.tgz",
"integrity": "sha512-moZWuqepAwWBffdF4JDadt8TgBD02iMhG6I1FHZf8xO20AsIp9rB+p0B8Zma2h2vAF/YMjeFCDmW5un6+zZz9g==",
"cpu": [
"arm64"
],
"license": "MIT",
"optional": true,
"os": [
"linux"
],
"engines": {
"node": ">= 10"
}
},
"node_modules/@napi-rs/canvas-linux-riscv64-gnu": {
"version": "0.1.82",
"resolved": "https://registry.npmjs.org/@napi-rs/canvas-linux-riscv64-gnu/-/canvas-linux-riscv64-gnu-0.1.82.tgz",
"integrity": "sha512-w9++2df2kG9eC9LWYIHIlMLuhIrKGQYfUxs97CwgxYjITeFakIRazI9LYWgVzEc98QZ9x9GQvlicFsrROV59MQ==",
"cpu": [
"riscv64"
],
"license": "MIT",
"optional": true,
"os": [
"linux"
],
"engines": {
"node": ">= 10"
}
},
"node_modules/@napi-rs/canvas-linux-x64-gnu": {
"version": "0.1.82",
"resolved": "https://registry.npmjs.org/@napi-rs/canvas-linux-x64-gnu/-/canvas-linux-x64-gnu-0.1.82.tgz",
"integrity": "sha512-lZulOPwrRi6hEg/17CaqdwWEUfOlIJuhXxincx1aVzsVOCmyHf+xFq4i6liJl1P+x2v6Iz2Z/H5zHvXJCC7Bwg==",
"cpu": [
"x64"
],
"license": "MIT",
"optional": true,
"os": [
"linux"
],
"engines": {
"node": ">= 10"
}
},
"node_modules/@napi-rs/canvas-linux-x64-musl": {
"version": "0.1.82",
"resolved": "https://registry.npmjs.org/@napi-rs/canvas-linux-x64-musl/-/canvas-linux-x64-musl-0.1.82.tgz",
"integrity": "sha512-Be9Wf5RTv1w6GXlTph55K3PH3vsAh1Ax4T1FQY1UYM0QfD0yrwGdnJ8/fhqw7dEgMjd59zIbjJQC8C3msbGn5g==",
"cpu": [
"x64"
],
"license": "MIT",
"optional": true,
"os": [
"linux"
],
"engines": {
"node": ">= 10"
}
},
"node_modules/@napi-rs/canvas-win32-x64-msvc": {
"version": "0.1.82",
"resolved": "https://registry.npmjs.org/@napi-rs/canvas-win32-x64-msvc/-/canvas-win32-x64-msvc-0.1.82.tgz",
"integrity": "sha512-LN/i8VrvxTDmEEK1c10z2cdOTkWT76LlTGtyZe5Kr1sqoSomKeExAjbilnu1+oee5lZUgS5yfZ2LNlVhCeARuw==",
"cpu": [
"x64"
],
"license": "MIT",
"optional": true,
"os": [
"win32"
],
"engines": {
"node": ">= 10"
}
},
"node_modules/@nodelib/fs.scandir": {
"version": "2.1.5",
"resolved": "https://registry.npmjs.org/@nodelib/fs.scandir/-/fs.scandir-2.1.5.tgz",
@@ -4007,6 +4193,24 @@
"@jridgewell/sourcemap-codec": "^1.5.5"
}
},
"node_modules/make-cancellable-promise": {
"version": "2.0.0",
"resolved": "https://registry.npmjs.org/make-cancellable-promise/-/make-cancellable-promise-2.0.0.tgz",
"integrity": "sha512-3SEQqTpV9oqVsIWqAcmDuaNeo7yBO3tqPtqGRcKkEo0lrzD3wqbKG9mkxO65KoOgXqj+zH2phJ2LiAsdzlogSw==",
"license": "MIT",
"funding": {
"url": "https://github.com/wojtekmaj/make-cancellable-promise?sponsor=1"
}
},
"node_modules/make-event-props": {
"version": "2.0.0",
"resolved": "https://registry.npmjs.org/make-event-props/-/make-event-props-2.0.0.tgz",
"integrity": "sha512-G/hncXrl4Qt7mauJEXSg3AcdYzmpkIITTNl5I+rH9sog5Yw0kK6vseJjCaPfOXqOqQuPUP89Rkhfz5kPS8ijtw==",
"license": "MIT",
"funding": {
"url": "https://github.com/wojtekmaj/make-event-props?sponsor=1"
}
},
"node_modules/math-intrinsics": {
"version": "1.1.0",
"resolved": "https://registry.npmjs.org/math-intrinsics/-/math-intrinsics-1.1.0.tgz",
@@ -4169,6 +4373,23 @@
"url": "https://opencollective.com/unified"
}
},
"node_modules/merge-refs": {
"version": "2.0.0",
"resolved": "https://registry.npmjs.org/merge-refs/-/merge-refs-2.0.0.tgz",
"integrity": "sha512-3+B21mYK2IqUWnd2EivABLT7ueDhb0b8/dGK8LoFQPrU61YITeCMn14F7y7qZafWNZhUEKb24cJdiT5Wxs3prg==",
"license": "MIT",
"funding": {
"url": "https://github.com/wojtekmaj/merge-refs?sponsor=1"
},
"peerDependencies": {
"@types/react": "^16.8.0 || ^17.0.0 || ^18.0.0 || ^19.0.0"
},
"peerDependenciesMeta": {
"@types/react": {
"optional": true
}
}
},
"node_modules/merge2": {
"version": "1.4.1",
"resolved": "https://registry.npmjs.org/merge2/-/merge2-1.4.1.tgz",
@@ -5060,6 +5281,47 @@
"react": ">=18"
}
},
"node_modules/react-pdf": {
"version": "10.2.0",
"resolved": "https://registry.npmjs.org/react-pdf/-/react-pdf-10.2.0.tgz",
"integrity": "sha512-zk0DIL31oCh8cuQycM0SJKfwh4Onz0/Nwi6wTOjgtEjWGUY6eM+/vuzvOP3j70qtEULn7m1JtaeGzud1w5fY2Q==",
"license": "MIT",
"dependencies": {
"clsx": "^2.0.0",
"dequal": "^2.0.3",
"make-cancellable-promise": "^2.0.0",
"make-event-props": "^2.0.0",
"merge-refs": "^2.0.0",
"pdfjs-dist": "5.4.296",
"tiny-invariant": "^1.0.0",
"warning": "^4.0.0"
},
"funding": {
"url": "https://github.com/wojtekmaj/react-pdf?sponsor=1"
},
"peerDependencies": {
"@types/react": "^16.8.0 || ^17.0.0 || ^18.0.0 || ^19.0.0",
"react": "^16.8.0 || ^17.0.0 || ^18.0.0 || ^19.0.0",
"react-dom": "^16.8.0 || ^17.0.0 || ^18.0.0 || ^19.0.0"
},
"peerDependenciesMeta": {
"@types/react": {
"optional": true
}
}
},
"node_modules/react-pdf/node_modules/pdfjs-dist": {
"version": "5.4.296",
"resolved": "https://registry.npmjs.org/pdfjs-dist/-/pdfjs-dist-5.4.296.tgz",
"integrity": "sha512-DlOzet0HO7OEnmUmB6wWGJrrdvbyJKftI1bhMitK7O2N8W2gc757yyYBbINy9IDafXAV9wmKr9t7xsTaNKRG5Q==",
"license": "Apache-2.0",
"engines": {
"node": ">=20.16.0 || >=22.3.0"
},
"optionalDependencies": {
"@napi-rs/canvas": "^0.1.80"
}
},
"node_modules/react-refresh": {
"version": "0.18.0",
"resolved": "https://registry.npmjs.org/react-refresh/-/react-refresh-0.18.0.tgz",
@@ -5382,6 +5644,12 @@
"url": "https://opencollective.com/webpack"
}
},
"node_modules/tiny-invariant": {
"version": "1.3.3",
"resolved": "https://registry.npmjs.org/tiny-invariant/-/tiny-invariant-1.3.3.tgz",
"integrity": "sha512-+FbBPE1o9QAYvviau/qC5SE3caw21q3xkvWKBtja5vgqOWIHHJ3ioaq1VPfn/Szqctz2bU/oYeKd9/z5BL+PVg==",
"license": "MIT"
},
"node_modules/tinyglobby": {
"version": "0.2.15",
"resolved": "https://registry.npmjs.org/tinyglobby/-/tinyglobby-0.2.15.tgz",
@@ -5824,6 +6092,15 @@
"node": ">=0.10.0"
}
},
"node_modules/warning": {
"version": "4.0.3",
"resolved": "https://registry.npmjs.org/warning/-/warning-4.0.3.tgz",
"integrity": "sha512-rpJyN222KWIvHJ/F53XSZv0Zl/accqHR8et1kpaMTD/fLCRxtV8iX8czMzY7sVZupTI3zcUTg8eycS2kNF9l6w==",
"license": "MIT",
"dependencies": {
"loose-envify": "^1.0.0"
}
},
"node_modules/which": {
"version": "2.0.2",
"resolved": "https://registry.npmjs.org/which/-/which-2.0.2.tgz",