code2logic 1.0.7__tar.gz → 1.0.9__tar.gz

code2logic-1.0.9/PKG-INFO

@@ -0,0 +1,470 @@
+Metadata-Version: 2.3
+Name: code2logic
+Version: 1.0.9
+Summary: Convert source code to logical representation for LLM analysis
+License: Apache-2.0
+Keywords: code-analysis,llm,ast,static-analysis,tree-sitter,code-understanding,documentation,dependency-graph,nlp
+Author: Softreck
+Author-email: info@softreck.dev
+Maintainer: Softreck
+Maintainer-email: info@softreck.dev
+Requires-Python: >=3.9,<4.0
+Classifier: Development Status :: 4 - Beta
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Software Development :: Documentation
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Software Development :: Quality Assurance
+Classifier: Topic :: Text Processing :: Linguistic
+Classifier: Typing :: Typed
+Provides-Extra: full
+Provides-Extra: graph
+Provides-Extra: llm
+Provides-Extra: nlp
+Provides-Extra: similarity
+Provides-Extra: treesitter
+Requires-Dist: httpx (>=0.25.0) ; extra == "llm" or extra == "full"
+Requires-Dist: litellm (>=1.0.0) ; extra == "llm" or extra == "full"
+Requires-Dist: networkx (>=3.0) ; extra == "graph" or extra == "full"
+Requires-Dist: nltk (>=3.8) ; extra == "nlp" or extra == "full"
+Requires-Dist: pyyaml (>=6.0) ; extra == "full"
+Requires-Dist: rapidfuzz (>=3.0) ; extra == "similarity" or extra == "full"
+Requires-Dist: tree-sitter (>=0.21.0) ; extra == "treesitter" or extra == "full"
+Requires-Dist: tree-sitter-javascript (>=0.21.0) ; extra == "treesitter" or extra == "full"
+Requires-Dist: tree-sitter-python (>=0.21.0) ; extra == "treesitter" or extra == "full"
+Requires-Dist: tree-sitter-typescript (>=0.21.0) ; extra == "treesitter" or extra == "full"
+Project-URL: Changelog, https://github.com/wronai/code2logic/blob/main/CHANGELOG.md
+Project-URL: Documentation, https://code2logic.readthedocs.io
+Project-URL: Homepage, https://github.com/wronai/code2logic
+Project-URL: Issues, https://github.com/wronai/code2logic/issues
+Project-URL: Repository, https://github.com/wronai/code2logic.git
+Description-Content-Type: text/markdown
+
+# Code2Logic
+
+[![PyPI version](https://badge.fury.io/py/code2logic.svg)](https://badge.fury.io/py/code2logic)
+[![Python 3.9+](https://img.shields.io/badge/python-3.9+-blue.svg)](https://www.python.org/downloads/)
+[![License: Apache 2.0](https://img.shields.io/badge/License-Apache%202.0-yellow.svg)](https://www.apache.org/licenses/LICENSE-2.0)
+
+**Convert source code to logical representation for LLM analysis.**
+
+Code2Logic analyzes codebases and generates compact, LLM-friendly representations with semantic understanding.
+Perfect for feeding project context to AI assistants, building code documentation, or analyzing code structure.
+
+## ✨ Features
+
+- 🌳 **Multi-language support** - Python, JavaScript, TypeScript, Java, Go, Rust, and more
+- 🎯 **Tree-sitter AST parsing** - 99% accuracy with graceful fallback
+- 📊 **NetworkX dependency graphs** - PageRank, hub detection, cycle analysis
+- 🔍 **Rapidfuzz similarity** - Find duplicate and similar functions
+- 🧠 **NLP intent extraction** - Human-readable function descriptions
+- 📦 **Zero dependencies** - Core works without any external libs
+
+## 🚀 Installation
+
+### Basic (no dependencies)
+
+```bash
+pip install code2logic
+```
+
+### Full (all features)
+
+```bash
+pip install code2logic[full]
+```
+
+### Selective features
+
+```bash
+pip install code2logic[treesitter]  # High-accuracy AST parsing
+pip install code2logic[graph]       # Dependency analysis
+pip install code2logic[similarity]  # Similar function detection
+pip install code2logic[nlp]         # Enhanced intents
+```
+
+## 📖 Quick Start
+
+### Command Line
+
+```bash
+# Standard Markdown output
+code2logic /path/to/project
+
+# Compact YAML (14% smaller, meta.legend transparency)
+code2logic /path/to/project -f yaml --compact -o analysis-compact.yaml
+
+# Ultra-compact TOON (71% smaller, single-letter keys)
+code2logic /path/to/project -f toon --ultra-compact -o analysis-ultra.toon
+
+# Generate schema alongside output
+code2logic /path/to/project -f yaml --compact --with-schema
+
+# With detailed analysis
+code2logic /path/to/project -d detailed
+```
+
+### Python API
+
+```python
+from code2logic import analyze_project, MarkdownGenerator
+
+# Analyze a project
+project = analyze_project("/path/to/project")
+
+# Generate output
+generator = MarkdownGenerator()
+output = generator.generate(project, detail_level='standard')
+print(output)
+
+# Access analysis results
+print(f"Files: {project.total_files}")
+print(f"Lines: {project.total_lines}")
+print(f"Languages: {project.languages}")
+
+# Get hub modules (most important)
+hubs = [p for p, n in project.dependency_metrics.items() if n.is_hub]
+print(f"Key modules: {hubs}")
+```
+
+### Organized Imports
+
+```python
+# Core analysis
+from code2logic.core import ProjectInfo, ProjectAnalyzer, analyze_project
+
+# Format generators
+from code2logic.formats import (
+    YAMLGenerator, JSONGenerator, TOONGenerator,
+    LogicMLGenerator, GherkinGenerator
+)
+
+# LLM clients
+from code2logic.llm import get_client, BaseLLMClient
+
+# Development tools
+from code2logic.tools import run_benchmark, CodeReviewer
+```
+
+## 📋 Output Formats
+
+### Markdown (default)
+
+Human-readable documentation with:
+
+- Project structure tree with hub markers (★)
+- Dependency graphs with PageRank scores
+- Classes with methods and intents
+- Functions with signatures and descriptions
+
+### Compact
+
+Ultra-compact format optimized for LLM context:
+
+```text
+# myproject | 102f 31875L | typescript:79/python:23
+ENTRY: index.ts main.py
+HUBS: evolution-manager llm-orchestrator
+
+[core/evolution]
+  evolution-manager.ts (3719L) C:EvolutionManager | F:createEvolutionManager
+  task-queue.ts (139L) C:TaskQueue,Task
+```
+
+### JSON
+
+Machine-readable format for:
+
+- RAG (Retrieval-Augmented Generation)
+- Database storage
+- Further analysis
+
+## 🔧 Configuration
+
+### Library Status
+
+Check which features are available:
+
+```bash
+code2logic --status
+```
+
+```text
+Library Status:
+  tree_sitter: ✓
+  networkx: ✓
+  rapidfuzz: ✓
+  nltk: ✗
+  spacy: ✗
+```
+
+### LLM Configuration
+
+Manage LLM providers, models, API keys, and routing priorities:
+
+```bash
+code2logic llm status
+code2logic llm set-provider auto
+code2logic llm set-model openrouter nvidia/nemotron-3-nano-30b-a3b:free
+code2logic llm key set openrouter <OPENROUTER_API_KEY>
+code2logic llm priority set-provider openrouter 10
+code2logic llm priority set-mode provider-first
+code2logic llm priority set-llm-model nvidia/nemotron-3-nano-30b-a3b:free 5
+code2logic llm priority set-llm-family nvidia/ 5
+code2logic llm config list
+```
+
+Notes:
+
+- `code2logic llm set-provider auto` enables automatic fallback selection: providers are tried in priority order.
+- API keys should be stored in `.env` (or environment variables), not in `litellm_config.yaml`.
+- These commands write configuration files:
+  - `.env` in the current working directory
+  - `litellm_config.yaml` in the current working directory
+  - `~/.code2logic/llm_config.json` in your home directory
+
+#### Priority modes
+
+You can choose how automatic fallback ordering is computed:
+
+- `provider-first`
+  providers are ordered by provider priority (defaults + overrides)
+- `model-first`
+  providers are ordered by priority rules for the provider's configured model (exact/prefix)
+- `mixed`
+  providers are ordered by the best (lowest) priority from either provider priority or model rules
+
+Configure the mode:
+
+```bash
+code2logic llm priority set-mode provider-first
+code2logic llm priority set-mode model-first
+code2logic llm priority set-mode mixed
+```
+
+Model priority rules are stored in `~/.code2logic/llm_config.json`.
+
+### Python API (Library Status)
+
+```python
+from code2logic import get_library_status
+
+status = get_library_status()
+# {'tree_sitter': True, 'networkx': True, ...}
+```
+
+## 📊 Analysis Features
+
+### Dependency Analysis
+
+- **PageRank** - Identifies most important modules
+- **Hub detection** - Central modules marked with ★
+- **Cycle detection** - Find circular dependencies
+- **Clustering** - Group related modules
+
+### Intent Generation
+
+Functions get human-readable descriptions:
+
+```yaml
+methods:
+  async findById(id:string) -> Promise<User>  # retrieves user by id
+  async createUser(data:UserDTO) -> Promise<User>  # creates user
+  validateEmail(email:string) -> boolean  # validates email
+```
+
+### Similarity Detection
+
+Find duplicate and similar functions:
+
+```yaml
+Similar Functions:
+  core/auth.ts::validateToken:
+    - python/auth.py::validate_token (92%)
+    - services/jwt.ts::verifyToken (85%)
+```
+
+## 🏗️ Architecture
+
+```text
+code2logic/
+├── analyzer.py      # Main orchestrator
+├── parsers.py       # Tree-sitter + fallback parser
+├── dependency.py    # NetworkX dependency analysis
+├── similarity.py    # Rapidfuzz similar detection
+├── intent.py        # NLP intent generation
+├── generators.py    # Output generators (MD/Compact/JSON)
+├── models.py        # Data structures
+└── cli.py           # Command-line interface
+```
+
+## 🔌 Integration Examples
+
+### With Claude/ChatGPT
+
+```python
+from code2logic import analyze_project, CompactGenerator
+
+project = analyze_project("./my-project")
+context = CompactGenerator().generate(project)
+
+# Use in your LLM prompt
+prompt = f"""
+Analyze this codebase and suggest improvements:
+
+{context}
+"""
+```
+
+### With RAG Systems
+
+```python
+import json
+from code2logic import analyze_project, JSONGenerator
+
+project = analyze_project("./my-project")
+data = json.loads(JSONGenerator().generate(project))
+
+# Index in vector DB
+for module in data['modules']:
+    for func in module['functions']:
+        embed_and_store(
+            text=f"{func['name']}: {func['intent']}",
+            metadata={'path': module['path'], 'type': 'function'}
+        )
+```
+
+## 🧪 Development
+
+### Setup
+
+```bash
+git clone https://github.com/wronai/code2logic
+cd code2logic
+poetry install --with dev -E full
+poetry run pre-commit install
+
+# Alternatively, you can use Makefile targets (prefer Poetry if available)
+make install-full
+```
+
+### Tests
+
+```bash
+make test
+make test-cov
+
+# Or directly:
+poetry run pytest
+poetry run pytest --cov=code2logic --cov-report=html
+```
+
+### Type Checking
+
+```bash
+make typecheck
+
+# Or directly:
+poetry run mypy code2logic
+```
+
+### Linting
+
+```bash
+make lint
+make format
+
+# Or directly:
+poetry run ruff check code2logic
+poetry run black code2logic
+```
+
+## 📈 Performance
+
+| Codebase Size | Files | Lines | Time | Output Size |
+| --- | --- | --- | --- | --- |
+| Small | 10 | 1K | <1s | ~5KB |
+| Medium | 100 | 30K | ~2s | ~50KB |
+| Large | 500 | 150K | ~10s | ~200KB |
+
+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/ --no-llm
+
+# Async multi-format benchmark
+python examples/09_async_benchmark.py --folder tests/samples/ --no-llm
+
+# Function-level reproduction
+python examples/10_function_reproduction.py --file tests/samples/sample_functions.py --no-llm
+
+python examples/15_unified_benchmark.py --folder tests/samples/ --no-llm
+
+# Terminal markdown rendering demo
+python examples/16_terminal_demo.py --folder tests/samples/
+```
+
+## 🤝 Contributing
+
+Contributions welcome! Please read our [Contributing Guide](CONTRIBUTING.md).
+
+## 📄 License
+
+Apache 2 License - see [LICENSE](LICENSE) for details.
+
+## 📚 Documentation
+
+- [00 - Docs Index](docs/00-index.md) - Documentation home (start here)
+- [01 - Getting Started](docs/01-getting-started.md) - Install and first steps
+- [02 - Configuration](docs/02-configuration.md) - API keys, environment setup
+- [03 - CLI Reference](docs/03-cli-reference.md) - Command-line usage
+- [04 - Python API](docs/04-python-api.md) - Programmatic usage
+- [05 - Output Formats](docs/05-output-formats.md) - Format comparison and usage
+- [06 - Format Specifications](docs/06-format-specifications.md) - Detailed format specs
+- [07 - TOON Format](docs/07-toon.md) - Token-Oriented Object Notation
+- [08 - LLM Integration](docs/08-llm-integration.md) - OpenRouter/Ollama/LiteLLM
+- [09 - LLM Comparison](docs/09-llm-comparison-report.md) - Provider/model comparison
+- [10 - Benchmarking](docs/10-benchmark.md) - Benchmark methodology and results
+- [11 - Repeatability](docs/11-repeatability.md) - Repeatability testing
+- [12 - Examples](docs/12-examples.md) - Usage workflows and examples
+- [13 - Architecture](docs/13-architecture.md) - System design and components
+- [14 - Format Analysis](docs/14-format-analysis.md) - Deeper format evaluation
+
+## 🔗 Links
+
+- [Documentation](https://code2logic.readthedocs.io)
+- [PyPI](https://pypi.org/project/code2logic/)
+- [GitHub](https://github.com/wronai/code2logic)
+- [Issues](https://github.com/wronai/code2logic/issues)
+

{code2logic-1.0.7 → code2logic-1.0.9}/README.md

@@ -299,28 +299,42 @@ for module in data['modules']:
 ```bash
 git clone https://github.com/wronai/code2logic
 cd code2logic
-pip install -e ".[dev]"
-pre-commit install
+poetry install --with dev -E full
+poetry run pre-commit install
+
+# Alternatively, you can use Makefile targets (prefer Poetry if available)
+make install-full
 ```
 
 ### Tests
 
 ```bash
-pytest
-pytest --cov=code2logic --cov-report=html
+make test
+make test-cov
+
+# Or directly:
+poetry run pytest
+poetry run pytest --cov=code2logic --cov-report=html
 ```
 
 ### Type Checking
 
 ```bash
-mypy code2logic
+make typecheck
+
+# Or directly:
+poetry run mypy code2logic
 ```
 
 ### Linting
 
 ```bash
-ruff check code2logic
-black code2logic
+make lint
+make format
+
+# Or directly:
+poetry run ruff check code2logic
+poetry run black code2logic
 ```
 
 ## 📈 Performance

{code2logic-1.0.7 → code2logic-1.0.9}/code2logic/__init__.py

@@ -18,7 +18,7 @@ Example:
     >>> print(output)
 """
 
-__version__ = "1.0.7"
+__version__ = "1.0.9"
 __author__ = "Softreck"
 __email__ = "info@softreck.dev"
 __license__ = "MIT"

{code2logic-1.0.7 → code2logic-1.0.9}/code2logic/generators.py

@@ -1004,6 +1004,7 @@ class YAMLGenerator:
         # Build detailed module data with enhanced information
         detailed_modules = []
         for m in project.modules:
+            file_kb = bytes_to_kb(getattr(m, 'file_bytes', 0))
             mod_data = {
                 'p': m.path,  # path
             }
@@ -1033,17 +1034,10 @@ class YAMLGenerator:
                 for const in m.constants:
                     if isinstance(const, str):
                         # Handle string constants (from UniversalParser)
-                        const_dict = {'n': const}
+                        const_data.append({'n': const})
                     else:
                         # Handle ConstantInfo objects (from TreeSitter parser)
-                        const_dict = {'n': const.name}
-                        if const.type_annotation:
-                            const_dict['t'] = const.type_annotation
-                        if const.value_keys:  # For dicts, show keys
-                            const_dict['keys'] = const.value_keys[:10]
-                        elif const.value and len(const.value) <= 100:  # For small values
-                            const_dict['v'] = const.value
-                    const_data.append(const_dict)
+                        const_data.append(self._constant_to_dict(const))
                 if const_data:
                     mod_data['const'] = const_data
             
@@ -1776,7 +1770,9 @@ class YAMLGenerator:
         if len(f.params) > 6:
             params += f', ...+{len(f.params)-6}'
         
-        return params if params else ''
+        if params:
+            return f"({params})"
+        return "()"
 
     def _constants_for_module(self, module: ModuleInfo, limit: int = 10) -> list:
         """Convert module constants into compact dictionaries."""

{code2logic-1.0.7 → code2logic-1.0.9}/code2logic/toon_format.py

@@ -85,10 +85,11 @@ class TOONGenerator:
         lines = []
         
         # Module summary as tabular array
-        lines.append(f"modules[{len(modules)}]{{path{self.delim_marker}lang{self.delim_marker}lines}}:")
+        lines.append(f"modules[{len(modules)}]{{path{self.delim_marker}lang{self.delim_marker}lines{self.delim_marker}kb}}:")
         for m in modules:
             path = self._quote(m.path)
-            lines.append(f"  {path}{self.delimiter}{m.language}{self.delimiter}{m.lines_code}")
+            kb = round((getattr(m, 'file_bytes', 0) or 0) / 1024, 1)
+            lines.append(f"  {path}{self.delimiter}{m.language}{self.delimiter}{m.lines_code}{self.delimiter}{kb}")
         
         # Detailed module info
         if detail in ('standard', 'full'):
@@ -107,6 +108,38 @@ class TOONGenerator:
                 if m.exports:
                     exports_str = self.delimiter.join(self._quote(x) for x in m.exports[:10])
                     lines.append(f"    exports[{len(m.exports)}]: {exports_str}")
+
+                # ENHANCED: Add constants with values/keys (critical for reproduction)
+                constants_attr = getattr(m, 'constants', []) or []
+                const_rows = []
+                for c in constants_attr:
+                    if isinstance(c, str):
+                        if c.startswith('conditional:'):
+                            continue
+                        const_rows.append({'n': c, 't': '-', 'v': '-', 'keys': '-'})
+                    else:
+                        keys = getattr(c, 'value_keys', None) or []
+                        v = getattr(c, 'value', None)
+                        t = getattr(c, 'type_annotation', '') or '-'
+                        if keys:
+                            const_rows.append({'n': c.name, 't': t, 'v': '-', 'keys': '|'.join(keys[:10])})
+                        elif v:
+                            v_snip = v.replace('\n', ' ').strip()
+                            if len(v_snip) > 120:
+                                v_snip = v_snip[:117] + '...'
+                            const_rows.append({'n': c.name, 't': t, 'v': v_snip, 'keys': '-'})
+                        else:
+                            const_rows.append({'n': c.name, 't': t, 'v': '-', 'keys': '-'})
+                    if len(const_rows) >= 8:
+                        break
+
+                if const_rows:
+                    header = f"n{self.delim_marker}t{self.delim_marker}v{self.delim_marker}keys"
+                    lines.append(f"    const[{len(const_rows)}]{{{header}}}:")
+                    for r in const_rows:
+                        lines.append(
+                            f"      {self._quote(r['n'])}{self.delimiter}{self._quote(r['t'])}{self.delimiter}{self._quote(r['v'])}{self.delimiter}{self._quote(r['keys'])}"
+                        )
                 
                 # Classes
                 if m.classes:
@@ -152,6 +185,19 @@ class TOONGenerator:
                 if c.properties:
                     props_str = self.delimiter.join(self._quote(x) for x in c.properties[:10])
                     lines.append(f"{ind}    properties[{len(c.properties)}]: {props_str}")
+
+                # ENHANCED: Dataclass fields
+                if getattr(c, 'is_dataclass', False) and getattr(c, 'fields', None):
+                    fields = c.fields[:20]
+                    header = f"n{self.delim_marker}t{self.delim_marker}default{self.delim_marker}factory"
+                    lines.append(f"{ind}    fields[{len(fields)}]{{{header}}}:")
+                    for f in fields:
+                        t = getattr(f, 'type_annotation', '') or '-'
+                        dflt = getattr(f, 'default', None) or '-'
+                        fac = getattr(f, 'default_factory', None) or '-'
+                        lines.append(
+                            f"{ind}      {self._quote(f.name)}{self.delimiter}{self._quote(t)}{self.delimiter}{self._quote(dflt)}{self.delimiter}{self._quote(fac)}"
+                        )
                 
                 # Methods with full details
                 if c.methods: