code2llm 0.5.15__tar.gz → 0.5.17__tar.gz

{code2llm-0.5.15 → code2llm-0.5.17}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: code2llm
-Version: 0.5.15
+Version: 0.5.17
 Summary: High-performance Python code flow analysis with optimized TOON format - CFG, DFG, call graphs, and intelligent code queries
 Home-page: https://github.com/wronai/stts
 Author: STTS Project
@@ -60,48 +60,18 @@ When you run `code2llm ./ -f all`, the following files are created:
 
 | File | Format | Purpose | Key Insights |
 |------|--------|---------|--------------|
-| `analysis.toon` | **TOON** | **🔥 Health diagnostics** - Complexity, god modules, coupling | 45 critical functions, 0 god modules |
-| `evolution.toon` | **TOON** | **📋 Refactoring queue** - Prioritized improvements | 0 refactoring actions needed |
-| `flow.toon` | **TOON** | **🔄 Data flow analysis** - Pipelines, contracts, types | Data dependencies and side effects |
-| `map.toon` | **TOON** | **🗺️ Structural map** - Modules, imports, signatures | Project architecture overview |
-| `project.toon` | **TOON** | **🧠 Project logic** - Code2Logic compact module view | Generated via code2logic integration |
+| `analysis.toon` | **TOON** | **🔥 Health diagnostics** - Complexity, god modules, coupling | 43 critical functions, 0 god modules |
+| `project.toon` | **TOON** | **🧠 Project logic** - Compact module view from code2logic | Generated via code2logic integration |
 
 ### 🤖 LLM-Ready Documentation
 
 | File | Format | Purpose | Use Case |
 |------|--------|---------|----------|
 | `context.md` | **Markdown** | **📖 LLM narrative** - Architecture summary | Paste into ChatGPT/Claude for code analysis |
-| `prompt.txt` | **Text** | **📝 Ready-to-send prompt** - Lists all generated files with instructions | Attach to LLM conversation as context guide |
-| `analysis.yaml` | **YAML** | **📊 Structured data** - Machine-readable | For scripts and automated processing |
-| `analysis.json` | **JSON** | **🔧 API format** - Programmatic access | For integration with other tools |
 
-### 📊 Visualizations
-
-| File | Format | Purpose | Description |
-|------|--------|---------|-------------|
-| `flow.mmd` | **Mermaid** | **🔄 Control flow diagram** | Function call paths with complexity styling |
-| `calls.mmd` | **Mermaid** | **📞 Call graph** | Function dependencies (edges only) |
-| `compact_flow.mmd` | **Mermaid** | **📦 Module overview** | Aggregated module-level view |
-| `*.png` | **PNG** | **🖼️ Visual diagrams** | Rendered versions of Mermaid files |
 
 ## 🚀 Quick Start Commands
 
-### Complete LLM Analysis (with Code2Logic)
-```bash
-# Generate complete analysis with code2logic integration
-# Creates: analysis.toon, evolution.toon, project.toon, prompt.txt, README.md
-
-# Using specific formats (recommended)
-code2llm ./ -f toon,evolution,code2logic -o ./project
-
-# Using 'all' format (includes code2logic)
-code2llm ./ -f all -o ./project
-```
-
-The `code2logic` format automatically:
-1. Runs `code2logic` tool to generate `project.toon` (compact module view)
-2. Creates `prompt.txt` - ready-to-send prompt listing all generated files
-
 ### Basic Analysis
 ```bash
 # Quick health check (TOON format only)
@@ -114,12 +84,6 @@ code2llm ./ -f all
 code2llm ./ -f context
 ```
 
-Przykład z projektu toonic, z użyciem modelu Kimi K2.5 w VScode Windsurf:
-![img_1.png](img_1.png)
-```bash
-code2llm ./ -f toon,evolution -o ./project
-```
-
 ### Performance Options
 ```bash
 # Fast analysis for large projects
@@ -132,6 +96,46 @@ code2llm ./ -f all --max-memory 500
 code2llm ./ -f all --no-png
 ```
 
+### Large Repository Analysis (Chunking)
+For repositories >100 files, automatic chunking splits analysis into smaller subprojects:
+
+```bash
+# Auto-chunking when >100 files detected
+code2llm ./ -f toon,evolution,code2logic --verbose
+
+# Force chunking with custom size limit
+code2llm ./ -f toon --chunk --chunk-size 256
+
+# Analyze only specific subproject
+code2llm ./ -f toon --only-subproject src
+
+# Skip tests and examples
+code2llm ./ -f toon --skip-subprojects tests examples
+
+# Customize file limit per chunk
+code2llm ./ -f toon --chunk --max-files-per-chunk 50
+```
+
+**Chunking Benefits:**
+- Each subproject analyzed separately (examples/, tests/, src/, etc.)
+- Output limited to ~256KB per file (configurable)
+- Parallel processing of chunks possible
+- Reduced memory usage for large repos
+
+**Output Structure:**
+```
+./project/
+  ├── src/                    # Core code analysis
+  │   ├── analysis.toon
+  │   └── evolution.toon
+  ├── tests/                 # Test code analysis
+  │   └── analysis.toon
+  ├── examples/              # Examples analysis
+  │   └── analysis.toon
+  ├── analysis.toon          # Merged summary
+  └── evolution.toon         # Full refactoring queue
+```
+
 ### Refactoring Focus
 ```bash
 # Get refactoring recommendations
@@ -213,23 +217,6 @@ cat map.toon | head -50
 grep "SIGNATURES" map.toon
 ```
 
-### `context.md` - LLM Narrative
-**Purpose**: Ready-to-paste context for AI assistants
-**Key sections**:
-- **Overview**: Project statistics
-- **Architecture**: Module breakdown
-- **Entry Points**: Public interfaces
-- **Patterns**: Design patterns detected
-
-**Example usage**:
-```bash
-# Copy to clipboard for LLM
-cat context.md | pbcopy  # macOS
-cat context.md | xclip -sel clip  # Linux
-
-# Use with Claude/ChatGPT for code analysis
-```
-
 ### `project.toon` - Project Logic (Code2Logic)
 **Purpose**: Compact module view generated by code2logic integration
 **Key sections**:
@@ -239,31 +226,49 @@ cat context.md | xclip -sel clip  # Linux
 
 **When to use**: When you need a lightweight project overview combined with code2llm analysis
 
-**Generation**:
+**Example usage**:
 ```bash
-# Generated automatically when using -f code2logic
-code2llm ./ -f toon,evolution,code2logic -o ./project
+# View compact project structure
+cat project.toon | head -30
+
+# Find largest files
+grep -E "^  .*[0-9]{3,}$" project.toon | sort -t',' -k2 -n -r | head -10
 ```
 
 ### `prompt.txt` - Ready-to-Send LLM Prompt
 **Purpose**: Pre-formatted prompt listing all generated files for LLM conversation
 **Contents**:
-- **Files section**: Lists all existing generated files (analysis.toon, context.md, etc.)
+- **Files section**: Lists all existing generated files with descriptions
 - **Missing section**: Shows which files weren't generated (if any)
 - **Task section**: Instructions for LLM analysis
-- **Constraints section**: Guidelines for suggested changes
+- **Requirements section**: Guidelines for suggested changes
 
 **Example usage**:
 ```bash
 # View the prompt
-cat project/prompt.txt
+cat prompt.txt
 
 # Copy to clipboard and paste into ChatGPT/Claude
-cat project/prompt.txt | pbcopy  # macOS
-cat project/prompt.txt | xclip -sel clip  # Linux
+cat prompt.txt | pbcopy  # macOS
+cat prompt.txt | xclip -sel clip  # Linux
 ```
 
-**Generated when**: Using `-f code2logic` or `-f all`
+### `context.md` - LLM Narrative
+**Purpose**: Ready-to-paste context for AI assistants
+**Key sections**:
+- **Overview**: Project statistics
+- **Architecture**: Module breakdown
+- **Entry Points**: Public interfaces
+- **Patterns**: Design patterns detected
+
+**Example usage**:
+```bash
+# Copy to clipboard for LLM
+cat context.md | pbcopy  # macOS
+cat context.md | xclip -sel clip  # Linux
+
+# Use with Claude/ChatGPT for code analysis
+```
 
 ### Visualization Files (`*.mmd`, `*.png`)
 **Purpose**: Visual understanding of code structure
@@ -409,10 +414,10 @@ code2llm ./ -f yaml --separate-orphans
 ---
 
 **Generated by**: `code2llm ./ -f all --readme`  
-**Analysis Date**: 2026-03-01  
-**Total Functions**: 645  
-**Total Classes**: 94  
-**Modules**: 76  
+**Analysis Date**: 2026-03-03  
+**Total Functions**: 700  
+**Total Classes**: 97  
+**Modules**: 83  
 
 For more information about code2llm, visit: https://github.com/tom-sapletta/code2llm
 

{code2llm-0.5.15 → code2llm-0.5.17}/README.md

@@ -10,48 +10,18 @@ When you run `code2llm ./ -f all`, the following files are created:
 
 | File | Format | Purpose | Key Insights |
 |------|--------|---------|--------------|
-| `analysis.toon` | **TOON** | **🔥 Health diagnostics** - Complexity, god modules, coupling | 45 critical functions, 0 god modules |
-| `evolution.toon` | **TOON** | **📋 Refactoring queue** - Prioritized improvements | 0 refactoring actions needed |
-| `flow.toon` | **TOON** | **🔄 Data flow analysis** - Pipelines, contracts, types | Data dependencies and side effects |
-| `map.toon` | **TOON** | **🗺️ Structural map** - Modules, imports, signatures | Project architecture overview |
-| `project.toon` | **TOON** | **🧠 Project logic** - Code2Logic compact module view | Generated via code2logic integration |
+| `analysis.toon` | **TOON** | **🔥 Health diagnostics** - Complexity, god modules, coupling | 43 critical functions, 0 god modules |
+| `project.toon` | **TOON** | **🧠 Project logic** - Compact module view from code2logic | Generated via code2logic integration |
 
 ### 🤖 LLM-Ready Documentation
 
 | File | Format | Purpose | Use Case |
 |------|--------|---------|----------|
 | `context.md` | **Markdown** | **📖 LLM narrative** - Architecture summary | Paste into ChatGPT/Claude for code analysis |
-| `prompt.txt` | **Text** | **📝 Ready-to-send prompt** - Lists all generated files with instructions | Attach to LLM conversation as context guide |
-| `analysis.yaml` | **YAML** | **📊 Structured data** - Machine-readable | For scripts and automated processing |
-| `analysis.json` | **JSON** | **🔧 API format** - Programmatic access | For integration with other tools |
 
-### 📊 Visualizations
-
-| File | Format | Purpose | Description |
-|------|--------|---------|-------------|
-| `flow.mmd` | **Mermaid** | **🔄 Control flow diagram** | Function call paths with complexity styling |
-| `calls.mmd` | **Mermaid** | **📞 Call graph** | Function dependencies (edges only) |
-| `compact_flow.mmd` | **Mermaid** | **📦 Module overview** | Aggregated module-level view |
-| `*.png` | **PNG** | **🖼️ Visual diagrams** | Rendered versions of Mermaid files |
 
 ## 🚀 Quick Start Commands
 
-### Complete LLM Analysis (with Code2Logic)
-```bash
-# Generate complete analysis with code2logic integration
-# Creates: analysis.toon, evolution.toon, project.toon, prompt.txt, README.md
-
-# Using specific formats (recommended)
-code2llm ./ -f toon,evolution,code2logic -o ./project
-
-# Using 'all' format (includes code2logic)
-code2llm ./ -f all -o ./project
-```
-
-The `code2logic` format automatically:
-1. Runs `code2logic` tool to generate `project.toon` (compact module view)
-2. Creates `prompt.txt` - ready-to-send prompt listing all generated files
-
 ### Basic Analysis
 ```bash
 # Quick health check (TOON format only)
@@ -64,12 +34,6 @@ code2llm ./ -f all
 code2llm ./ -f context
 ```
 
-Przykład z projektu toonic, z użyciem modelu Kimi K2.5 w VScode Windsurf:
-![img_1.png](img_1.png)
-```bash
-code2llm ./ -f toon,evolution -o ./project
-```
-
 ### Performance Options
 ```bash
 # Fast analysis for large projects
@@ -82,6 +46,46 @@ code2llm ./ -f all --max-memory 500
 code2llm ./ -f all --no-png
 ```
 
+### Large Repository Analysis (Chunking)
+For repositories >100 files, automatic chunking splits analysis into smaller subprojects:
+
+```bash
+# Auto-chunking when >100 files detected
+code2llm ./ -f toon,evolution,code2logic --verbose
+
+# Force chunking with custom size limit
+code2llm ./ -f toon --chunk --chunk-size 256
+
+# Analyze only specific subproject
+code2llm ./ -f toon --only-subproject src
+
+# Skip tests and examples
+code2llm ./ -f toon --skip-subprojects tests examples
+
+# Customize file limit per chunk
+code2llm ./ -f toon --chunk --max-files-per-chunk 50
+```
+
+**Chunking Benefits:**
+- Each subproject analyzed separately (examples/, tests/, src/, etc.)
+- Output limited to ~256KB per file (configurable)
+- Parallel processing of chunks possible
+- Reduced memory usage for large repos
+
+**Output Structure:**
+```
+./project/
+  ├── src/                    # Core code analysis
+  │   ├── analysis.toon
+  │   └── evolution.toon
+  ├── tests/                 # Test code analysis
+  │   └── analysis.toon
+  ├── examples/              # Examples analysis
+  │   └── analysis.toon
+  ├── analysis.toon          # Merged summary
+  └── evolution.toon         # Full refactoring queue
+```
+
 ### Refactoring Focus
 ```bash
 # Get refactoring recommendations
@@ -163,23 +167,6 @@ cat map.toon | head -50
 grep "SIGNATURES" map.toon
 ```
 
-### `context.md` - LLM Narrative
-**Purpose**: Ready-to-paste context for AI assistants
-**Key sections**:
-- **Overview**: Project statistics
-- **Architecture**: Module breakdown
-- **Entry Points**: Public interfaces
-- **Patterns**: Design patterns detected
-
-**Example usage**:
-```bash
-# Copy to clipboard for LLM
-cat context.md | pbcopy  # macOS
-cat context.md | xclip -sel clip  # Linux
-
-# Use with Claude/ChatGPT for code analysis
-```
-
 ### `project.toon` - Project Logic (Code2Logic)
 **Purpose**: Compact module view generated by code2logic integration
 **Key sections**:
@@ -189,31 +176,49 @@ cat context.md | xclip -sel clip  # Linux
 
 **When to use**: When you need a lightweight project overview combined with code2llm analysis
 
-**Generation**:
+**Example usage**:
 ```bash
-# Generated automatically when using -f code2logic
-code2llm ./ -f toon,evolution,code2logic -o ./project
+# View compact project structure
+cat project.toon | head -30
+
+# Find largest files
+grep -E "^  .*[0-9]{3,}$" project.toon | sort -t',' -k2 -n -r | head -10
 ```
 
 ### `prompt.txt` - Ready-to-Send LLM Prompt
 **Purpose**: Pre-formatted prompt listing all generated files for LLM conversation
 **Contents**:
-- **Files section**: Lists all existing generated files (analysis.toon, context.md, etc.)
+- **Files section**: Lists all existing generated files with descriptions
 - **Missing section**: Shows which files weren't generated (if any)
 - **Task section**: Instructions for LLM analysis
-- **Constraints section**: Guidelines for suggested changes
+- **Requirements section**: Guidelines for suggested changes
 
 **Example usage**:
 ```bash
 # View the prompt
-cat project/prompt.txt
+cat prompt.txt
 
 # Copy to clipboard and paste into ChatGPT/Claude
-cat project/prompt.txt | pbcopy  # macOS
-cat project/prompt.txt | xclip -sel clip  # Linux
+cat prompt.txt | pbcopy  # macOS
+cat prompt.txt | xclip -sel clip  # Linux
 ```
 
-**Generated when**: Using `-f code2logic` or `-f all`
+### `context.md` - LLM Narrative
+**Purpose**: Ready-to-paste context for AI assistants
+**Key sections**:
+- **Overview**: Project statistics
+- **Architecture**: Module breakdown
+- **Entry Points**: Public interfaces
+- **Patterns**: Design patterns detected
+
+**Example usage**:
+```bash
+# Copy to clipboard for LLM
+cat context.md | pbcopy  # macOS
+cat context.md | xclip -sel clip  # Linux
+
+# Use with Claude/ChatGPT for code analysis
+```
 
 ### Visualization Files (`*.mmd`, `*.png`)
 **Purpose**: Visual understanding of code structure
@@ -359,10 +364,10 @@ code2llm ./ -f yaml --separate-orphans
 ---
 
 **Generated by**: `code2llm ./ -f all --readme`  
-**Analysis Date**: 2026-03-01  
-**Total Functions**: 645  
-**Total Classes**: 94  
-**Modules**: 76  
+**Analysis Date**: 2026-03-03  
+**Total Functions**: 700  
+**Total Classes**: 97  
+**Modules**: 83  
 
 For more information about code2llm, visit: https://github.com/tom-sapletta/code2llm
 

{code2llm-0.5.15 → code2llm-0.5.17}/code2llm/__init__.py

@@ -8,7 +8,7 @@ Includes NLP Processing Pipeline for query normalization, intent matching,
 and entity resolution with multilingual support.
 """
 
-__version__ = "0.5.15"
+__version__ = "0.5.17"
 __author__ = "STTS Project"
 
 # Core analysis components