kreuzberg 3.2.0__tar.gz → 3.4.0__tar.gz

kreuzberg-3.4.0/.commitlintrc

@@ -0,0 +1 @@
+{ "extends": ["@commitlint/config-conventional"] }

kreuzberg-3.4.0/.docker/Dockerfile

@@ -0,0 +1,21 @@
+FROM ghcr.io/astral-sh/uv:python3.13-bookworm as app
+ARG EXTRAS=""
+WORKDIR /app
+ENV PYTHONDONTWRITEBYTECODE 1
+ENV PYTHONUNBUFFERED 1
+ENV UV_LINK_MODE=copy
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    pandoc \
+    tesseract-ocr \
+    && apt-get clean && rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
+
+
+COPY pyproject.toml uv.lock README.md ./
+COPY kreuzberg kreuzberg
+
+RUN uv sync --extra api${EXTRAS:+ --extra ${EXTRAS}} --no-editable --no-dev --compile-bytecode
+
+RUN groupadd -r appuser && useradd -r -g appuser -d /app -s /sbin/nologin appuser
+USER appuser
+CMD ["litestar", "--app", "kreuzberg._api.main:app", "run", "--host", "0.0.0.0"]

kreuzberg-3.4.0/.docker/README.md

@@ -0,0 +1,87 @@
+# Kreuzberg Docker Images
+
+[![GitHub](https://img.shields.io/badge/GitHub-Goldziher%2Fkreuzberg-blue)](https://github.com/Goldziher/kreuzberg)
+[![PyPI](https://badge.fury.io/py/kreuzberg.svg)](https://badge.fury.io/py/kreuzberg)
+[![Documentation](https://img.shields.io/badge/docs-GitHub_Pages-blue)](https://goldziher.github.io/kreuzberg/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://github.com/Goldziher/kreuzberg/blob/main/LICENSE)
+
+High-performance Python library for text extraction from documents, available as Docker images.
+
+**Source Code**: [github.com/Goldziher/kreuzberg](https://github.com/Goldziher/kreuzberg)
+
+## Quick Start
+
+```bash
+docker run -p 8000:8000 goldziher/kreuzberg:latest
+```
+
+## Available Tags
+
+- `latest` - Latest stable release with API server and Tesseract OCR
+- `X.Y.Z` - Specific version (e.g., `3.0.0`)
+- `X.Y.Z-easyocr` - With EasyOCR support
+- `X.Y.Z-paddle` - With PaddleOCR support
+- `X.Y.Z-gmft` - With GMFT table extraction
+- `X.Y.Z-all` - With all optional dependencies
+
+## Usage
+
+### Extract Files via API
+
+```bash
+# Single file
+curl -X POST http://localhost:8000/extract \
+  -F "data=@document.pdf"
+
+# Multiple files
+curl -X POST http://localhost:8000/extract \
+  -F "data=@document1.pdf" \
+  -F "data=@document2.docx"
+```
+
+### Docker Compose
+
+```yaml
+version: '3.8'
+
+services:
+  kreuzberg:
+    image: goldziher/kreuzberg:latest
+    ports:
+      - "8000:8000"
+    restart: unless-stopped
+```
+
+## Features
+
+- **🚀 High Performance**: Optimized for speed and efficiency
+- **📄 Multiple Formats**: PDF, DOCX, images, HTML, and more
+- **🔍 OCR Support**: Built-in Tesseract, optional EasyOCR/PaddleOCR
+- **📊 Table Extraction**: Extract tables with GMFT
+- **🔒 Secure**: Runs as non-root user, no external API calls
+- **📦 Ready to Use**: Pre-configured API server
+
+## Documentation
+
+- **[GitHub Repository](https://github.com/Goldziher/kreuzberg)** - Source code and issue tracking
+- **[Full Documentation](https://goldziher.github.io/kreuzberg/)** - Complete user guide and API reference
+- **[API Documentation](https://goldziher.github.io/kreuzberg/user-guide/api-server/)** - REST API endpoints and usage
+- **[Docker Guide](https://goldziher.github.io/kreuzberg/user-guide/docker/)** - Detailed Docker usage guide
+
+## Support
+
+- **Issues**: [github.com/Goldziher/kreuzberg/issues](https://github.com/Goldziher/kreuzberg/issues)
+- **Discussions**: [github.com/Goldziher/kreuzberg/discussions](https://github.com/Goldziher/kreuzberg/discussions)
+- **Discord**: [Join our community](https://discord.gg/pXxagNK2zN)
+
+## Contributing
+
+Contributions are welcome! See our [Contributing Guide](https://github.com/Goldziher/kreuzberg/blob/main/docs/contributing.md).
+
+## License
+
+MIT License - see [LICENSE](https://github.com/Goldziher/kreuzberg/blob/main/LICENSE) for details.
+
+______________________________________________________________________
+
+Made with ❤️ by the [Kreuzberg contributors](https://github.com/Goldziher/kreuzberg/graphs/contributors)

kreuzberg-3.4.0/.dockerignore

@@ -0,0 +1,15 @@
+*.pyc
+*.pyd
+*.pyo
+.git
+.github/
+.gitignore
+.idea
+.mypy_cache
+.pytest_cache
+.ruff_cache
+.vscode
+__pycache__
+benchmarks/
+docs/
+tests/

kreuzberg-3.4.0/.github/benchmarks/README.md

@@ -0,0 +1,15 @@
+# Performance Baseline
+
+This directory contains baseline performance metrics for the Kreuzberg library.
+
+## Files
+
+- `baseline.json` - Performance baseline automatically updated from main branch CI
+- This file is used for performance regression detection in PRs
+
+## How it works
+
+1. When code is pushed to `main`, CI runs benchmarks and stores results as `baseline.json`
+1. When PRs are opened, CI compares current performance against this baseline
+1. If performance degrades beyond threshold (20%), the CI check fails
+1. The baseline is automatically updated when new changes are merged to main

kreuzberg-3.4.0/.github/dependabot.yaml

@@ -0,0 +1,6 @@
+version: 2
+updates:
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "daily"

kreuzberg-3.4.0/.github/workflows/ci.yaml

@@ -0,0 +1,124 @@
+name: CI
+
+on:
+  pull_request:
+    branches:
+      - main
+  push:
+    branches:
+      - main
+      - feat/smart-multiprocessing
+
+jobs:
+  validate:
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v6
+        with:
+          enable-cache: true
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version-file: "pyproject.toml"
+
+      - name: Install Dependencies
+        shell: bash
+        run: |
+          if [[ "${{ runner.os }}" == "Windows" ]] && [[ -d ".venv" ]]; then
+            echo "Removing existing .venv directory on Windows"
+            rm -rf .venv
+          fi
+          uv sync --all-packages --all-extras --dev
+
+      - name: Load Cached Pre-Commit Dependencies
+        id: cached-pre-commit-dependencies
+        uses: actions/cache@v4
+        with:
+          path: ~/.cache/pre-commit/
+          key: pre-commit|${{ env.pythonLocation }}|${{ hashFiles('.pre-commit-config.yaml') }}
+
+      - name: Execute Pre-Commit
+        run: uv run pre-commit run --show-diff-on-failure --color=always --all-files
+
+  test:
+    strategy:
+      matrix:
+        os: [ ubuntu-latest, macOS-latest, windows-latest ]
+        python: ${{ github.event_name == 'pull_request' && fromJSON('["3.13"]') || fromJSON('["3.9", "3.10", "3.11", "3.12", "3.13"]') }}
+    runs-on: ${{ matrix.os }}
+    timeout-minutes: 30
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v6
+        with:
+          enable-cache: true
+
+      - name: Install Python
+        uses: actions/setup-python@v5
+        id: setup-python
+        with:
+          python-version: ${{ matrix.python }}
+
+      - name: Cache Python Dependencies
+        id: python-cache
+        uses: actions/cache@v4
+        with:
+          path: |
+            ~/.cache/uv
+            .venv
+          key: python-dependencies-${{ matrix.os }}-${{ steps.setup-python.outputs.python-version }}-${{ hashFiles('uv.lock') }}
+          restore-keys: |
+            python-dependencies-${{ matrix.os }}-${{ matrix.python }}-
+
+      - name: Install Dependencies
+        shell: bash
+        run: |
+          if [[ "${{ runner.os }}" == "Windows" ]] && [[ -d ".venv" ]]; then
+            echo "Removing existing .venv directory on Windows"
+            rm -rf .venv
+          fi
+          uv sync --all-packages --all-extras --dev
+
+      - name: Cache Test Artifacts
+        uses: actions/cache@v4
+        with:
+          path: .pytest_cache/
+          key: pytest-cache-${{ matrix.os }}-${{ matrix.python }}
+
+      - name: Cache and Install Homebrew (macOS)
+        if: runner.os == 'macOS'
+        uses: tecolicom/actions-use-homebrew-tools@v1
+        with:
+          tools: 'tesseract tesseract-lang pandoc'
+          key: 'homebrew-tools-${{ runner.os }}'
+          cache: yes
+          verbose: false
+
+      - name: Cache and Install APT Packages (Linux)
+        if: runner.os == 'Linux'
+        uses: awalsh128/cache-apt-pkgs-action@latest
+        with:
+          packages: tesseract-ocr tesseract-ocr-deu pandoc
+          version: 1.0
+
+      - name: Install System Dependencies (Windows)
+        if: runner.os == 'Windows'
+        run: |
+          choco install -y tesseract pandoc
+          Write-Output "C:\Program Files\Tesseract-OCR" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
+          Write-Output "C:\Program Files\Pandoc" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
+          $env:PATH = "C:\Program Files\Tesseract-OCR;C:\Program Files\Pandoc;" + $env:PATH
+          tesseract --version
+          pandoc --version
+
+      - name: Run Tests
+        run: uv run pytest -s -vvv

kreuzberg-3.4.0/.github/workflows/pr-title.yaml

@@ -0,0 +1,20 @@
+name: "Check PR Title"
+
+on:
+  pull_request_target:
+    types:
+      - opened
+      - edited
+      - synchronize
+
+permissions:
+  pull-requests: read
+
+jobs:
+  main:
+    name: Validate PR title
+    runs-on: ubuntu-latest
+    steps:
+      - uses: amannn/action-semantic-pull-request@v5
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

kreuzberg-3.4.0/.github/workflows/publish-docker.yml

@@ -0,0 +1,101 @@
+# .github/workflows/publish-docker.yml
+
+name: Publish Docker Images
+
+on:
+  workflow_run:
+    workflows: ["Release"]
+    types:
+      - completed
+    branches:
+      - main
+
+jobs:
+  build-and-push:
+    runs-on: ubuntu-latest
+    if: ${{ github.event.workflow_run.conclusion == 'success' }}
+    permissions:
+      contents: read
+      packages: write
+
+    strategy:
+      matrix:
+        include:
+          - name: core
+            extras: ""
+            tag_suffix: "" # The base image tag (includes API + tesseract)
+          - name: easyocr
+            extras: "easyocr"
+            tag_suffix: "-easyocr"
+          - name: paddle
+            extras: "paddleocr"
+            tag_suffix: "-paddle"
+          - name: gmft
+            extras: "gmft"
+            tag_suffix: "-gmft"
+          - name: all
+            extras: "all"
+            tag_suffix: "-all"
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ github.event.workflow_run.head_branch }}
+
+      - name: Get release version
+        id: get_version
+        run: |
+          echo "VERSION=${{ github.event.workflow_run.head_branch }}" >> $GITHUB_OUTPUT
+          # If triggered by a tag, extract version
+          if [[ "${{ github.event.workflow_run.head_branch }}" =~ ^v[0-9]+\.[0-9]+\.[0-9]+ ]]; then
+            echo "VERSION=${{ github.event.workflow_run.head_branch }}" >> $GITHUB_OUTPUT
+          else
+            # Get the latest tag
+            git fetch --tags
+            echo "VERSION=$(git describe --tags --abbrev=0)" >> $GITHUB_OUTPUT
+          fi
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Log in to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Extract metadata (tags, labels) for Docker
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: goldziher/kreuzberg
+          tags: |
+            # Release version tag (e.g., v3.0.0-easyocr)
+            type=raw,value=${{ steps.get_version.outputs.VERSION }}${{ matrix.tag_suffix }}
+            # Latest tag for each variant (e.g., latest-easyocr)
+            type=raw,value=latest${{ matrix.tag_suffix }}
+
+      - name: Build and push Docker image
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          file: ./.docker/Dockerfile
+          platforms: linux/amd64,linux/arm64
+          push: true
+          build-args: |
+            EXTRAS=${{ matrix.extras }}
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
+
+      - name: Update Docker Hub README
+        uses: peter-evans/dockerhub-description@v4
+        if: matrix.name == 'core'
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+          repository: goldziher/kreuzberg
+          readme-filepath: ./.docker/README.md

kreuzberg-3.4.0/.github/workflows/release.yaml

@@ -0,0 +1,31 @@
+name: Release
+
+on:
+  release:
+    types: [published]
+
+jobs:
+  release:
+    runs-on: ubuntu-latest
+    environment: pypi
+    permissions:
+      id-token: write
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v6
+        with:
+          enable-cache: true
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version-file: "pyproject.toml"
+
+      - name: Install Dependencies
+        run: uv build
+
+      - name: Publish
+        uses: pypa/gh-action-pypi-publish@release/v1

kreuzberg-3.4.0/.gitignore

@@ -0,0 +1,34 @@
+*$py.class
+*.Cache
+*.cscfg
+*.egg-info/
+*.log
+*.py[cod]
+*.suo
+*.user
+*temp/
+.coverage
+.coverage*
+.cursorrules
+.dist/
+.DS_store
+.env
+.idea/
+.kreuzberg/
+.mypy_cache/
+.pytest_cache/
+.python-version
+.ropeproject
+.ruff_cache/
+.run/
+.venv/
+.vscode/
+.windsurfrules
+__pycache__/
+benchmark_results.json
+CLAUDE.md
+coverage.xml
+docker-compose.yaml
+GEMINI.md
+prompt_template.egg-info/
+requirements.txt

kreuzberg-3.4.0/.markdownlint.yaml

@@ -0,0 +1,17 @@
+default: true
+
+MD007:
+  indent: 4
+
+MD033: false
+
+MD041: false
+
+MD013: false
+
+MD014: false
+
+MD024:
+  siblings_only: true
+
+MD046: false

kreuzberg-3.4.0/.pre-commit-config.yaml

@@ -0,0 +1,86 @@
+repos:
+  - repo: https://github.com/alessandrojcm/commitlint-pre-commit-hook
+    rev: "v9.22.0"
+    hooks:
+      - id: commitlint
+        stages: [commit-msg]
+        additional_dependencies: ["@commitlint/config-conventional"]
+  - repo: https://github.com/Goldziher/ai-rulez
+    rev: v1.1.2
+    hooks:
+      - id: ai-rulez-validate
+      - id: ai-rulez-generate
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v5.0.0
+    hooks:
+      - id: name-tests-test
+        args:
+          - --pytest
+        exclude: factories|test_utils|completion.py|test_data
+      - id: trailing-whitespace
+      - id: end-of-file-fixer
+      - id: check-toml
+      - id: check-case-conflict
+      - id: detect-private-key
+  - repo: https://github.com/abravalheri/validate-pyproject
+    rev: v0.24.1
+    hooks:
+      - id: validate-pyproject
+  - repo: https://github.com/executablebooks/mdformat
+    rev: 0.7.22
+    hooks:
+      - id: mdformat
+        additional_dependencies:
+          - mdformat-mkdocs==4.0.0
+  - repo: https://github.com/igorshubovych/markdownlint-cli
+    rev: v0.45.0
+    hooks:
+      - id: markdownlint-fix
+  - repo: https://github.com/adamchainz/blacken-docs
+    rev: 1.19.1
+    hooks:
+      - id: blacken-docs
+        args: ["--pyi", "--line-length", "130"]
+        additional_dependencies:
+          - black==25.1.0
+  - repo: https://github.com/rbubley/mirrors-prettier
+    rev: "v3.6.2"
+    hooks:
+      - id: prettier
+        exclude: ^tests|^.idea|^migrations|^.git|README.md|^docs
+  - repo: https://github.com/tox-dev/pyproject-fmt
+    rev: "v2.6.0"
+    hooks:
+      - id: pyproject-fmt
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.12.1
+    hooks:
+      - id: ruff
+        args: ["--fix", "--unsafe-fixes"]
+      - id: ruff-format
+  - repo: https://github.com/codespell-project/codespell
+    rev: v2.4.1
+    hooks:
+      - id: codespell
+        exclude: ^tests|^scripts|^kreuzberg/_tesseract|^kreuzberg/_mime_types
+        additional_dependencies:
+          - tomli
+  - repo: https://github.com/jsh9/pydoclint
+    rev: 0.6.7
+    hooks:
+      - id: pydoclint
+        args:
+          [
+            --style=google,
+            --check-return-types=False,
+            --arg-type-hints-in-docstring=False,
+          ]
+        exclude: ^benchmarks/|^kreuzberg/_|^tests/|^scripts/|^run_benchmarks\.py
+  - repo: local
+    hooks:
+      - id: mypy
+        name: mypy
+        entry: uv run mypy
+        require_serial: true
+        language: system
+        types: [python]