content-core 1.1.2__tar.gz → 1.2.0__tar.gz

content_core-1.2.0/.github/workflows/claude-code-review.yml

@@ -0,0 +1,77 @@
+name: Claude Code Review
+
+on:
+  pull_request:
+    types: [opened, synchronize]
+    # Optional: Only run on specific file changes
+    # paths:
+    #   - "src/**/*.ts"
+    #   - "src/**/*.tsx"
+    #   - "src/**/*.js"
+    #   - "src/**/*.jsx"
+
+jobs:
+  claude-review:
+    # Optional: Filter by PR author
+    # if: |
+    #   github.event.pull_request.user.login == 'external-contributor' ||
+    #   github.event.pull_request.user.login == 'new-developer' ||
+    #   github.event.pull_request.author_association == 'FIRST_TIME_CONTRIBUTOR'
+    
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      pull-requests: read
+      issues: read
+      id-token: write
+    
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 1
+
+      - name: Run Claude Code Review
+        id: claude-review
+        uses: anthropics/claude-code-action@beta
+        with:
+          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
+          
+          # Optional: Specify model (defaults to Claude Sonnet 4, uncomment for Claude Opus 4)
+          # model: "claude-opus-4-20250514"
+          
+          # Direct prompt for automated review (no @claude mention needed)
+          direct_prompt: |
+            Please review this pull request (and any added updates) and provide feedback on:
+            - Code quality and best practices
+            - Potential bugs or issues
+            - Performance considerations
+            - Documentation updates: does the README.md and docs/ reflect what changed?
+            - Security concerns
+            - Test coverage
+            
+            If the pull request received updates after your first review, please redo the review based on the new code
+            Be constructive and helpful in your feedback.
+          
+          # Optional: Customize review based on file types
+          # direct_prompt: |
+          #   Review this PR focusing on:
+          #   - For TypeScript files: Type safety and proper interface usage
+          #   - For API endpoints: Security, input validation, and error handling
+          #   - For React components: Performance, accessibility, and best practices
+          #   - For tests: Coverage, edge cases, and test quality
+          
+          # Optional: Different prompts for different authors
+          # direct_prompt: |
+          #   ${{ github.event.pull_request.author_association == 'FIRST_TIME_CONTRIBUTOR' && 
+          #   'Welcome! Please review this PR from a first-time contributor. Be encouraging and provide detailed explanations for any suggestions.' ||
+          #   'Please provide a thorough code review focusing on our coding standards and best practices.' }}
+          
+          # Optional: Add specific tools for running tests or linting
+          # allowed_tools: "Bash(npm run test),Bash(npm run lint),Bash(npm run typecheck)"
+          
+          # Optional: Skip review for certain conditions
+          # if: |
+          #   !contains(github.event.pull_request.title, '[skip-review]') &&
+          #   !contains(github.event.pull_request.title, '[WIP]')
+

content_core-1.2.0/.github/workflows/claude.yml

@@ -0,0 +1,59 @@
+name: Claude Code
+
+on:
+  issue_comment:
+    types: [created]
+  pull_request_review_comment:
+    types: [created]
+  issues:
+    types: [opened, assigned]
+  pull_request_review:
+    types: [submitted]
+
+jobs:
+  claude:
+    if: |
+      (github.event_name == 'issue_comment' && contains(github.event.comment.body, '@claude')) ||
+      (github.event_name == 'pull_request_review_comment' && contains(github.event.comment.body, '@claude')) ||
+      (github.event_name == 'pull_request_review' && contains(github.event.review.body, '@claude')) ||
+      (github.event_name == 'issues' && (contains(github.event.issue.body, '@claude') || contains(github.event.issue.title, '@claude')))
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      pull-requests: read
+      issues: read
+      id-token: write
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 1
+
+      - name: Run Claude Code
+        id: claude
+        uses: anthropics/claude-code-action@beta
+        with:
+          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
+          
+          # Optional: Specify model (defaults to Claude Sonnet 4, uncomment for Claude Opus 4)
+          # model: "claude-opus-4-20250514"
+          
+          # Optional: Customize the trigger phrase (default: @claude)
+          # trigger_phrase: "/claude"
+          
+          # Optional: Trigger when specific user is assigned to an issue
+          # assignee_trigger: "claude-bot"
+          
+          # Optional: Allow Claude to run specific commands
+          # allowed_tools: "Bash(npm install),Bash(npm run build),Bash(npm run test:*),Bash(npm run lint:*)"
+          
+          # Optional: Add custom instructions for Claude to customize its behavior for your project
+          # custom_instructions: |
+          #   Follow our coding standards
+          #   Ensure all new code has tests
+          #   Use TypeScript for new files
+          
+          # Optional: Custom environment variables for Claude
+          # claude_env: |
+          #   NODE_ENV: test
+

{content_core-1.1.2 → content_core-1.2.0}/.gitignore

@@ -22,4 +22,7 @@ WIP/
 
 *.ignore
 .windsurfrules
-CLAUDE.md
+CLAUDE.md
+
+node_modules/
+**/notebooks/private

{content_core-1.1.2 → content_core-1.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: content-core
-Version: 1.1.2
+Version: 1.2.0
 Summary: Extract what matters from any media source. Available as Python Library, macOS Service, CLI and MCP Server
 Author-email: LUIS NOVO <lfnovo@gmail.com>
 License-File: LICENSE
@@ -10,7 +10,6 @@ Requires-Dist: aiohttp>=3.11
 Requires-Dist: asciidoc>=10.2.1
 Requires-Dist: bs4>=0.0.2
 Requires-Dist: dicttoxml>=1.7.16
-Requires-Dist: docling>=2.34.0
 Requires-Dist: esperanto>=1.2.0
 Requires-Dist: firecrawl-py>=2.7.0
 Requires-Dist: jinja2>=3.1.6
@@ -31,6 +30,8 @@ Requires-Dist: pytubefix>=9.1.1
 Requires-Dist: readability-lxml>=0.8.4.1
 Requires-Dist: validators>=0.34.0
 Requires-Dist: youtube-transcript-api>=1.0.3
+Provides-Extra: docling
+Requires-Dist: docling>=2.34.0; extra == 'docling'
 Provides-Extra: mcp
 Requires-Dist: fastmcp>=0.5.0; extra == 'mcp'
 Description-Content-Type: text/markdown
@@ -39,29 +40,70 @@ Description-Content-Type: text/markdown
 
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 
-**Content Core** is a versatile Python library designed to extract and process content from various sources, providing a unified interface for handling text, web pages, and local files.
+**Content Core** is a powerful, AI-powered content extraction and processing platform that transforms any source into clean, structured content. Extract text from websites, transcribe videos, process documents, and generate AI summaries—all through a unified interface with multiple integration options.
 
-## Overview
+## 🚀 What You Can Do
 
-> **Note:** As of v0.8, the default extraction engine is `'auto'`. Content Core will automatically select the best extraction method based on your environment and available API keys, with a smart fallback order for both URLs and files. For files/documents, `'auto'` now tries Docling first, then falls back to simple extraction. You can override the engine if needed, but `'auto'` is recommended for most users.
+**Extract content from anywhere:**
+- 📄 **Documents** - PDF, Word, PowerPoint, Excel, Markdown, HTML, EPUB
+- 🎥 **Media** - Videos (MP4, AVI, MOV) with automatic transcription  
+- 🎵 **Audio** - MP3, WAV, M4A with speech-to-text conversion
+- 🌐 **Web** - Any URL with intelligent content extraction
+- 🖼️ **Images** - JPG, PNG, TIFF with OCR text recognition
+- 📦 **Archives** - ZIP, TAR, GZ with content analysis
 
-The primary goal of Content Core is to simplify the process of ingesting content from diverse origins. Whether you have raw text, a URL pointing to an article, or a local file like a video or markdown document, Content Core aims to extract the meaningful content for further use.
+**Process with AI:**
+- ✨ **Clean & format** extracted content automatically
+- 📝 **Generate summaries** with customizable styles (bullet points, executive summary, etc.)
+- 🎯 **Context-aware processing** - explain to a child, technical summary, action items
+- 🔄 **Smart engine selection** - automatically chooses the best extraction method
 
-## Key Features
+## 🛠️ Multiple Ways to Use
 
-*   **Multi-Source Extraction:** Handles content from:
-    *   Direct text strings.
-    *   Web URLs (using robust extraction methods).
-    *   Local files (including automatic transcription for video/audio files and parsing for text-based formats).
-*   **Intelligent Processing:** Applies appropriate extraction techniques based on the source type. See the [Processors Documentation](./docs/processors.md) for detailed information on how different content types are handled.
-*   **Smart Engine Selection:** By default, Content Core uses the `'auto'` engine, which:
-    * For URLs: Uses Firecrawl if `FIRECRAWL_API_KEY` is set, else tries Jina. Jina might fail because of rate limits, which can be fixed by adding `JINA_API_KEY`. If Jina failes, BeautifulSoup is used as a fallback.
-    * For files: Tries Docling extraction first (for robust document parsing), then falls back to simple extraction if needed.
-    * You can override this by specifying an engine, but `'auto'` is recommended for most users.
-*   **Content Cleaning (Optional):** Likely integrates with LLMs (via `prompter.py` and Jinja templates) to refine and clean the extracted content.
-*   **MCP Server:** Includes a Model Context Protocol (MCP) server for seamless integration with Claude Desktop and other MCP-compatible applications.
-*   **macOS Services:** Right-click context menu integration for Finder (extract and summarize files directly).
-*   **Asynchronous:** Built with `asyncio` for efficient I/O operations.
+### 🖥️ Command Line (Zero Install)
+```bash
+# Extract content from any source
+uvx --from "content-core" ccore https://example.com
+uvx --from "content-core" ccore document.pdf
+
+# Generate AI summaries  
+uvx --from "content-core" csum video.mp4 --context "bullet points"
+```
+
+### 🤖 Claude Desktop Integration
+One-click setup with Model Context Protocol (MCP) - extract content directly in Claude conversations.
+
+### 🔍 Raycast Extension  
+Smart auto-detection commands:
+- **Extract Content** - Full interface with format options
+- **Summarize Content** - 9 summary styles available
+- **Quick Extract** - Instant clipboard extraction
+
+### 🖱️ macOS Right-Click Integration
+Right-click any file in Finder → Services → Extract or Summarize content instantly.
+
+### 🐍 Python Library
+```python
+import content_core as cc
+
+# Extract from any source
+result = await cc.extract("https://example.com/article")
+summary = await cc.summarize_content(result, context="explain to a child")
+```
+
+## ⚡ Key Features
+
+*   **🎯 Intelligent Auto-Detection:** Automatically selects the best extraction method based on content type and available services
+*   **🔧 Smart Engine Selection:** 
+    * **URLs:** Firecrawl → Jina → BeautifulSoup fallback chain
+    * **Documents:** Docling → Enhanced PyMuPDF → Simple extraction fallback  
+    * **Media:** OpenAI Whisper transcription
+    * **Images:** OCR with multiple engine support
+*   **📊 Enhanced PDF Processing:** Advanced PyMuPDF engine with quality flags, table detection, and optional OCR for mathematical formulas
+*   **🌍 Multiple Integrations:** CLI, Python library, MCP server, Raycast extension, macOS Services
+*   **⚡ Zero-Install Options:** Use `uvx` for instant access without installation
+*   **🧠 AI-Powered Processing:** LLM integration for content cleaning and summarization
+*   **🔄 Asynchronous:** Built with `asyncio` for efficient processing
 
 ## Getting Started
 
@@ -245,6 +287,49 @@ Add to your `claude_desktop_config.json`:
 
 For detailed setup instructions, configuration options, and usage examples, see our [MCP Documentation](docs/mcp.md).
 
+## Enhanced PDF Processing
+
+Content Core features an optimized PyMuPDF extraction engine with significant improvements for scientific documents and complex PDFs.
+
+### Key Improvements
+
+- **🔬 Mathematical Formula Extraction**: Enhanced quality flags eliminate `<!-- formula-not-decoded -->` placeholders
+- **📊 Automatic Table Detection**: Tables converted to markdown format for LLM consumption
+- **🔧 Quality Text Rendering**: Better ligature, whitespace, and image-text integration
+- **⚡ Optional OCR Enhancement**: Selective OCR for formula-heavy pages (requires Tesseract)
+
+### Configuration for Scientific Documents
+
+For documents with heavy mathematical content, enable OCR enhancement:
+
+```yaml
+# In cc_config.yaml
+extraction:
+  pymupdf:
+    enable_formula_ocr: true      # Enable OCR for formula-heavy pages
+    formula_threshold: 3          # Min formulas per page to trigger OCR
+    ocr_fallback: true           # Graceful fallback if OCR fails
+```
+
+```python
+# Runtime configuration
+from content_core.config import set_pymupdf_ocr_enabled
+set_pymupdf_ocr_enabled(True)
+```
+
+### Requirements for OCR Enhancement
+
+```bash
+# Install Tesseract OCR (optional, for formula enhancement)
+# macOS
+brew install tesseract
+
+# Ubuntu/Debian
+sudo apt-get install tesseract-ocr
+```
+
+**Note**: OCR is optional - you get improved PDF extraction automatically without any additional setup.
+
 ## macOS Services Integration
 
 Content Core provides powerful right-click integration with macOS Finder, allowing you to extract and summarize content from any file without installation. Choose between clipboard or TextEdit output for maximum flexibility.
@@ -288,6 +373,50 @@ Create **4 convenient services** for different workflows:
 
 For complete setup instructions with copy-paste scripts, see [macOS Services Documentation](docs/macos.md).
 
+## Raycast Extension
+
+Content Core provides a powerful Raycast extension with smart auto-detection that handles both URLs and file paths seamlessly. Extract and summarize content directly from your Raycast interface without switching applications.
+
+### Quick Setup
+
+**From Raycast Store** (coming soon):
+1. Open Raycast and search for "Content Core"
+2. Install the extension by `luis_novo`
+3. Configure API keys in preferences
+
+**Manual Installation**:
+1. Download the extension from the repository
+2. Open Raycast → "Import Extension"
+3. Select the `raycast-content-core` folder
+
+### Commands
+
+**🔍 Extract Content** - Smart URL/file detection with full interface
+- Auto-detects URLs vs file paths in real-time
+- Multiple output formats (Text, JSON, XML)
+- Drag & drop support for files
+- Rich results view with metadata
+
+**📝 Summarize Content** - AI-powered summaries with customizable styles  
+- 9 different summary styles (bullet points, executive summary, etc.)
+- Auto-detects source type with visual feedback
+- One-click snippet creation and quicklinks
+
+**⚡ Quick Extract** - Instant extraction to clipboard
+- Type → Tab → Paste source → Enter
+- No UI, works directly from command bar
+- Perfect for quick workflows
+
+### Features
+
+- **Smart Auto-Detection**: Instantly recognizes URLs vs file paths
+- **Zero Installation**: Uses `uvx` for Content Core execution
+- **Rich Integration**: Keyboard shortcuts, clipboard actions, Raycast snippets
+- **All File Types**: Documents, videos, audio, images, archives
+- **Visual Feedback**: Real-time type detection with icons
+
+For detailed setup, configuration, and usage examples, see [Raycast Extension Documentation](docs/raycast.md).
+
 ## Using with Langchain
 
 For users integrating with the [Langchain](https://python.langchain.com/) framework, `content-core` exposes a set of compatible tools. These tools, located in the `src/content_core/tools` directory, allow you to leverage `content-core` extraction, cleaning, and summarization capabilities directly within your Langchain agents and chains.

{content_core-1.1.2 → content_core-1.2.0}/README.md

@@ -2,29 +2,70 @@
 
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 
-**Content Core** is a versatile Python library designed to extract and process content from various sources, providing a unified interface for handling text, web pages, and local files.
+**Content Core** is a powerful, AI-powered content extraction and processing platform that transforms any source into clean, structured content. Extract text from websites, transcribe videos, process documents, and generate AI summaries—all through a unified interface with multiple integration options.
 
-## Overview
+## 🚀 What You Can Do
 
-> **Note:** As of v0.8, the default extraction engine is `'auto'`. Content Core will automatically select the best extraction method based on your environment and available API keys, with a smart fallback order for both URLs and files. For files/documents, `'auto'` now tries Docling first, then falls back to simple extraction. You can override the engine if needed, but `'auto'` is recommended for most users.
+**Extract content from anywhere:**
+- 📄 **Documents** - PDF, Word, PowerPoint, Excel, Markdown, HTML, EPUB
+- 🎥 **Media** - Videos (MP4, AVI, MOV) with automatic transcription  
+- 🎵 **Audio** - MP3, WAV, M4A with speech-to-text conversion
+- 🌐 **Web** - Any URL with intelligent content extraction
+- 🖼️ **Images** - JPG, PNG, TIFF with OCR text recognition
+- 📦 **Archives** - ZIP, TAR, GZ with content analysis
 
-The primary goal of Content Core is to simplify the process of ingesting content from diverse origins. Whether you have raw text, a URL pointing to an article, or a local file like a video or markdown document, Content Core aims to extract the meaningful content for further use.
+**Process with AI:**
+- ✨ **Clean & format** extracted content automatically
+- 📝 **Generate summaries** with customizable styles (bullet points, executive summary, etc.)
+- 🎯 **Context-aware processing** - explain to a child, technical summary, action items
+- 🔄 **Smart engine selection** - automatically chooses the best extraction method
 
-## Key Features
+## 🛠️ Multiple Ways to Use
 
-*   **Multi-Source Extraction:** Handles content from:
-    *   Direct text strings.
-    *   Web URLs (using robust extraction methods).
-    *   Local files (including automatic transcription for video/audio files and parsing for text-based formats).
-*   **Intelligent Processing:** Applies appropriate extraction techniques based on the source type. See the [Processors Documentation](./docs/processors.md) for detailed information on how different content types are handled.
-*   **Smart Engine Selection:** By default, Content Core uses the `'auto'` engine, which:
-    * For URLs: Uses Firecrawl if `FIRECRAWL_API_KEY` is set, else tries Jina. Jina might fail because of rate limits, which can be fixed by adding `JINA_API_KEY`. If Jina failes, BeautifulSoup is used as a fallback.
-    * For files: Tries Docling extraction first (for robust document parsing), then falls back to simple extraction if needed.
-    * You can override this by specifying an engine, but `'auto'` is recommended for most users.
-*   **Content Cleaning (Optional):** Likely integrates with LLMs (via `prompter.py` and Jinja templates) to refine and clean the extracted content.
-*   **MCP Server:** Includes a Model Context Protocol (MCP) server for seamless integration with Claude Desktop and other MCP-compatible applications.
-*   **macOS Services:** Right-click context menu integration for Finder (extract and summarize files directly).
-*   **Asynchronous:** Built with `asyncio` for efficient I/O operations.
+### 🖥️ Command Line (Zero Install)
+```bash
+# Extract content from any source
+uvx --from "content-core" ccore https://example.com
+uvx --from "content-core" ccore document.pdf
+
+# Generate AI summaries  
+uvx --from "content-core" csum video.mp4 --context "bullet points"
+```
+
+### 🤖 Claude Desktop Integration
+One-click setup with Model Context Protocol (MCP) - extract content directly in Claude conversations.
+
+### 🔍 Raycast Extension  
+Smart auto-detection commands:
+- **Extract Content** - Full interface with format options
+- **Summarize Content** - 9 summary styles available
+- **Quick Extract** - Instant clipboard extraction
+
+### 🖱️ macOS Right-Click Integration
+Right-click any file in Finder → Services → Extract or Summarize content instantly.
+
+### 🐍 Python Library
+```python
+import content_core as cc
+
+# Extract from any source
+result = await cc.extract("https://example.com/article")
+summary = await cc.summarize_content(result, context="explain to a child")
+```
+
+## ⚡ Key Features
+
+*   **🎯 Intelligent Auto-Detection:** Automatically selects the best extraction method based on content type and available services
+*   **🔧 Smart Engine Selection:** 
+    * **URLs:** Firecrawl → Jina → BeautifulSoup fallback chain
+    * **Documents:** Docling → Enhanced PyMuPDF → Simple extraction fallback  
+    * **Media:** OpenAI Whisper transcription
+    * **Images:** OCR with multiple engine support
+*   **📊 Enhanced PDF Processing:** Advanced PyMuPDF engine with quality flags, table detection, and optional OCR for mathematical formulas
+*   **🌍 Multiple Integrations:** CLI, Python library, MCP server, Raycast extension, macOS Services
+*   **⚡ Zero-Install Options:** Use `uvx` for instant access without installation
+*   **🧠 AI-Powered Processing:** LLM integration for content cleaning and summarization
+*   **🔄 Asynchronous:** Built with `asyncio` for efficient processing
 
 ## Getting Started
 
@@ -208,6 +249,49 @@ Add to your `claude_desktop_config.json`:
 
 For detailed setup instructions, configuration options, and usage examples, see our [MCP Documentation](docs/mcp.md).
 
+## Enhanced PDF Processing
+
+Content Core features an optimized PyMuPDF extraction engine with significant improvements for scientific documents and complex PDFs.
+
+### Key Improvements
+
+- **🔬 Mathematical Formula Extraction**: Enhanced quality flags eliminate `<!-- formula-not-decoded -->` placeholders
+- **📊 Automatic Table Detection**: Tables converted to markdown format for LLM consumption
+- **🔧 Quality Text Rendering**: Better ligature, whitespace, and image-text integration
+- **⚡ Optional OCR Enhancement**: Selective OCR for formula-heavy pages (requires Tesseract)
+
+### Configuration for Scientific Documents
+
+For documents with heavy mathematical content, enable OCR enhancement:
+
+```yaml
+# In cc_config.yaml
+extraction:
+  pymupdf:
+    enable_formula_ocr: true      # Enable OCR for formula-heavy pages
+    formula_threshold: 3          # Min formulas per page to trigger OCR
+    ocr_fallback: true           # Graceful fallback if OCR fails
+```
+
+```python
+# Runtime configuration
+from content_core.config import set_pymupdf_ocr_enabled
+set_pymupdf_ocr_enabled(True)
+```
+
+### Requirements for OCR Enhancement
+
+```bash
+# Install Tesseract OCR (optional, for formula enhancement)
+# macOS
+brew install tesseract
+
+# Ubuntu/Debian
+sudo apt-get install tesseract-ocr
+```
+
+**Note**: OCR is optional - you get improved PDF extraction automatically without any additional setup.
+
 ## macOS Services Integration
 
 Content Core provides powerful right-click integration with macOS Finder, allowing you to extract and summarize content from any file without installation. Choose between clipboard or TextEdit output for maximum flexibility.
@@ -251,6 +335,50 @@ Create **4 convenient services** for different workflows:
 
 For complete setup instructions with copy-paste scripts, see [macOS Services Documentation](docs/macos.md).
 
+## Raycast Extension
+
+Content Core provides a powerful Raycast extension with smart auto-detection that handles both URLs and file paths seamlessly. Extract and summarize content directly from your Raycast interface without switching applications.
+
+### Quick Setup
+
+**From Raycast Store** (coming soon):
+1. Open Raycast and search for "Content Core"
+2. Install the extension by `luis_novo`
+3. Configure API keys in preferences
+
+**Manual Installation**:
+1. Download the extension from the repository
+2. Open Raycast → "Import Extension"
+3. Select the `raycast-content-core` folder
+
+### Commands
+
+**🔍 Extract Content** - Smart URL/file detection with full interface
+- Auto-detects URLs vs file paths in real-time
+- Multiple output formats (Text, JSON, XML)
+- Drag & drop support for files
+- Rich results view with metadata
+
+**📝 Summarize Content** - AI-powered summaries with customizable styles  
+- 9 different summary styles (bullet points, executive summary, etc.)
+- Auto-detects source type with visual feedback
+- One-click snippet creation and quicklinks
+
+**⚡ Quick Extract** - Instant extraction to clipboard
+- Type → Tab → Paste source → Enter
+- No UI, works directly from command bar
+- Perfect for quick workflows
+
+### Features
+
+- **Smart Auto-Detection**: Instantly recognizes URLs vs file paths
+- **Zero Installation**: Uses `uvx` for Content Core execution
+- **Rich Integration**: Keyboard shortcuts, clipboard actions, Raycast snippets
+- **All File Types**: Documents, videos, audio, images, archives
+- **Visual Feedback**: Real-time type detection with icons
+
+For detailed setup, configuration, and usage examples, see [Raycast Extension Documentation](docs/raycast.md).
+
 ## Using with Langchain
 
 For users integrating with the [Langchain](https://python.langchain.com/) framework, `content-core` exposes a set of compatible tools. These tools, located in the `src/content_core/tools` directory, allow you to leverage `content-core` extraction, cleaning, and summarization capabilities directly within your Langchain agents and chains.

{content_core-1.1.2 → content_core-1.2.0}/docs/processors.md

@@ -1,6 +1,6 @@
 # Content Core Processors
 
-**Note:** As of vNEXT, the default extraction engine is now `'auto'`. This means Content Core will automatically select the best extraction method based on your environment and available API keys, with a smart fallback order for both URLs and files. For files/documents, `'auto'` now tries Docling first, then falls back to simple extraction. See details below.
+**Note:** As of vNEXT, the default extraction engine is now `'auto'`. This means Content Core will automatically select the best extraction method based on your environment and available API keys, with a smart fallback order for both URLs and files. For files/documents, `'auto'` now tries Docling first, then falls back to enhanced PyMuPDF extraction (with quality flags and table detection), then to basic simple extraction. See details below.
 
 This document provides an overview of the content processors available in Content Core. These processors are responsible for extracting and handling content from various sources and file types.
 
@@ -42,14 +42,35 @@ Content Core uses a modular approach to process content from different sources.
 - **Returned Data**: Transcribed text from the media content.
 - **Location**: `src/content_core/processors/transcription.py`
 
-### 5. **Docling Processor**
+### 5. **Enhanced PyMuPDF Processor (Simple Engine)**
+- **Purpose**: Optimized PDF extraction using PyMuPDF with enhanced quality flags, table detection, and optional OCR
+- **Supported Input**: PDF files, EPUB files
+- **Returned Data**: High-quality text extraction with proper mathematical symbols, converted tables in markdown format
+- **Location**: `src/content_core/processors/pdf.py`
+- **Key Enhancements**:
+  - **Quality Flags**: Automatically applies `TEXT_PRESERVE_LIGATURES`, `TEXT_PRESERVE_WHITESPACE`, and `TEXT_PRESERVE_IMAGES` for better text rendering
+  - **Mathematical Formula Support**: Eliminates `<!-- formula-not-decoded -->` placeholders by properly extracting mathematical symbols (∂, ∇, ρ, etc.)
+  - **Table Detection**: Automatic detection and conversion of tables to markdown format for LLM consumption
+  - **Selective OCR**: Optional OCR enhancement for formula-heavy pages (requires Tesseract installation)
+- **Configuration**: Configure OCR enhancement in `cc_config.yaml`:
+  ```yaml
+  extraction:
+    pymupdf:
+      enable_formula_ocr: false    # Enable OCR for formula-heavy pages
+      formula_threshold: 3         # Min formulas per page to trigger OCR
+      ocr_fallback: true          # Graceful fallback if OCR fails
+  ```
+- **Performance**: Standard extraction maintains baseline performance; OCR only triggers selectively on formula-heavy pages
+
+### 6. **Docling Processor**
 - **Purpose**: Use Docling library for rich document parsing (PDF, DOCX, XLSX, PPTX, Markdown, AsciiDoc, HTML, CSV, images).
 - **Supported Input**: PDF, DOCX, XLSX, PPTX, Markdown, AsciiDoc, HTML, CSV, Images (PNG, JPEG, TIFF, BMP).
 - **Returned Data**: Content converted to configured format (markdown, html, json).
 - **Location**: `src/content_core/processors/docling.py`
 - **Default Document Engine (`auto`) Logic for Files/Documents**:
     - Tries the `'docling'` extraction method first (robust document parsing for supported types).
-    - If `'docling'` fails or is not supported, automatically falls back to simple extraction (fast, lightweight for supported types).
+    - If `'docling'` fails or is not supported, automatically falls back to enhanced PyMuPDF extraction (fast, with quality flags and table detection).
+    - Final fallback to basic simple extraction if needed.
     - You can explicitly specify `'docling'` or `'simple'` as the document engine, but `'auto'` is now the default and recommended for most users.
 - **Configuration**: Activate the Docling engine in `cc_config.yaml` or custom config:
   ```yaml