code2logic 1.0.0__tar.gz → 1.0.1__tar.gz

{code2logic-1.0.0 → code2logic-1.0.1}/.gitignore

@@ -1,3 +1,6 @@
+examples/reproduction/*
+examples/output/*
+bdd_output/*
 .idea
 # Byte-compiled / optimized / DLL files
 __pycache__/

{code2logic-1.0.0 → code2logic-1.0.1}/CHANGELOG.md

@@ -7,6 +7,16 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [1.0.1] - 2026-01-03
+
+### Changed
+- Improved benchmark robustness and artifact hygiene in example scripts.
+- Added packaging tools to development extras.
+
+### Fixed
+- Cleaned and hardened benchmark output generation (atomic writes, cleanup of generated artifacts).
+- Improved error reporting in benchmarking and function reproduction examples.
+
 ### Added
 - Initial release of code2logic
 - Multi-language code analysis support (Python, JavaScript, Java, C/C++)

{code2logic-1.0.0 → code2logic-1.0.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: code2logic
-Version: 1.0.0
+Version: 1.0.1
 Summary: Convert source code to logical representation for LLM analysis
 Project-URL: Homepage, https://github.com/softreck/code2logic
 Project-URL: Documentation, https://code2logic.readthedocs.io
@@ -30,11 +30,13 @@ Classifier: Typing :: Typed
 Requires-Python: >=3.9
 Provides-Extra: dev
 Requires-Dist: black>=23.0; extra == 'dev'
+Requires-Dist: build>=1.0.0; extra == 'dev'
 Requires-Dist: mypy>=1.0; extra == 'dev'
 Requires-Dist: pre-commit>=3.0; extra == 'dev'
 Requires-Dist: pytest-cov>=4.0; extra == 'dev'
 Requires-Dist: pytest>=7.0; extra == 'dev'
 Requires-Dist: ruff>=0.1.0; extra == 'dev'
+Requires-Dist: twine>=4.0.0; extra == 'dev'
 Provides-Extra: docs
 Requires-Dist: mkdocs-material>=9.0; extra == 'docs'
 Requires-Dist: mkdocs>=1.5; extra == 'docs'
@@ -306,6 +308,39 @@ black code2logic
 
 Compact format is ~10-15x smaller than Markdown.
 
+## 🔬 Code Reproduction Benchmarks
+
+Code2Logic can reproduce code from specifications using LLMs. Benchmark results:
+
+### Format Comparison (Token Efficiency)
+
+| Format | Score | Token Efficiency | Spec Tokens | Runs OK |
+|--------|-------|------------------|-------------|---------|
+| **YAML** | **71.1%** | 42.1 | **366** | 66.7% |
+| **Markdown** | 65.6% | **48.7** | 385 | **100%** |
+| JSON | 61.9% | 23.7 | 605 | 66.7% |
+| Gherkin | 51.3% | 19.1 | 411 | 66.7% |
+
+### Key Findings
+
+- **YAML is best for score** - 71.1% reproduction accuracy
+- **Markdown is best for token efficiency** - 48.7 score/1000 tokens
+- **YAML uses 39.6% fewer tokens than JSON** with 9.2% higher score
+- **Markdown has 100% runs OK** - generated code always executes
+
+### Run Benchmarks
+
+```bash
+# Token-aware benchmark
+python examples/11_token_benchmark.py --folder tests/samples/
+
+# Async multi-format benchmark
+python examples/09_async_benchmark.py --folder tests/samples/
+
+# Function-level reproduction
+python examples/10_function_reproduction.py --multi-lang
+```
+
 ## 🤝 Contributing
 
 Contributions welcome! Please read our [Contributing Guide](CONTRIBUTING.md).
@@ -314,6 +349,11 @@ Contributions welcome! Please read our [Contributing Guide](CONTRIBUTING.md).
 
 MIT License - see [LICENSE](LICENSE) for details.
 
+## 📚 Documentation
+
+- [API Documentation](DOCS.md) - Complete API reference
+- [Refactoring Plan](TODO.md) - Development roadmap
+
 ## 🔗 Links
 
 - [Documentation](https://code2logic.readthedocs.io)

{code2logic-1.0.0 → code2logic-1.0.1}/README.md

@@ -240,6 +240,39 @@ black code2logic
 
 Compact format is ~10-15x smaller than Markdown.
 
+## 🔬 Code Reproduction Benchmarks
+
+Code2Logic can reproduce code from specifications using LLMs. Benchmark results:
+
+### Format Comparison (Token Efficiency)
+
+| Format | Score | Token Efficiency | Spec Tokens | Runs OK |
+|--------|-------|------------------|-------------|---------|
+| **YAML** | **71.1%** | 42.1 | **366** | 66.7% |
+| **Markdown** | 65.6% | **48.7** | 385 | **100%** |
+| JSON | 61.9% | 23.7 | 605 | 66.7% |
+| Gherkin | 51.3% | 19.1 | 411 | 66.7% |
+
+### Key Findings
+
+- **YAML is best for score** - 71.1% reproduction accuracy
+- **Markdown is best for token efficiency** - 48.7 score/1000 tokens
+- **YAML uses 39.6% fewer tokens than JSON** with 9.2% higher score
+- **Markdown has 100% runs OK** - generated code always executes
+
+### Run Benchmarks
+
+```bash
+# Token-aware benchmark
+python examples/11_token_benchmark.py --folder tests/samples/
+
+# Async multi-format benchmark
+python examples/09_async_benchmark.py --folder tests/samples/
+
+# Function-level reproduction
+python examples/10_function_reproduction.py --multi-lang
+```
+
 ## 🤝 Contributing
 
 Contributions welcome! Please read our [Contributing Guide](CONTRIBUTING.md).
@@ -248,6 +281,11 @@ Contributions welcome! Please read our [Contributing Guide](CONTRIBUTING.md).
 
 MIT License - see [LICENSE](LICENSE) for details.
 
+## 📚 Documentation
+
+- [API Documentation](DOCS.md) - Complete API reference
+- [Refactoring Plan](TODO.md) - Development roadmap
+
 ## 🔗 Links
 
 - [Documentation](https://code2logic.readthedocs.io)

code2logic-1.0.1/code2logic/__init__.py

@@ -0,0 +1,265 @@
+"""
+Code2Logic - Convert source code to logical representation for LLM analysis.
+
+A Python library that analyzes codebases and generates compact, LLM-friendly
+representations with semantic understanding using NLP and AST parsing.
+
+Features:
+- Multi-language support (Python, JavaScript, TypeScript, Java, Go, Rust, etc.)
+- Tree-sitter AST parsing for 99% accuracy
+- NetworkX dependency graph analysis with PageRank
+- Rapidfuzz similarity detection for duplicate functions
+- NLP-powered intent extraction from function names and docstrings
+
+Example:
+    >>> from code2logic import analyze_project, MarkdownGenerator
+    >>> project = analyze_project("/path/to/project")
+    >>> output = MarkdownGenerator().generate(project)
+    >>> print(output)
+"""
+
+__version__ = "1.0.1"
+__author__ = "Softreck"
+__email__ = "info@softreck.dev"
+__license__ = "MIT"
+
+from .analyzer import (
+    ProjectAnalyzer,
+    analyze_project,
+)
+from .models import (
+    FunctionInfo,
+    ClassInfo,
+    TypeInfo,
+    ModuleInfo,
+    DependencyNode,
+    ProjectInfo,
+)
+from .generators import (
+    MarkdownGenerator,
+    CompactGenerator,
+    JSONGenerator,
+    YAMLGenerator,
+    CSVGenerator,
+)
+from .gherkin import (
+    GherkinGenerator,
+    StepDefinitionGenerator,
+    CucumberYAMLGenerator,
+    csv_to_gherkin,
+    gherkin_to_test_data,
+)
+from .intent import EnhancedIntentGenerator
+from .parsers import TreeSitterParser, UniversalParser
+from .dependency import DependencyAnalyzer
+from .similarity import SimilarityDetector
+from .config import Config, load_env, get_api_key, get_model
+from .llm_clients import (
+    BaseLLMClient,
+    OpenRouterClient,
+    OllamaLocalClient,
+    LiteLLMClient,
+    get_client,
+)
+from .reproduction import (
+    generate_file_gherkin,
+    compare_code,
+    extract_code_block,
+    CodeReproducer,
+)
+from .code_review import (
+    analyze_code_quality,
+    check_security_issues,
+    check_performance_issues,
+    CodeReviewer,
+)
+from .benchmark import (
+    ReproductionBenchmark,
+    run_benchmark,
+    FormatResult,
+    BenchmarkResult,
+)
+from .file_formats import (
+    generate_file_csv,
+    generate_file_json,
+    generate_file_yaml,
+)
+from .adaptive import (
+    AdaptiveReproducer,
+    AdaptiveResult,
+    get_llm_capabilities,
+    LLM_CAPABILITIES,
+)
+from .universal import (
+    UniversalReproducer,
+    UniversalParser,
+    CodeGenerator,
+    CodeLogic,
+    CodeElement,
+    Language,
+    ElementType,
+    reproduce_file,
+)
+from .project_reproducer import (
+    ProjectReproducer,
+    ProjectResult,
+    FileResult,
+    reproduce_project,
+)
+from .refactor import (
+    find_duplicates,
+    analyze_quality,
+    suggest_refactoring,
+    compare_codebases,
+    quick_analyze,
+    RefactoringReport,
+    DuplicateGroup,
+)
+from .metrics import (
+    ReproductionMetrics,
+    ReproductionResult,
+    TextMetrics,
+    StructuralMetrics,
+    SemanticMetrics,
+    FormatMetrics,
+    analyze_reproduction,
+    compare_formats,
+)
+from .base import (
+    VerboseMixin,
+    BaseParser,
+    BaseGenerator,
+)
+from .markdown_format import (
+    MarkdownHybridGenerator,
+    MarkdownSpec,
+    generate_markdown_hybrid,
+)
+from .logicml import (
+    LogicMLGenerator,
+    LogicMLSpec,
+    generate_logicml,
+)
+from .prompts import (
+    FORMAT_HINTS,
+    get_reproduction_prompt,
+    get_review_prompt,
+    get_fix_prompt,
+)
+from .chunked_reproduction import (
+    ChunkedReproducer,
+    ChunkedResult,
+    ChunkedSpec,
+    Chunk,
+    chunk_spec,
+    auto_chunk_reproduce,
+    get_llm_limit,
+)
+
+__all__ = [
+    # Version
+    "__version__",
+    # Main API
+    "analyze_project",
+    "ProjectAnalyzer",
+    # Models
+    "FunctionInfo",
+    "ClassInfo", 
+    "TypeInfo",
+    "ModuleInfo",
+    "DependencyNode",
+    "ProjectInfo",
+    # Generators
+    "MarkdownGenerator",
+    "CompactGenerator",
+    "JSONGenerator",
+    "YAMLGenerator",
+    "CSVGenerator",
+    # Gherkin/BDD
+    "GherkinGenerator",
+    "StepDefinitionGenerator",
+    "CucumberYAMLGenerator",
+    "csv_to_gherkin",
+    "gherkin_to_test_data",
+    # Components
+    "EnhancedIntentGenerator",
+    "TreeSitterParser",
+    "UniversalParser",
+    "DependencyAnalyzer",
+    "SimilarityDetector",
+    # Configuration
+    "Config",
+    "load_env",
+    "get_api_key",
+    "get_model",
+    # LLM Clients
+    "BaseLLMClient",
+    "OpenRouterClient",
+    "OllamaLocalClient",
+    "LiteLLMClient",
+    "get_client",
+    # Reproduction
+    "generate_file_gherkin",
+    "compare_code",
+    "extract_code_block",
+    "CodeReproducer",
+    # Code Review
+    "analyze_code_quality",
+    "check_security_issues",
+    "check_performance_issues",
+    "CodeReviewer",
+    # Benchmark
+    "ReproductionBenchmark",
+    "run_benchmark",
+    "FormatResult",
+    "BenchmarkResult",
+    # File Formats
+    "generate_file_csv",
+    "generate_file_json",
+    "generate_file_yaml",
+    # Adaptive
+    "AdaptiveReproducer",
+    "AdaptiveResult",
+    "get_llm_capabilities",
+    "LLM_CAPABILITIES",
+    # Universal
+    "UniversalReproducer",
+    "UniversalParser",
+    "CodeGenerator",
+    "CodeLogic",
+    "CodeElement",
+    "Language",
+    "ElementType",
+    "reproduce_file",
+    # Project
+    "ProjectReproducer",
+    "ProjectResult",
+    "FileResult",
+    "reproduce_project",
+    # Refactoring
+    "find_duplicates",
+    "analyze_quality",
+    "suggest_refactoring",
+    "compare_codebases",
+    "quick_analyze",
+    "RefactoringReport",
+    "DuplicateGroup",
+    # Metrics
+    "ReproductionMetrics",
+    "ReproductionResult",
+    "TextMetrics",
+    "StructuralMetrics",
+    "SemanticMetrics",
+    "FormatMetrics",
+    "analyze_reproduction",
+    "compare_formats",
+    # Base
+    "VerboseMixin",
+    "BaseParser",
+    "BaseGenerator",
+    # Markdown Format
+    "MarkdownHybridGenerator",
+    "MarkdownSpec",
+    "generate_markdown_hybrid",
+    "generate_file_markdown",
+]

code2logic-1.0.1/code2logic/__main__.py

@@ -0,0 +1,12 @@
+"""
+Allow running code2logic as a module: python -m code2logic
+
+Usage:
+    python -m code2logic /path/to/project
+    python -m code2logic /path/to/project -f gherkin -o tests.feature
+"""
+
+from .cli import main
+
+if __name__ == '__main__':
+    main()