mcp-vector-search 0.5.0__tar.gz → 0.5.1__tar.gz

{mcp_vector_search-0.5.0 → mcp_vector_search-0.5.1}/CLAUDE.md

@@ -8,11 +8,20 @@ This file provides comprehensive guidance for Claude Code (claude.ai/code) and C
 
 ## 🔴 Project Overview (CRITICAL)
 
-**MCP Vector Search** is a CLI-first semantic code search tool with MCP (Model Context Protocol) integration. It provides intelligent code search using vector embeddings and AST-aware parsing for **7 languages**: Python, JavaScript, TypeScript, Dart/Flutter, PHP, Ruby, and Markdown.
+**MCP Vector Search** is a CLI-first semantic code search tool with MCP (Model Context Protocol) integration. It provides intelligent code search using vector embeddings and AST-aware parsing for **8 languages**: Python, JavaScript, TypeScript, Dart/Flutter, PHP, Ruby, HTML, and Markdown/Text.
 
-### 🎉 Recent Major Features (NEW IN v0.5.0)
+### 🎉 Recent Major Features
 
-**1. PHP Language Support** 🐘
+**NEW (Unreleased): HTML Language Support** 🌐
+- Semantic content extraction from HTML documents
+- Intelligent chunking based on heading hierarchy (h1-h6)
+- Extracts text from semantic tags (section, article, main, aside, nav, header, footer, p)
+- Preserves class and id attributes for context
+- Ignores script and style tags
+- Perfect for static sites, documentation, web templates
+- Supported extensions: `.html`, `.htm`
+
+**v0.5.0: PHP Language Support** 🐘
 - Full AST-aware parsing with tree-sitter
 - Class, interface, and trait detection
 - Method extraction (public, private, protected, static)
@@ -20,7 +29,7 @@ This file provides comprehensive guidance for Claude Code (claude.ai/code) and C
 - PHPDoc comment extraction
 - Laravel framework patterns (Controllers, Models, Eloquent)
 
-**2. Ruby Language Support** 💎
+**v0.5.0: Ruby Language Support** 💎
 - Full AST-aware parsing with tree-sitter
 - Module and class detection with namespace support (::)
 - Instance and class method extraction
@@ -29,15 +38,15 @@ This file provides comprehensive guidance for Claude Code (claude.ai/code) and C
 - RDoc comment extraction
 - Rails framework patterns (ActiveRecord, Controllers)
 
-**3. Dart/Flutter Language Support** 🎯 (v0.4.15)
+**v0.4.15: Dart/Flutter Language Support** 🎯
 - Full AST-aware parsing with tree-sitter
 - Widget detection (StatelessWidget, StatefulWidget)
 - State class recognition (_WidgetNameState patterns)
 - Async/Future<T> support
 - Dartdoc comment extraction
-- Cross-language semantic search with all 7 languages
+- Cross-language semantic search with all supported languages
 
-**4. Enhanced Install Command** 🚀 (v0.4.15)
+**v0.4.15: Enhanced Install Command** 🚀
 - One-step complete project setup
 - Multi-tool MCP detection (Claude Code, Cursor, Windsurf, VS Code)
 - Interactive MCP configuration
@@ -45,7 +54,7 @@ This file provides comprehensive guidance for Claude Code (claude.ai/code) and C
 - Rich progress indicators
 - Options: `--no-mcp`, `--no-index`, `--mcp-tool`, `--extensions`
 
-**5. Rich Help System** 📚 (v0.4.15)
+**v0.4.15: Rich Help System** 📚
 - Organized help panels (Core, Customization, Advanced)
 - Comprehensive examples in all commands
 - Next-step hints after operations
@@ -206,9 +215,9 @@ The codebase follows a **layered architecture** with clear separation of concern
 #### 🟡 3. Parser System (`src/mcp_vector_search/parsers/`) - LANGUAGE SUPPORT
 - **Base**: `base.py` - abstract `BaseParser` interface (extend for new languages)
 - **Registry**: `registry.py` - dynamic parser discovery and selection
-- **Language Parsers**: `python.py`, `javascript.py`, `typescript.py`, `dart.py`, `php.py`, `ruby.py`, `text.py`
+- **Language Parsers**: `python.py`, `javascript.py`, `typescript.py`, `dart.py`, `php.py`, `ruby.py`, `html.py`, `text.py`
 - **Output**: Each parser extracts functions, classes, methods, and semantic chunks
-- **Total Languages**: 7 (Python, JavaScript, TypeScript, Dart, PHP, Ruby, Markdown)
+- **Total Languages**: 8 (Python, JavaScript, TypeScript, Dart, PHP, Ruby, HTML, Text/Markdown)
 
 #### 🔴 4. MCP Integration (`src/mcp_vector_search/mcp/`) - CLAUDE INTEGRATION
 - **Server**: `server.py` - Model Context Protocol server implementation
@@ -472,7 +481,7 @@ mcp-vector-search auto-index check --dry-run --verbose
 
 ### 🟡 Known Issues (Being Addressed)
 - **Tree-sitter**: Integration needs improvement (using regex fallback)
-- **Language Support**: Currently 7 languages (Python, JS, TS, Dart, PHP, Ruby, Markdown)
+- **Language Support**: Currently 8 languages (Python, JS, TS, Dart, PHP, Ruby, HTML, Text/Markdown)
 - **Binary Files**: No support for notebooks, images, compiled files
 
 ### 🟢 Future Improvements

{mcp_vector_search-0.5.0 → mcp_vector_search-0.5.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mcp-vector-search
-Version: 0.5.0
+Version: 0.5.1
 Summary: CLI-first semantic code search with MCP integration
 Project-URL: Homepage, https://github.com/bobmatnyc/mcp-vector-search
 Project-URL: Documentation, https://mcp-vector-search.readthedocs.io
@@ -71,7 +71,7 @@ A modern, fast, and intelligent code search tool that understands your codebase
 ### 🚀 **Core Capabilities**
 - **Semantic Search**: Find code by meaning, not just keywords
 - **AST-Aware Parsing**: Understands code structure (functions, classes, methods)
-- **Multi-Language Support**: Python, JavaScript, TypeScript, Dart/Flutter, PHP, Ruby (with extensible architecture)
+- **Multi-Language Support**: 8 languages - Python, JavaScript, TypeScript, Dart/Flutter, PHP, Ruby, HTML, and Markdown/Text (with extensible architecture)
 - **Real-time Indexing**: File watching with automatic index updates
 - **Local-First**: Complete privacy with on-device processing
 - **Zero Configuration**: Auto-detects project structure and languages
@@ -355,21 +355,35 @@ Projects are configured via `.mcp-vector-search/config.json`:
 
 ### Supported Languages
 
+MCP Vector Search supports **8 programming languages** with full semantic search capabilities:
+
+| Language   | Extensions | Status | Features |
+|------------|------------|--------|----------|
+| Python     | `.py`, `.pyw` | ✅ Full | Functions, classes, methods, docstrings |
+| JavaScript | `.js`, `.jsx`, `.mjs` | ✅ Full | Functions, classes, JSDoc, ES6+ syntax |
+| TypeScript | `.ts`, `.tsx` | ✅ Full | Interfaces, types, generics, decorators |
+| Dart       | `.dart` | ✅ Full | Functions, classes, widgets, async, dartdoc |
+| PHP        | `.php`, `.phtml` | ✅ Full | Classes, methods, traits, PHPDoc, Laravel patterns |
+| Ruby       | `.rb`, `.rake`, `.gemspec` | ✅ Full | Modules, classes, methods, RDoc, Rails patterns |
+| HTML       | `.html`, `.htm` | ✅ Full | Semantic content extraction, heading hierarchy, text chunking |
+| Text/Markdown | `.txt`, `.md`, `.markdown` | ✅ Basic | Semantic chunking for documentation |
+
+**Planned Languages:**
 | Language   | Status | Features |
 |------------|--------|----------|
-| Python     | ✅ Full | Functions, classes, methods, docstrings |
-| JavaScript | ✅ Full | Functions, classes, JSDoc, ES6+ syntax |
-| TypeScript | ✅ Full | Interfaces, types, generics, decorators |
-| Dart       | ✅ Full | Functions, classes, widgets, async, dartdoc |
-| PHP        | ✅ Full | Classes, methods, traits, PHPDoc, Laravel patterns |
-| Ruby       | ✅ Full | Modules, classes, methods, RDoc, Rails patterns |
-| Text/Markdown | ✅ Basic | Semantic chunking for documentation |
 | Java       | 🔄 Planned | Classes, methods, annotations |
 | Go         | 🔄 Planned | Functions, structs, interfaces |
 | Rust       | 🔄 Planned | Functions, structs, traits |
 
 #### New Language Support
 
+**HTML Support** (Unreleased):
+- **Semantic Extraction**: Content from h1-h6, p, section, article, main, aside, nav, header, footer
+- **Intelligent Chunking**: Based on heading hierarchy (h1-h6)
+- **Context Preservation**: Maintains class and id attributes for searchability
+- **Script/Style Filtering**: Ignores non-content elements
+- **Use Cases**: Static sites, documentation, web templates, HTML fragments
+
 **Dart/Flutter Support** (v0.4.15):
 - **Widget Detection**: StatelessWidget, StatefulWidget recognition
 - **State Classes**: Automatic parsing of `_WidgetNameState` patterns

{mcp_vector_search-0.5.0 → mcp_vector_search-0.5.1}/README.md

@@ -15,7 +15,7 @@ A modern, fast, and intelligent code search tool that understands your codebase
 ### 🚀 **Core Capabilities**
 - **Semantic Search**: Find code by meaning, not just keywords
 - **AST-Aware Parsing**: Understands code structure (functions, classes, methods)
-- **Multi-Language Support**: Python, JavaScript, TypeScript, Dart/Flutter, PHP, Ruby (with extensible architecture)
+- **Multi-Language Support**: 8 languages - Python, JavaScript, TypeScript, Dart/Flutter, PHP, Ruby, HTML, and Markdown/Text (with extensible architecture)
 - **Real-time Indexing**: File watching with automatic index updates
 - **Local-First**: Complete privacy with on-device processing
 - **Zero Configuration**: Auto-detects project structure and languages
@@ -299,21 +299,35 @@ Projects are configured via `.mcp-vector-search/config.json`:
 
 ### Supported Languages
 
+MCP Vector Search supports **8 programming languages** with full semantic search capabilities:
+
+| Language   | Extensions | Status | Features |
+|------------|------------|--------|----------|
+| Python     | `.py`, `.pyw` | ✅ Full | Functions, classes, methods, docstrings |
+| JavaScript | `.js`, `.jsx`, `.mjs` | ✅ Full | Functions, classes, JSDoc, ES6+ syntax |
+| TypeScript | `.ts`, `.tsx` | ✅ Full | Interfaces, types, generics, decorators |
+| Dart       | `.dart` | ✅ Full | Functions, classes, widgets, async, dartdoc |
+| PHP        | `.php`, `.phtml` | ✅ Full | Classes, methods, traits, PHPDoc, Laravel patterns |
+| Ruby       | `.rb`, `.rake`, `.gemspec` | ✅ Full | Modules, classes, methods, RDoc, Rails patterns |
+| HTML       | `.html`, `.htm` | ✅ Full | Semantic content extraction, heading hierarchy, text chunking |
+| Text/Markdown | `.txt`, `.md`, `.markdown` | ✅ Basic | Semantic chunking for documentation |
+
+**Planned Languages:**
 | Language   | Status | Features |
 |------------|--------|----------|
-| Python     | ✅ Full | Functions, classes, methods, docstrings |
-| JavaScript | ✅ Full | Functions, classes, JSDoc, ES6+ syntax |
-| TypeScript | ✅ Full | Interfaces, types, generics, decorators |
-| Dart       | ✅ Full | Functions, classes, widgets, async, dartdoc |
-| PHP        | ✅ Full | Classes, methods, traits, PHPDoc, Laravel patterns |
-| Ruby       | ✅ Full | Modules, classes, methods, RDoc, Rails patterns |
-| Text/Markdown | ✅ Basic | Semantic chunking for documentation |
 | Java       | 🔄 Planned | Classes, methods, annotations |
 | Go         | 🔄 Planned | Functions, structs, interfaces |
 | Rust       | 🔄 Planned | Functions, structs, traits |
 
 #### New Language Support
 
+**HTML Support** (Unreleased):
+- **Semantic Extraction**: Content from h1-h6, p, section, article, main, aside, nav, header, footer
+- **Intelligent Chunking**: Based on heading hierarchy (h1-h6)
+- **Context Preservation**: Maintains class and id attributes for searchability
+- **Script/Style Filtering**: Ignores non-content elements
+- **Use Cases**: Static sites, documentation, web templates, HTML fragments
+
 **Dart/Flutter Support** (v0.4.15):
 - **Widget Detection**: StatelessWidget, StatefulWidget recognition
 - **State Classes**: Automatic parsing of `_WidgetNameState` patterns

{mcp_vector_search-0.5.0 → mcp_vector_search-0.5.1}/docs/CHANGELOG.md

@@ -7,6 +7,23 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+### Added
+- **HTML Language Support**: Full HTML parser implementation
+  - Semantic content extraction from HTML tags
+  - Intelligent chunking based on heading hierarchy
+  - Ignores script and style tag content
+  - Extracts text from h1-h6, p, section, article, main, aside, nav, header, footer
+  - Preserves class and id attributes for context
+  - Supported extensions: `.html`, `.htm`
+
+### Enhanced
+- **Text Parser**: Now supports markdown files (`.md`, `.markdown`) in addition to `.txt`
+- **Language Count**: Now supports **8 languages** (up from 7):
+  - Python, JavaScript, TypeScript (existing)
+  - Dart, PHP, Ruby (v0.5.0)
+  - **HTML** (new)
+  - Text/Markdown (enhanced)
+
 ## [0.5.0] - 2025-10-02
 
 ### Added
@@ -33,7 +50,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - **Configuration Format**: Added required `"type": "stdio"` field for Claude Code compatibility
 
 ### Enhanced
-- **Language Support**: Now supports **7 languages** total
+- **Language Support**: Now supports **7 languages** total (8 as of next release)
   - Python, JavaScript, TypeScript (existing)
   - Dart/Flutter (v0.4.15)
   - **PHP** (new)

{mcp_vector_search-0.5.0 → mcp_vector_search-0.5.1}/docs/CLI_FEATURES.md

@@ -2,17 +2,18 @@
 
 ## Supported Languages
 
-MCP Vector Search now supports **7 programming languages** with full semantic search capabilities:
+MCP Vector Search now supports **8 programming languages** with full semantic search capabilities:
 
 | Language   | Extensions | Features |
 |------------|------------|----------|
-| Python     | `.py` | Functions, classes, methods, docstrings |
+| Python     | `.py`, `.pyw` | Functions, classes, methods, docstrings |
 | JavaScript | `.js`, `.jsx`, `.mjs` | Functions, classes, JSDoc, ES6+ syntax |
 | TypeScript | `.ts`, `.tsx` | Interfaces, types, generics, decorators |
 | Dart       | `.dart` | Functions, classes, widgets, async, dartdoc |
 | PHP        | `.php`, `.phtml` | Classes, methods, traits, PHPDoc, Laravel patterns |
 | Ruby       | `.rb`, `.rake`, `.gemspec` | Modules, classes, methods, RDoc, Rails patterns |
-| Markdown   | `.md`, `.txt` | Semantic chunking for documentation |
+| HTML       | `.html`, `.htm` | Semantic content extraction, heading hierarchy, text chunking |
+| Text/Markdown | `.txt`, `.md`, `.markdown` | Semantic chunking for documentation |
 
 ### Framework Support
 
@@ -23,6 +24,11 @@ MCP Vector Search now supports **7 programming languages** with full semantic se
 ### Search Examples by Language
 
 ```bash
+# HTML - Static Site Content
+mcp-vector-search search "contact form section"
+mcp-vector-search search "navigation menu structure"
+mcp-vector-search search "pricing table layout"
+
 # PHP - Laravel Controller
 mcp-vector-search search "user authentication controller"
 

{mcp_vector_search-0.5.0 → mcp_vector_search-0.5.1}/src/mcp_vector_search/__init__.py

@@ -1,7 +1,7 @@
 """MCP Vector Search - CLI-first semantic code search with MCP integration."""
 
-__version__ = "0.5.0"
-__build__ = "18"
+__version__ = "0.5.1"
+__build__ = "19"
 __author__ = "Robert Matsuoka"
 __email__ = "bobmatnyc@gmail.com"
 

{mcp_vector_search-0.5.0 → mcp_vector_search-0.5.1}/src/mcp_vector_search/parsers/__init__.py

@@ -1,7 +1,8 @@
 """Language parsers for MCP Vector Search."""
 
 from .dart import DartParser
+from .html import HTMLParser
 from .php import PHPParser
 from .ruby import RubyParser
 
-__all__ = ["DartParser", "PHPParser", "RubyParser"]
+__all__ = ["DartParser", "HTMLParser", "PHPParser", "RubyParser"]