Add qualityt check and contributing doc

.editorconfig

@@ -0,0 +1,18 @@
+root = true
+
+[*]
+charset = utf-8
+end_of_line = lf
+indent_style = space
+indent_size = 2
+insert_final_newline = true
+trim_trailing_whitespace = true
+
+[*.py]
+indent_size = 4
+
+[*.md]
+trim_trailing_whitespace = false
+
+[Makefile]
+indent_style = tab

CHANGELOG.md

@@ -0,0 +1,23 @@
+# Changelog
+
+All notable changes to Docling Studio will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/), and this project adheres to [Semantic Versioning](https://semver.org/).
+
+## [0.1.0] - 2025-01-01
+
+### Added
+
+- Initial release of Docling Studio
+- PDF upload and document management
+- Configurable Docling pipeline (OCR, tables, code, formulas, images)
+- Bounding box visualization with color-coded overlays
+- Per-page results synchronized with PDF viewer
+- Markdown and HTML export
+- Analysis history with re-visit capability
+- Dark/Light theme support
+- French and English localization
+- Docker and Docker Compose deployment
+- CI/CD with GitHub Actions (tests + multi-arch Docker build)
+- Health check endpoint (`/health`)
+- SQLite-backed persistence

CONTRIBUTING.md

@@ -0,0 +1,97 @@
+# Contributing to Docling Studio
+
+Thank you for your interest in contributing to Docling Studio! This guide will help you get started.
+
+## Getting Started
+
+1. **Fork** the repository on GitHub
+2. **Clone** your fork locally:
+   ```bash
+   git clone https://github.com/<your-username>/Docling-Studio.git
+   cd Docling-Studio
+   ```
+3. **Create a branch** for your work:
+   ```bash
+   git checkout -b feature/my-feature
+   ```
+
+## Development Setup
+
+### Backend (Python 3.12+)
+
+```bash
+cd document-parser
+python -m venv .venv && source .venv/bin/activate
+pip install -r requirements.txt
+pip install ruff pytest pytest-asyncio httpx  # dev tools
+uvicorn main:app --reload --port 8000
+```
+
+### Frontend (Node 20+)
+
+```bash
+cd frontend
+npm install
+npm run dev
+```
+
+## Code Quality
+
+### Backend — Ruff
+
+We use [Ruff](https://docs.astral.sh/ruff/) for linting and formatting Python code.
+
+```bash
+cd document-parser
+ruff check .          # lint
+ruff check . --fix    # lint with auto-fix
+ruff format .         # format
+```
+
+### Frontend — ESLint + Prettier
+
+```bash
+cd frontend
+npx eslint src/       # lint
+npx prettier --check src/  # check formatting
+npx prettier --write src/  # auto-format
+```
+
+## Running Tests
+
+```bash
+# Backend (99 tests)
+cd document-parser
+pytest tests/ -v
+
+# Frontend (87 tests)
+cd frontend
+npm run test:run
+```
+
+All tests must pass before submitting a PR.
+
+## Submitting Changes
+
+1. **Commit** with clear, descriptive messages
+2. **Push** your branch to your fork
+3. Open a **Pull Request** against `main`
+4. Describe **what** changed and **why** in the PR description
+5. Ensure CI passes (tests + build)
+
+## Pull Request Guidelines
+
+- Keep PRs focused — one feature or fix per PR
+- Add tests for new functionality
+- Update documentation if behavior changes
+- Follow existing code style and conventions
+
+## Reporting Issues
+
+- Use GitHub Issues to report bugs or request features
+- Include steps to reproduce for bugs
+- Mention your OS, Python/Node version, and Docker version if relevant
+
+## License
+
+By contributing, you agree that your contributions will be licensed under the [MIT License](LICENSE).

document-parser/api/analyses.py

@@ -42,7 +42,7 @@ async def create_analysis(body: CreateAnalysisRequest):
     try:
         job = await analysis_service.create(body.documentId, pipeline_options=pipeline_opts)
     except ValueError as e:
-        raise HTTPException(status_code=404, detail=str(e))
+        raise HTTPException(status_code=404, detail=str(e)) from e
 
     return _to_response(job)
 

document-parser/api/documents.py

@@ -44,7 +44,7 @@ async def upload(file: UploadFile):
             file_content=content,
         )
     except ValueError as e:
-        raise HTTPException(status_code=413, detail=str(e))
+        raise HTTPException(status_code=413, detail=str(e)) from e
 
     return _to_response(doc)
 
@@ -90,7 +90,7 @@ async def preview(
         png_bytes = document_service.generate_preview(file_content, page=page, dpi=dpi)
         return Response(content=png_bytes, media_type="image/png")
     except ValueError as e:
-        raise HTTPException(status_code=404, detail=str(e))
+        raise HTTPException(status_code=404, detail=str(e)) from e
-    except Exception:
+    except Exception as exc:
         logger.exception("Failed to generate preview")
-        raise HTTPException(status_code=422, detail="Failed to generate preview")
+        raise HTTPException(status_code=422, detail="Failed to generate preview") from exc

document-parser/conftest.py

@@ -1,4 +1,3 @@
-import pytest
 
 
 pytest_plugins = ["pytest_asyncio"]

document-parser/domain/models.py

@@ -5,10 +5,10 @@ from __future__ import annotations
 import enum
 import uuid
 from dataclasses import dataclass, field
-from datetime import datetime, timezone
+from datetime import UTC, datetime
 
 
-class AnalysisStatus(str, enum.Enum):
+class AnalysisStatus(enum.StrEnum):
     PENDING = "PENDING"
     RUNNING = "RUNNING"
     COMPLETED = "COMPLETED"
@@ -16,7 +16,7 @@ class AnalysisStatus(str, enum.Enum):
 
 
 def _utcnow() -> datetime:
-    return datetime.now(timezone.utc)
+    return datetime.now(UTC)
 
 
 def _new_id() -> str:

document-parser/domain/parsing.py

@@ -6,17 +6,18 @@ per-page elements with bounding boxes and hierarchy levels.
 
 from __future__ import annotations
 
+import contextlib
 import logging
 import threading
 from dataclasses import dataclass, field
 
-from docling.document_converter import DocumentConverter, PdfFormatOption
 from docling.datamodel.base_models import InputFormat
 from docling.datamodel.pipeline_options import (
     PdfPipelineOptions,
     TableFormerMode,
     TableStructureOptions,
 )
+from docling.document_converter import DocumentConverter, PdfFormatOption
 from docling_core.types.doc import (
     CodeItem,
     DocItem,
@@ -215,10 +216,8 @@ def _process_content_item(
 
             content = getattr(item, "text", "") or ""
             if isinstance(item, TableItem):
-                try:
+                with contextlib.suppress(AttributeError, ValueError):
                     content = item.export_to_markdown()
-                except (AttributeError, ValueError):
-                    pass
 
             pages[page_no].elements.append(
                 PageElement(type=element_type, bbox=bbox, content=content, level=level)

document-parser/main.py

@@ -14,9 +14,9 @@ from contextlib import asynccontextmanager
 from fastapi import FastAPI
 from fastapi.middleware.cors import CORSMiddleware
 
-from persistence.database import init_db
-from api.documents import router as documents_router
 from api.analyses import router as analyses_router
+from api.documents import router as documents_router
+from persistence.database import init_db
 
 logging.basicConfig(
     level=logging.INFO,

document-parser/persistence/analysis_repo.py

@@ -18,7 +18,7 @@ def _row_to_job(row) -> AnalysisJob:
         started_at=row["started_at"],
         completed_at=row["completed_at"],
         created_at=row["created_at"],
-        document_filename=row["filename"] if "filename" in row.keys() else None,
+        document_filename=row["filename"] if "filename" in row.keys() else None,  # noqa: SIM118
     )
 
 

document-parser/pyproject.toml

@@ -0,0 +1,30 @@
+[tool.ruff]
+target-version = "py312"
+line-length = 100
+
+[tool.ruff.lint]
+select = [
+  "E",    # pycodestyle errors
+  "W",    # pycodestyle warnings
+  "F",    # pyflakes
+  "I",    # isort
+  "N",    # pep8-naming
+  "UP",   # pyupgrade
+  "B",    # flake8-bugbear
+  "SIM",  # flake8-simplify
+  "TCH",  # flake8-type-checking
+  "RUF",  # ruff-specific
+]
+ignore = [
+  "E501",   # line too long (handled by formatter)
+  "B008",   # do not perform function calls in argument defaults (FastAPI Depends)
+  "N815",   # camelCase in Pydantic models (intentional — matches frontend API contract)
+  "TC003",  # datetime import used at runtime by Pydantic
+]
+
+[tool.ruff.lint.isort]
+known-first-party = ["api", "domain", "persistence", "services"]
+
+[tool.ruff.format]
+quote-style = "double"
+indent-style = "space"

document-parser/services/analysis_service.py

@@ -96,7 +96,7 @@ async def _run_analysis(
 
         logger.info("Analysis completed: %s (%d pages)", job_id, result.page_count)
 
-    except asyncio.TimeoutError:
+    except TimeoutError:
         logger.error("Analysis timed out after %ds: %s", CONVERSION_TIMEOUT, job_id)
         await _mark_failed(job_id, f"Conversion timed out after {CONVERSION_TIMEOUT}s")
 

document-parser/tests/test_api_endpoints.py

@@ -5,7 +5,7 @@ from unittest.mock import AsyncMock, patch
 import pytest
 from fastapi.testclient import TestClient
 
-from domain.models import AnalysisJob, AnalysisStatus, Document
+from domain.models import AnalysisJob, Document
 from main import app
 
 

document-parser/tests/test_bbox.py

@@ -33,8 +33,8 @@ class TestToTopleftList:
         bbox = BoundingBox(l=10, t=500, r=300, b=100, coord_origin=CoordOrigin.BOTTOMLEFT)
         result = to_topleft_list(bbox, page_height=800.0)
 
-        l, t, r, b = result
+        left, t, r, b = result
-        assert r > l, "width should be positive"
+        assert r > left, "width should be positive"
         assert b > t, "height should be positive"
 
     def test_full_page_bbox_bottomleft(self):

document-parser/tests/test_models.py

@@ -1,6 +1,6 @@
 """Tests for domain models."""
 
-from datetime import datetime, timezone
+from datetime import datetime
 
 from domain.models import AnalysisJob, AnalysisStatus, Document
 

document-parser/tests/test_pipeline_options.py

@@ -2,8 +2,7 @@
 
 from __future__ import annotations
 
-import asyncio
+from unittest.mock import AsyncMock, MagicMock, patch
-from unittest.mock import AsyncMock, MagicMock, patch, call
 
 import pytest
 from docling.datamodel.base_models import InputFormat
@@ -12,8 +11,11 @@ from docling.datamodel.pipeline_options import (
     TableFormerMode,
 )
 
-from domain.parsing import ConversionOptions, build_converter, convert_document, get_default_converter
+from domain.parsing import (
-
+    ConversionOptions,
+    build_converter,
+    convert_document,
+)
 
 # ---------------------------------------------------------------------------
 # build_converter — verifies Docling pipeline options are wired correctly
@@ -452,6 +454,7 @@ class TestAnalysisEndpointPipelineOptions:
     @pytest.fixture
     def client(self):
         from fastapi.testclient import TestClient
+
         from main import app
         return TestClient(app, raise_server_exceptions=False)
 

document-parser/tests/test_repos.py

@@ -1,11 +1,10 @@
 """Tests for persistence repositories using a temporary SQLite database."""
 
-import os
 
 import pytest
 
 from domain.models import AnalysisJob, AnalysisStatus, Document
-from persistence import document_repo, analysis_repo
+from persistence import analysis_repo, document_repo
 from persistence.database import init_db
 
 

document-parser/tests/test_schemas.py

@@ -1,6 +1,5 @@
 """Tests for API schemas — camelCase serialization and validation."""
 
-from datetime import datetime
 
 import pytest
 

frontend/.prettierignore

@@ -0,0 +1,3 @@
+dist/
+node_modules/
+package-lock.json

frontend/.prettierrc

@@ -0,0 +1,9 @@
+{
+  "semi": false,
+  "singleQuote": true,
+  "trailingComma": "all",
+  "printWidth": 100,
+  "tabWidth": 2,
+  "arrowParens": "always",
+  "vueIndentScriptAndStyle": false
+}

frontend/eslint.config.js

@@ -0,0 +1,26 @@
+import js from '@eslint/js'
+import pluginVue from 'eslint-plugin-vue'
+
+export default [
+  js.configs.recommended,
+  ...pluginVue.configs['flat/recommended'],
+  {
+    files: ['src/**/*.{js,vue}'],
+    rules: {
+      'no-console': ['warn', { allow: ['warn', 'error'] }],
+      'no-debugger': 'error',
+      'no-unused-vars': ['error', { argsIgnorePattern: '^_' }],
+      'vue/multi-word-component-names': 'off',
+      'vue/require-default-prop': 'off',
+      // Formatting handled by Prettier
+      'vue/max-attributes-per-line': 'off',
+      'vue/singleline-html-element-content-newline': 'off',
+      'vue/html-closing-bracket-spacing': 'off',
+      'vue/html-self-closing': 'off',
+      'vue/attributes-order': 'off',
+    },
+  },
+  {
+    ignores: ['dist/', 'node_modules/', '*.config.js'],
+  },
+]

frontend/jsconfig.json

@@ -0,0 +1,20 @@
+{
+  "compilerOptions": {
+    "target": "ES2022",
+    "module": "ESNext",
+    "moduleResolution": "bundler",
+    "strict": false,
+    "jsx": "preserve",
+    "resolveJsonModule": true,
+    "isolatedModules": true,
+    "esModuleInterop": true,
+    "lib": ["ESNext", "DOM"],
+    "skipLibCheck": true,
+    "noEmit": true,
+    "paths": {
+      "@/*": ["./src/*"]
+    }
+  },
+  "include": ["src/**/*.js", "src/**/*.vue"],
+  "exclude": ["node_modules", "dist"]
+}

frontend/package.json

@@ -8,7 +8,11 @@
     "build": "vite build",
     "preview": "vite preview",
     "test": "vitest --watch",
-    "test:run": "vitest run"
+    "test:run": "vitest run",
+    "lint": "eslint src/",
+    "lint:fix": "eslint src/ --fix",
+    "format": "prettier --write src/",
+    "format:check": "prettier --check src/"
   },
   "dependencies": {
     "dompurify": "^3.3.3",
@@ -18,7 +22,11 @@
     "vue-router": "^4.6.4"
   },
   "devDependencies": {
+    "@eslint/js": "^9.0.0",
     "@vitejs/plugin-vue": "^5.2.0",
+    "eslint": "^9.0.0",
+    "eslint-plugin-vue": "^9.32.0",
+    "prettier": "^3.4.0",
     "vite": "^5.4.0",
     "vitest": "^2.1.0"
   }

frontend/src/features/analysis/pipelineOptions.test.js

@@ -1,6 +1,5 @@
 import { describe, it, expect, vi, beforeEach, afterEach } from 'vitest'
 import { setActivePinia, createPinia } from 'pinia'
-import { createAnalysis } from './api.js'
 import { useAnalysisStore } from './store.js'
 
 vi.mock('../../shared/api/http.js', () => ({
@@ -14,7 +13,6 @@ vi.mock('./api.js', () => ({
   deleteAnalysis: vi.fn(),
 }))
 
-import { apiFetch } from '../../shared/api/http.js'
 import * as api from './api.js'
 
 // ---------------------------------------------------------------------------
@@ -22,9 +20,6 @@ import * as api from './api.js'
 // ---------------------------------------------------------------------------
 
 describe('createAnalysis — pipeline options body construction', () => {
-  // For these tests we need the REAL createAnalysis, not the mock.
-  // So we re-import the actual module.
-  let realCreateAnalysis
 
   beforeEach(() => {
     vi.clearAllMocks()