obliq-ocr 0.1.0__tar.gz

obliq_ocr-0.1.0/.gitattributes

@@ -0,0 +1,6 @@
+* text=auto eol=lf
+*.py text eol=lf
+*.md text eol=lf
+*.toml text eol=lf
+*.yml text eol=lf
+*.json text eol=lf

obliq_ocr-0.1.0/.github/ISSUE_TEMPLATE/architecture.yml

@@ -0,0 +1,26 @@
+name: Architecture & Refactoring
+description: Propose architectural changes, structural refactoring, or engine updates.
+title: "[Arch]: "
+labels: ["type:refactoring", "needs-triage"]
+body:
+  - type: textarea
+    id: arch-summary
+    attributes:
+      label: Problem / Context
+      description: Describe the current architectural limitation, technical debt, or bottleneck.
+    validations:
+      required: true
+  - type: textarea
+    id: proposed-architecture
+    attributes:
+      label: Proposed Architecture & Modules
+      description: Outline the structural changes (e.g., core engine decoupling, ONNX session pooling, PyMuPDF interface changes).
+    validations:
+      required: true
+  - type: textarea
+    id: breaking-changes
+    attributes:
+      label: Breaking Changes & Compatibility
+      description: List any potential breaking changes to public APIs or internal module contracts.
+    validations:
+      required: false

obliq_ocr-0.1.0/.github/ISSUE_TEMPLATE/bug_report.yml

@@ -0,0 +1,17 @@
+name: Bug Report
+description: File a bug report to help us improve obliq-OCR.
+title: "[Bug]: "
+labels: ["type:bug"]
+body:
+  - type: textarea
+    attributes:
+      label: Description
+      description: A clear and concise description of what the bug is.
+    validations:
+      required: true
+  - type: textarea
+    attributes:
+      label: Reproduction / Steps to Reproduce
+      description: Share sample code snippet or document properties (digital vs scanned).
+    validations:
+      required: true

obliq_ocr-0.1.0/.github/ISSUE_TEMPLATE/ci.yml

@@ -0,0 +1,30 @@
+name: CI / Tooling Update
+description: Request or propose updates to GitHub Actions workflows, linting, packaging, or pre-commit hooks.
+title: "[CI]: "
+labels: ["type:ci", "needs-triage"]
+body:
+  - type: textarea
+    id: ci-description
+    attributes:
+      label: Overview
+      description: Describe the workflow change, quality gate, matrix update, or security scan to be added/modified.
+    validations:
+      required: true
+  - type: dropdown
+    id: ci-category
+    attributes:
+      label: Category
+      options:
+        - GitHub Actions Workflow
+        - Pre-commit Hooks / Ruff / Mypy
+        - Packaging (Hatch / Hatch-vcs / Build)
+        - Security & Dependency Scanning
+    validations:
+      required: true
+  - type: textarea
+    id: verification-plan
+    attributes:
+      label: Verification & Test Plan
+      description: How should this CI workflow change be tested and validated?
+    validations:
+      required: true

obliq_ocr-0.1.0/.github/ISSUE_TEMPLATE/cli.yml

@@ -0,0 +1,19 @@
+name: CLI Feature or Issue
+description: Report bugs or request enhancements specifically related to the obliq-OCR command-line interface.
+title: "[CLI]: "
+labels: ["cli", "needs-triage"]
+body:
+  - type: textarea
+    id: cli-summary
+    attributes:
+      label: Summary
+      description: Describe the CLI feature request, argument change, or behavior bug.
+    validations:
+      required: true
+  - type: textarea
+    id: command-example
+    attributes:
+      label: Command Execution & Expected Output
+      description: Provide the exact `obliq-ocr ...` command invocation and expected terminal output.
+    validations:
+      required: true

obliq_ocr-0.1.0/.github/ISSUE_TEMPLATE/feature_request.yml

@@ -0,0 +1,26 @@
+name: Feature Request
+description: Propose a new feature, enhancement, or capability for obliq-OCR.
+title: "[Feat]: "
+labels: ["type:feature", "needs-triage"]
+body:
+  - type: textarea
+    id: feature-description
+    attributes:
+      label: Feature Description
+      description: A clear and concise description of what you want to achieve or add.
+    validations:
+      required: true
+  - type: textarea
+    id: use-case
+    attributes:
+      label: Use Case & Motivation
+      description: Why is this feature needed? What problem does it solve for users or downstream workflows?
+    validations:
+      required: true
+  - type: textarea
+    id: proposed-solution
+    attributes:
+      label: Proposed Implementation / Design
+      description: Optional detailed description of how this could be implemented (API surface, modules, or dependencies).
+    validations:
+      required: false

obliq_ocr-0.1.0/.github/ISSUE_TEMPLATE/testing.yml

@@ -0,0 +1,19 @@
+name: Testing & Test Fixtures
+description: Propose new test suites, synthetic PDF fixture enhancements, or coverage additions.
+title: "[Test]: "
+labels: ["type:test", "needs-triage"]
+body:
+  - type: textarea
+    id: test-gap
+    attributes:
+      label: Testing Scope / Gap
+      description: Identify missing test scenarios, uncovered modules, or edge-case PDF fixtures needing validation.
+    validations:
+      required: true
+  - type: textarea
+    id: implementation-details
+    attributes:
+      label: Test Implementation Details
+      description: Describe how synthetic PDF fixtures or unit/integration tests should be constructed under `tests/`.
+    validations:
+      required: false

obliq_ocr-0.1.0/.github/dependabot.yml

@@ -0,0 +1,14 @@
+version: 2
+updates:
+  - package-ecosystem: "pip"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+    open-pull-requests-limit: 10
+    reviewers:
+      - "abhirajadhikary06"
+
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "weekly"

obliq_ocr-0.1.0/.github/labeler.yml

@@ -0,0 +1,29 @@
+
+ocr:
+  - changed-files:
+      - any-glob-to-any-file:
+          - "src/obliq_ocr/parser.py"
+          - "src/obliq_ocr/engine.py"
+          - "src/obliq_ocr/cli.py"
+
+pdf-parsing:
+  - changed-files:
+      - any-glob-to-any-file:
+          - "src/obliq_ocr/core.py"
+          - "src/obliq_ocr/utils.py"
+
+packaging:
+  - changed-files:
+      - any-glob-to-any-file:
+          - "pyproject.toml"
+          - "setup.py"
+
+github_actions:
+  - changed-files:
+      - any-glob-to-any-file:
+          - ".github/workflows/**"
+
+test:
+  - changed-files:
+      - any-glob-to-any-file:
+          - "tests/**/*.py"

obliq_ocr-0.1.0/.github/pull_request_template.md

@@ -0,0 +1,13 @@
+## Description
+<!-- Provide a brief description of the changes introduced in this PR. -->
+
+## Changes
+- [ ] Bug fix / Refactoring
+- [ ] New feature (`type:feature`)
+- [ ] Documentation update (`type:docs`)
+- [ ] CI / Tooling change (`type:ci`)
+
+## Testing & Validation
+- [ ] Passed unit and integration test suite (`pytest`)
+- [ ] Verified performance / accuracy regression benchmarks (if applicable)
+- [ ] Tested locally via wheel installation in a clean venv

obliq_ocr-0.1.0/.github/release-drafter.yml

@@ -0,0 +1,48 @@
+name-template: "v$RESOLVED_VERSION"
+tag-template: "v$RESOLVED_VERSION"
+
+categories:
+  - title: "💥 Breaking Changes"
+    labels:
+      - "breaking-change"
+      - "major"
+
+  - title: "🚢 New Features & Enhancements"
+    labels:
+      - "feature"
+      - "enhancement"
+
+  - title: "🦗 Bug Fixes"
+    labels:
+      - "bug"
+      - "fix"
+
+  - title: "📦 Packaging & Release"
+    labels:
+      - "packaging"
+      - "ci"
+
+version-resolver:
+  major:
+    labels:
+      - "breaking-change"
+      - "major"
+
+  minor:
+    labels:
+      - "feature"
+      - "enhancement"
+
+  patch:
+    labels:
+      - "bug"
+      - "fix"
+      - "packaging"
+      - "ci"
+
+  default: patch
+
+template: |
+  ## Changes
+  $CHANGES
+  **Full Changelog**: $COMPARE_URL

obliq_ocr-0.1.0/.github/workflows/autolabel.yml

@@ -0,0 +1,21 @@
+
+name: Auto-Labeler
+
+on:
+  pull_request_target:
+    types: [opened, synchronize, reopened]
+
+jobs:
+  label:
+    runs-on: ubuntu-latest
+
+    permissions:
+      contents: read
+      pull-requests: write
+
+    steps:
+      - name: Automatically label pull requests
+        uses: actions/labeler@v7
+        with:
+          repo-token: ${{ secrets.GITHUB_TOKEN }}
+          configuration-path: .github/labeler.yml

obliq_ocr-0.1.0/.github/workflows/ci.yml

@@ -0,0 +1,143 @@
+name: CI Quality Gates
+
+on:
+  push:
+    branches: [ main ]
+    paths:
+      - 'src/**'
+      - 'tests/**'
+      - 'pyproject.toml'
+      - 'Makefile'
+      - 'README.md'  # tests/test_readme.py runs the quickstart
+      - '.github/workflows/ci.yml'
+  pull_request:
+    branches: [ main ]
+    paths:
+      - 'src/**'
+      - 'tests/**'
+      - 'pyproject.toml'
+      - 'Makefile'
+      - 'README.md'  # tests/test_readme.py runs the quickstart
+      - '.github/workflows/ci.yml'
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  lint-and-typecheck:
+    name: Lint & Type Check
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout Code
+        uses: actions/checkout@v4
+
+      - name: Install System Dependencies (OpenCV / OpenGL)
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y libgl1 libglib2.0-0
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+          cache: 'pip'
+
+      - name: Install Dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install -e .[dev] ruff mypy
+
+      - name: Run Ruff Linter
+        run: ruff check .
+
+      - name: Run Ruff Formatter Check
+        run: ruff format --check --exclude src/obliq_ocr/_version.py .
+
+      - name: Run Mypy Type Check
+        run: mypy src/
+
+  test-matrix:
+    name: Test (Python ${{ matrix.python-version }})
+    needs: lint-and-typecheck
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ['3.10', '3.11', '3.12']
+    steps:
+      - name: Checkout Code
+        uses: actions/checkout@v4
+
+      - name: Install System Dependencies (OpenCV / OpenGL)
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y libgl1 libglib2.0-0
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: 'pip'
+
+      - name: Install Package & Test Dependencies
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install -e .[test,dev] pytest pytest-cov jiwer
+
+      - name: Generate Synthetic PDF Fixtures
+        run: python tests/scripts/generate_fixtures.py
+
+      - name: Run Pytest Suite with Coverage
+        run: python -m pytest --cov=obliq_ocr
+
+      - name: Run Model-Accuracy Regression Gate
+        run: python tests/scripts/evaluate_accuracy.py
+
+      - name: Run Performance Benchmark Check
+        run: python tests/scripts/benchmark_performance.py
+
+      - name: Upload Coverage to Codecov
+        uses: codecov/codecov-action@v4
+        with:
+          file: ./coverage.xml
+          fail_ci_if_error: false
+          slug: OBLIQ-in/obliq-OCR
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
+
+  build-package:
+    name: Build & Validate Package
+    needs: lint-and-typecheck
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout Code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+          cache: 'pip'
+
+      - name: Install PEP 517 Build Tools
+        run: |
+          python -m pip install --upgrade pip
+          pip install build twine hatch-vcs
+
+      - name: Build Source Distribution and Wheel
+        run: python -m build
+
+      - name: Check Package Metadata Rendering
+        run: twine check dist/*
+
+      - name: Install Wheel in Isolated Venv & Run Smoke Test
+        run: |
+          python -m venv .smoke_venv
+          source .smoke_venv/bin/activate
+          pip install --upgrade pip
+          pip install dist/*.whl
+          python -c "import obliq_ocr; print('Package imported successfully, version:', obliq_ocr.__version__)"
+          obliq-ocr --help

obliq_ocr-0.1.0/.github/workflows/docs.yml

@@ -0,0 +1,84 @@
+name: Docs Site
+
+# Builds the docs site on every PR (strict: a broken link or bad reference
+# fails the build) and deploys it to GitHub Pages when a release is published.
+# Run it by hand on main for the first deploy.
+
+on:
+  pull_request:
+    branches: [ main ]
+    paths:
+      - 'docs/**'
+      - 'src/**'
+      - 'README.md'
+      - 'mkdocs.yml'
+      - 'mkdocs_hooks.py'
+      - 'pyproject.toml'
+      - '.github/workflows/docs.yml'
+  push:
+    branches: [ main ]
+    paths:
+      - 'docs/**'
+      - 'src/**'
+      - 'README.md'
+      - 'mkdocs.yml'
+      - 'mkdocs_hooks.py'
+      - 'pyproject.toml'
+      - '.github/workflows/docs.yml'
+  release:
+    types: [ published ]
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  build:
+    name: Build Docs (strict)
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout Code
+        uses: actions/checkout@v4
+
+      # The docs tools need Python 3.11+, even though the package supports 3.10.
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.12'
+          cache: 'pip'
+
+      - name: Install Docs Tools
+        run: |
+          python -m pip install --upgrade pip
+          pip install --group docs
+
+      - name: Build Site
+        run: mkdocs build --strict
+        env:
+          NO_MKDOCS_2_WARNING: '1'
+
+      - name: Upload Site for Pages
+        if: github.event_name == 'release' || github.event_name == 'workflow_dispatch'
+        uses: actions/upload-pages-artifact@v3
+        with:
+          path: site
+
+  deploy:
+    name: Deploy to GitHub Pages
+    needs: build
+    if: github.event_name == 'release' || (github.event_name == 'workflow_dispatch' && github.ref == 'refs/heads/main')
+    runs-on: ubuntu-latest
+    permissions:
+      pages: write
+      id-token: write
+    environment:
+      name: github-pages
+      url: ${{ steps.deployment.outputs.page_url }}
+    steps:
+      - name: Deploy
+        id: deployment
+        uses: actions/deploy-pages@v4

obliq_ocr-0.1.0/.github/workflows/gitleaks.yml

@@ -0,0 +1,39 @@
+name: Secret Scanning (Gitleaks)
+
+on:
+  push:
+    branches: [ main ]
+    paths-ignore:
+      - '**/*.md'
+      - 'docs/**'
+      - '.gitignore'
+      - '.lychee.toml'
+  pull_request:
+    branches: [ main ]
+    paths-ignore:
+      - '**/*.md'
+      - 'docs/**'
+      - '.gitignore'
+      - '.lychee.toml'
+  schedule:
+    - cron: '0 0 * * 1'
+  workflow_dispatch:
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  gitleaks:
+    name: Gitleaks Scan
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout Code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Run Gitleaks Scan via Docker
+        uses: docker://zricethezav/gitleaks:latest
+        with:
+          args: detect --source="/github/workspace" --verbose

obliq_ocr-0.1.0/.github/workflows/link-checker.yml

@@ -0,0 +1,47 @@
+name: Documentation Link Checker
+
+on:
+  push:
+    branches: [ main ]
+    paths:
+      - '**/*.md'
+      - 'docs/**'
+      - '.lychee.toml'
+      - '.github/workflows/link-checker.yml'
+  pull_request:
+    branches: [ main ]
+    paths:
+      - '**/*.md'
+      - 'docs/**'
+      - '.lychee.toml'
+      - '.github/workflows/link-checker.yml'
+  schedule:
+    # Run weekly on Sundays at 00:00 UTC to catch dead external links
+    - cron: '0 0 * * 0'
+  workflow_dispatch:
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  lychee-link-check:
+    name: Check Markdown Links
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout Code
+        uses: actions/checkout@v4
+
+      - name: Restore Lychee Cache
+        uses: actions/cache@v4
+        with:
+          path: .lycheecache
+          key: cache-lychee-${{ github.sha }}
+          restore-keys: cache-lychee-
+
+      - name: Run Lychee Link Checker
+        uses: lycheeverse/lychee-action@v2.3.0
+        with:
+          args: --config .lychee.toml --no-progress './**/*.md'
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

obliq_ocr-0.1.0/.github/workflows/pr-title.yml

@@ -0,0 +1,36 @@
+name: Pull Request Title Check
+
+on:
+  pull_request:
+    types: [opened, edited, synchronize, reopened]
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  validate-pr-title:
+    name: Validate PR Title
+    runs-on: ubuntu-latest
+    steps:
+      - name: Lint PR Title
+        uses: amannn/action-semantic-pull-request@v5
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          # Configure permitted conventional commit types
+          types: |
+            feat
+            fix
+            docs
+            style
+            refactor
+            perf
+            test
+            ci
+            chore
+            revert
+          # Require a scope (optional, set to false if scopes shouldn't be strictly mandatory)
+          requireScope: false
+          # Custom error message for invalid titles
+          validateSingleCommit: true

obliq_ocr-0.1.0/.github/workflows/release-drafter.yml

@@ -0,0 +1,60 @@
+name: Release Drafter & Changelog Sync
+
+on:
+  push:
+    branches:
+      - main
+  release:
+    types: [published]
+
+permissions:
+  contents: write
+  pull-requests: read
+
+jobs:
+  update_release_draft:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Run Release Drafter
+        uses: release-drafter/release-drafter@v6
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+  update_changelog:
+    if: github.event_name == 'release' && github.event.action == 'published'
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Append Release Notes to Changelog
+        run: |
+          # Create a temp file with the new release entry
+          echo "## [${{ github.event.release.tag_name }}] - $(date +%Y-%m-%d)" > new_entry.md
+          echo "" >> new_entry.md
+          echo "${{ github.event.release.body }}" >> new_entry.md
+          echo "" >> new_entry.md
+
+          # Insert the new entry right below the header in CHANGELOG.md (preserving older entries)
+          python3 -c "
+          with open('CHANGELOG.md', 'r') as f:
+              content = f.read()
+
+          # Find where '## [Unreleased]' or the first version header starts, and insert above it
+          marker = '## [Unreleased]'
+          if marker in content:
+              parts = content.split(marker)
+              new_content = parts[0] + marker + '\n\n' + open('new_entry.md').read() + '---\n\n' + parts[1]
+          else:
+              new_content = open('new_entry.md').read() + '\n' + content
+
+          with open('CHANGELOG.md', 'w') as f:
+              f.write(new_content)
+          "
+          rm new_entry.md
+
+      - name: Commit and Push Changelog
+        uses: stefanzweifel/git-auto-commit-action@v5
+        with:
+          commit_message: "docs(changelog): update CHANGELOG.md for v${{ github.event.release.tag_name }}"
+          file_pattern: "CHANGELOG.md"