kreuzberg 3.13.2__tar.gz → 3.13.3__tar.gz

{kreuzberg-3.13.2 → kreuzberg-3.13.3}/.github/workflows/ci.yaml

@@ -23,7 +23,7 @@ jobs:
           enable-cache: true
 
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
           python-version-file: "pyproject.toml"
 
@@ -54,7 +54,7 @@ jobs:
   coverage:
     needs: validate
     runs-on: ubuntu-latest
-    timeout-minutes: 20
+    timeout-minutes: 120
     steps:
       - name: Checkout
         uses: actions/checkout@v5
@@ -65,7 +65,7 @@ jobs:
           enable-cache: true
 
       - name: Install Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         id: setup-python
         with:
           python-version: "3.13"
@@ -142,7 +142,7 @@ jobs:
       matrix:
         os: [ubuntu-latest, windows-latest, macos-latest]
         python: ["3.10", "3.11", "3.12", "3.13"]
-    timeout-minutes: 30
+    timeout-minutes: 120
     steps:
       - name: Checkout
         uses: actions/checkout@v5
@@ -153,7 +153,7 @@ jobs:
           enable-cache: true
 
       - name: Install Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         id: setup-python
         with:
           python-version: ${{ matrix.python }}

{kreuzberg-3.13.2 → kreuzberg-3.13.3}/.github/workflows/docker-e2e-tests.yml

@@ -25,7 +25,7 @@ jobs:
           enable-cache: true
 
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
           python-version-file: "pyproject.toml"
 
@@ -48,7 +48,6 @@ jobs:
           sudo rm -rf /opt/ghc
           sudo rm -rf /opt/hostedtoolcache/CodeQL
           sudo rm -rf /usr/local/share/boost
-          sudo rm -rf "$AGENT_TOOLSDIRECTORY"
 
           sudo apt-get clean
           sudo apt-get autoremove -y

{kreuzberg-3.13.2 → kreuzberg-3.13.3}/.github/workflows/docs.yml

@@ -29,7 +29,7 @@ jobs:
           fetch-depth: 0
 
       - name: Setup Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
           python-version: '3.11'
 

{kreuzberg-3.13.2 → kreuzberg-3.13.3}/.github/workflows/publish-docker.yml

@@ -62,7 +62,6 @@ jobs:
           sudo rm -rf /usr/local/lib/node_modules
           sudo rm -rf /opt/microsoft
           sudo rm -rf /usr/local/.ghcup
-          sudo rm -rf /opt/hostedtoolcache
 
           # Clean apt
           sudo apt-get clean

{kreuzberg-3.13.2 → kreuzberg-3.13.3}/.github/workflows/release.yaml

@@ -21,7 +21,7 @@ jobs:
           enable-cache: true
 
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
           python-version-file: "pyproject.toml"
 

{kreuzberg-3.13.2 → kreuzberg-3.13.3}/.gitignore

@@ -66,3 +66,6 @@ yarn-error.log*
 *.tmp
 *.temp
 .tmp/
+
+# AI Rules generated files
+.claude/agents/

{kreuzberg-3.13.2 → kreuzberg-3.13.3}/.pre-commit-config.yaml

@@ -5,11 +5,12 @@ repos:
       - id: commitlint
         stages: [commit-msg]
         additional_dependencies: ["@commitlint/config-conventional"]
-  - repo: https://github.com/Goldziher/ai-rulez
-    rev: v1.6.1
-    hooks:
-      - id: ai-rulez-validate
-      - id: ai-rulez-generate
+  # Temporarily disabled due to CI environment issues
+  # - repo: https://github.com/Goldziher/ai-rulez
+  #   rev: v2.0.1
+  #   hooks:
+  #     - id: ai-rulez-validate
+  #     - id: ai-rulez-generate
   - repo: https://github.com/pre-commit/pre-commit-hooks
     rev: v6.0.0
     hooks:
@@ -37,7 +38,7 @@ repos:
     hooks:
       - id: markdownlint-fix
   - repo: https://github.com/adamchainz/blacken-docs
-    rev: 1.19.1
+    rev: 1.20.0
     hooks:
       - id: blacken-docs
         args: ["--pyi", "--line-length", "130"]
@@ -53,7 +54,7 @@ repos:
     hooks:
       - id: pyproject-fmt
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.12.11
+    rev: v0.12.12
     hooks:
       - id: ruff
         args: ["--fix", "--unsafe-fixes"]

{kreuzberg-3.13.2 → kreuzberg-3.13.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: kreuzberg
-Version: 3.13.2
+Version: 3.13.3
 Summary: Document intelligence framework for Python - Extract text, metadata, and structured data from diverse file formats
 Project-URL: documentation, https://kreuzberg.dev
 Project-URL: homepage, https://github.com/Goldziher/kreuzberg
@@ -31,15 +31,15 @@ Requires-Python: >=3.10
 Requires-Dist: anyio>=4.10.0
 Requires-Dist: chardetng-py>=0.3.5
 Requires-Dist: exceptiongroup>=1.2.2; python_version < '3.11'
-Requires-Dist: html-to-markdown[lxml]>=1.9.1
+Requires-Dist: html-to-markdown[lxml]>=1.10.0
 Requires-Dist: mcp>=1.13.0
 Requires-Dist: msgspec>=0.18.0
 Requires-Dist: numpy>=1.24.0
 Requires-Dist: playa-pdf>=0.7.0
-Requires-Dist: polars>=1.33.0
+Requires-Dist: polars>=1.33.1
 Requires-Dist: psutil>=7.0.0
 Requires-Dist: pypdfium2==4.30.0
-Requires-Dist: python-calamine>=0.5.2
+Requires-Dist: python-calamine>=0.5.3
 Requires-Dist: python-pptx>=1.0.2
 Requires-Dist: typing-extensions>=4.15.0; python_version < '3.12'
 Provides-Extra: additional-extensions
@@ -55,17 +55,17 @@ Requires-Dist: keybert>=0.9.0; extra == 'all'
 Requires-Dist: litestar[opentelemetry,standard,structlog]>=2.17.0; extra == 'all'
 Requires-Dist: mailparse>=1.0.15; extra == 'all'
 Requires-Dist: paddleocr>=3.2.0; extra == 'all'
-Requires-Dist: paddlepaddle>=3.1.1; extra == 'all'
+Requires-Dist: paddlepaddle>=3.2.0; extra == 'all'
 Requires-Dist: playa-pdf[crypto]>=0.7.0; extra == 'all'
 Requires-Dist: rich>=14.1.0; extra == 'all'
-Requires-Dist: semantic-text-splitter>=0.27.0; extra == 'all'
+Requires-Dist: semantic-text-splitter>=0.28.0; extra == 'all'
 Requires-Dist: setuptools>=80.9.0; extra == 'all'
 Requires-Dist: spacy>=3.8.7; extra == 'all'
 Requires-Dist: tomli>=2.0.0; (python_version < '3.11') and extra == 'all'
 Provides-Extra: api
 Requires-Dist: litestar[opentelemetry,standard,structlog]>=2.17.0; extra == 'api'
 Provides-Extra: chunking
-Requires-Dist: semantic-text-splitter>=0.27.0; extra == 'chunking'
+Requires-Dist: semantic-text-splitter>=0.28.0; extra == 'chunking'
 Provides-Extra: cli
 Requires-Dist: click>=8.2.1; extra == 'cli'
 Requires-Dist: rich>=14.1.0; extra == 'cli'
@@ -85,7 +85,7 @@ Provides-Extra: langdetect
 Requires-Dist: fast-langdetect>=0.3.2; extra == 'langdetect'
 Provides-Extra: paddleocr
 Requires-Dist: paddleocr>=3.2.0; extra == 'paddleocr'
-Requires-Dist: paddlepaddle>=3.1.1; extra == 'paddleocr'
+Requires-Dist: paddlepaddle>=3.2.0; extra == 'paddleocr'
 Requires-Dist: setuptools>=80.9.0; extra == 'paddleocr'
 Description-Content-Type: text/markdown
 

{kreuzberg-3.13.2 → kreuzberg-3.13.3}/ai-rulez.yaml

@@ -1,115 +1,8 @@
-metadata:
-  name: "Kreuzberg"
-  version: "3.5.0"
-  description: "A text extraction library supporting PDFs, images, office documents and more"
-
-targets:
-  claude-files:
-    - "CLAUDE.md"
-    - ".claude/**/*.md"
-
-  cursor-files:
-    - ".cursorrules"
-
-  windsurf-files:
-    - ".windsurfrules"
-
-  gemini-files:
-    - "GEMINI.md"
-
-outputs:
-  - file: "CLAUDE.md"
-    template: |
-      # CLAUDE.md
-
-      This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
-
-      ## Project Overview
-
-      {{ .Description }}
-
-      {{ range .Rules }}
-      ## {{ .Name }}
-      {{ .Content }}
-      {{ end }}
-
-      {{ range .Sections }}
-      ## {{ .Title }}
-      {{ .Content }}
-      {{ end }}
-
-  - file: "GEMINI.md"
-    template: |
-      # GEMINI.md
-
-      This file provides guidance to Gemini when working with code in this repository.
-
-      ## Project Overview
-
-      {{ .Description }}
-
-      {{ range .Rules }}
-      ## {{ .Name }}
-      {{ .Content }}
-      {{ end }}
-
-      {{ range .Sections }}
-      ## {{ .Title }}
-      {{ .Content }}
-      {{ end }}
-
-  - file: ".cursorrules"
-    template: |
-      # Kreuzberg
-      A text extraction library supporting PDFs, images, office documents and more
-
-      {{ range .Rules }}
-      ## {{ .Name }}
-      {{ .Content }}
-      {{ end }}
-
-      {{ range .Sections }}
-      ## {{ .Title }}
-      {{ .Content }}
-      {{ end }}
-
-  - file: ".windsurfrules"
-    template: |
-      # Kreuzberg
-      A text extraction library supporting PDFs, images, office documents and more
-
-      {{ range .Rules }}
-      ## {{ .Name }}
-      {{ .Content }}
-      {{ end }}
-
-      {{ range .Sections }}
-      ## {{ .Title }}
-      {{ .Content }}
-      {{ end }}
-
-  - path: ".claude/agents/"
-    type: "agent"
-    naming_scheme: "{priority:02d}-{name}.md"
-    template: |
-      # Agent: {{ .Name }}
-
-      **Description**: {{ .Description }}
-      **Priority**: {{ .Priority }}
-
-      ## Tools Available
-      {{ range .Tools }}
-      - {{ . }}
-      {{ end }}
-
-      ## System Prompt
-      {{ .SystemPrompt }}
-
 agents:
-  - name: "python-engineer"
-    description: "Expert Python developer for implementing features and fixing bugs"
-    priority: 10
-    targets: ["@claude-files"]
+  - description: Expert Python developer for implementing features and fixing bugs
+    id: python-engineer
+    name: python-engineer
+    priority: critical
     system_prompt: |
       You are an expert Python engineer specializing in the Kreuzberg text extraction library.
 
@@ -138,11 +31,13 @@ agents:
       - ALWAYS prefer editing existing files
       - All builtin imports at top level (except cyclical/optional)
       - Maintain 95% test coverage requirement
-
-  - name: "test-engineer"
-    description: "Writes comprehensive tests for kreuzberg functionality"
-    priority: 9
-    targets: ["@claude-files"]
+    targets:
+      - CLAUDE.md
+      - .claude/**/*.md
+  - description: Writes comprehensive tests for kreuzberg functionality
+    id: test-engineer
+    name: test-engineer
+    priority: high
     system_prompt: |
       You are a test automation expert for the Kreuzberg text extraction library.
 
@@ -173,16 +68,13 @@ agents:
       - Use descriptive names that explain what's being tested
 
       Always ensure tests are isolated, repeatable, and fast.
-
-  - name: "code-reviewer"
-    description: "Reviews code for quality, security, and compliance"
-    priority: 10
-    targets: ["@claude-files"]
-    tools:
-      - "Read"
-      - "Grep"
-      - "Glob"
-      - "LS"
+    targets:
+      - CLAUDE.md
+      - .claude/**/*.md
+  - description: Reviews code for quality, security, and compliance
+    id: code-reviewer
+    name: code-reviewer
+    priority: critical
     system_prompt: |
       You are a senior code reviewer for the Kreuzberg text extraction library.
 
@@ -231,11 +123,18 @@ agents:
 
       Provide specific, actionable feedback with code examples when relevant.
       Rate severity: Critical, High, Medium, Low.
-
-  - name: "infra-engineer"
-    description: "Manages infrastructure, CI/CD, Docker, and deployment configurations"
-    priority: 9
-    targets: ["@claude-files"]
+    targets:
+      - CLAUDE.md
+      - .claude/**/*.md
+    tools:
+      - Read
+      - Grep
+      - Glob
+      - LS
+  - description: Manages infrastructure, CI/CD, Docker, and deployment configurations
+    id: infra-engineer
+    name: infra-engineer
+    priority: high
     system_prompt: |
       You are an infrastructure and DevOps engineer for the Kreuzberg text extraction library.
 
@@ -300,11 +199,13 @@ agents:
       - Security first approach
       - Resource optimization
       - Clear documentation
-
-  - name: "performance-optimizer"
-    description: "Optimizes performance and resource usage"
-    priority: 8
-    targets: ["@claude-files"]
+    targets:
+      - CLAUDE.md
+      - .claude/**/*.md
+  - description: Optimizes performance and resource usage
+    id: performance-optimizer
+    name: performance-optimizer
+    priority: medium
     system_prompt: |
       You are a performance optimization specialist for the Kreuzberg text extraction library.
 
@@ -349,11 +250,108 @@ agents:
       Always measure before and after optimization.
       Focus on bottlenecks identified through profiling.
       Ensure optimizations don't break functionality or reduce code clarity.
-
+    targets:
+      - CLAUDE.md
+      - .claude/**/*.md
+metadata:
+  description: A text extraction library supporting PDFs, images, office documents and more
+  name: Kreuzberg
+  version: 3.5.0
+outputs:
+  - path: CLAUDE.md
+    template:
+      type: inline
+      value: |
+        # CLAUDE.md
+
+        This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
+
+        ## Project Overview
+
+        {{ .Description }}
+
+        {{ range .Rules }}
+        ## {{ .Name }}
+        {{ .Content }}
+        {{ end }}
+
+        {{ range .Sections }}
+        ## {{ .Name }}
+        {{ .Content }}
+        {{ end }}
+  - path: GEMINI.md
+    template:
+      type: inline
+      value: |
+        # GEMINI.md
+
+        This file provides guidance to Gemini when working with code in this repository.
+
+        ## Project Overview
+
+        {{ .Description }}
+
+        {{ range .Rules }}
+        ## {{ .Name }}
+        {{ .Content }}
+        {{ end }}
+
+        {{ range .Sections }}
+        ## {{ .Name }}
+        {{ .Content }}
+        {{ end }}
+  - path: .cursorrules
+    template:
+      type: inline
+      value: |
+        # Kreuzberg
+        A text extraction library supporting PDFs, images, office documents and more
+
+        {{ range .Rules }}
+        ## {{ .Name }}
+        {{ .Content }}
+        {{ end }}
+
+        {{ range .Sections }}
+        ## {{ .Name }}
+        {{ .Content }}
+        {{ end }}
+  - path: .windsurfrules
+    template:
+      type: inline
+      value: |
+        # Kreuzberg
+        A text extraction library supporting PDFs, images, office documents and more
+
+        {{ range .Rules }}
+        ## {{ .Name }}
+        {{ .Content }}
+        {{ end }}
+
+        {{ range .Sections }}
+        ## {{ .Name }}
+        {{ .Content }}
+        {{ end }}
+  - naming_scheme: "{priority:02d}-{name}.md"
+    path: .claude/agents/
+    template:
+      type: inline
+      value: |
+        # Agent: {{ .Name }}
+
+        **Description**: {{ .Description }}
+        **Priority**: {{ .Priority }}
+
+        ## Tools Available
+        {{ range .Tools }}
+        - {{ . }}
+        {{ end }}
+
+        ## System Prompt
+        {{ .SystemPrompt }}
+    type: agent
 rules:
-  - name: "Development Commands"
-    priority: 10
-    content: |
+  - content: |
       ### Dependencies
       - Install dependencies: `uv sync`
       - Install with all optional dependencies: `uv sync --all-extras`
@@ -378,10 +376,9 @@ rules:
       - Build docs: `uv run mkdocs build --clean --strict`
       - Serve docs locally: `uv run mkdocs serve`
       - Install doc dependencies: `uv sync --group doc`
-
-  - name: "Important Instructions"
-    priority: 10
-    content: |
+    name: Development Commands
+    priority: critical
+  - content: |
       - Do what has been asked; nothing more, nothing less
       - NEVER create files unless they're absolutely necessary for achieving your goal
       - ALWAYS prefer editing an existing file to creating a new one
@@ -389,10 +386,9 @@ rules:
       - Only create documentation files if explicitly requested by the User
       - All builtin imports should be at the top level (except for cyclical or optional dependencies)
       - When committing, always use the format specified in the CLAUDE.md
-
-  - name: "Architecture"
-    priority: 9
-    content: |
+    name: Important Instructions
+    priority: critical
+  - content: |
       ### Core Extraction Flow
       1. **Entry Point**: `extraction.py` provides main functions (`extract_file`, `extract_bytes`, etc.)
       2. **Registry Pattern**: `ExtractorRegistry` selects appropriate extractor based on MIME type
@@ -415,10 +411,9 @@ rules:
       - New OCR backends: Implement `BaseOCR` interface
       - Configuration options: Extend `ExtractionConfig` or create backend-specific configs
       - Hooks: Use `pre_validate_hook` and `post_extraction_hook` for custom processing
-
-  - name: "Error Handling"
-    priority: 8
-    content: |
+    name: Architecture
+    priority: high
+  - content: |
       - **Exception-based**: All errors are raised as exceptions, no tuple returns
       - **Base class**: All exceptions inherit from `KreuzbergError`
       - **Context**: Exceptions include a `context` parameter with debugging information
@@ -427,20 +422,18 @@ rules:
         - `ParsingError`: Document parsing failures
         - `OCRError`: OCR processing failures
         - `MissingDependencyError`: Missing optional dependencies
-
-  - name: "Testing Patterns"
-    priority: 7
-    content: |
+    name: Error Handling
+    priority: medium
+  - content: |
       - Test files in `tests/test_source_files/` for various formats
       - Mock OCR responses for predictable testing
       - Both sync and async test variants
       - Comprehensive error case coverage
       - OCR tests marked as `xfail` in CI environments for resilience
       - Integration tests use timeouts and retry logic where appropriate
-
-  - name: "CI/CD and Deployment"
-    priority: 6
-    content: |
+    name: Testing Patterns
+    priority: low
+  - content: |
       ### GitHub Actions Workflows
       - **Release**: Automated PyPI publishing via GitHub releases, triggers Docker builds
       - **Docker**: Multi-platform Docker builds (linux/amd64, linux/arm64), triggered by releases
@@ -462,10 +455,9 @@ rules:
       - **Docker version detection**: Use `git tag --sort=-version:refname | head -n1` not `git describe`
       - **Docs dependencies**: Use `uv sync --group doc` for proper mkdocs-material[imaging] support
       - **Docker Hub README**: May fail due to permissions, use `continue-on-error: true`
-
-  - name: "Package Management"
-    priority: 6
-    content: |
+    name: CI/CD and Deployment
+    priority: minimal
+  - content: |
       ### Optional Dependencies Structure
       ```toml
       [project.optional-dependencies]
@@ -499,10 +491,10 @@ rules:
       - **Usage**: Required for PDFs with AES encryption (RC4 is supported in base installation)
       - **Password Support**: Supports single password or list of passwords to try in sequence
       - **Size Impact**: Increases installation size by ~24MB due to cryptography package
-
+    name: Package Management
+    priority: minimal
 sections:
-  - title: "Language Detection"
-    content: |
+  - content: |
       ### Automatic Language Detection (v3.5.0+)
       - **Feature**: Automatically detect languages in extracted text
       - **Implementation**: Uses fast-langdetect library for high-performance detection
@@ -511,9 +503,9 @@ sections:
         - Configure via `LanguageDetectionConfig` for confidence thresholds
       - **Output**: Results available in `ExtractionResult.detected_languages`
       - **Integration**: Works with all extraction methods and file types
-
-  - title: "Planned Features"
-    content: |
+    id: language-detection
+    name: Language Detection
+  - content: |
       ### Structured Extraction (Issue #55)
       - **Goal**: Enable extraction of structured data from documents using vision models
       - **Implementation**:
@@ -522,3 +514,5 @@ sections:
         - Use LiteLLM for vision model integration
         - Implement retry logic with error feedback
       - **Configuration**: Currently programmatic only (no `kreuzberg.toml`)
+    id: planned-features
+    name: Planned Features