Dracor (Drama Corpora Project)

🚀 Task Instruction for Analyzing Character ID Marking Issues in Historical Plays Using DraCor

This project aims to detect and fix potential errors in character ID markings by analyzing historical play scripts from the DraCor database. Specifically, we need to select a play from the DraCor database, conduct a comprehensive analysis of character relationships and the full - text structure, and identify various issues in character ID markings.

🚀 Quick Start

✨ Features

• Analyze historical play scripts from the DraCor database.
• Detect and fix potential errors in character ID markings.
• Generate a detailed report on the detected issues.

📦 Installation

• Python Version: It is recommended to use Python 3.10 or higher.
• Install Dependencies: Install necessary libraries, including the Model Context Protocol Python SDK.

💻 Usage Examples

Basic Usage

The following steps show how to perform the analysis:

1. Select a Play: Choose a specific play from the DraCor database.
2. Analyze Character Relationships: Carefully examine the interactions and relationships between characters in the play to ensure each character has a unique ID marking.
3. Analyze the Full - Text Structure: Conduct a structured analysis of the full text of the play, including dramatic plots and scenes, and note the diversity of character names or historical spelling variants.
4. Detect Character ID Marking Issues:
   • Check for spelling differences in character names.
   • Confirm if there is any confusion or overlap of character names.
   • Pay attention to historical spelling variants in the play.
   • Identify whether the character IDs in stage directions are consistent with other parts.

📚 Documentation

Analysis Steps

1. Play Selection: First, select a specific play from the DraCor database.
2. Character Relationship Analysis: Thoroughly check the interactions and relationships between characters in the play to ensure that each character has a unique ID marking.
3. Full - Text Structure Analysis: Structurally analyze the full text of the play, including dramatic plots and scenes, and be aware of the diversity of character names or historical spelling variants.
4. Character ID Marking Issue Detection:
   • Check for spelling differences in character names.
   • Confirm if there is any confusion or overlap of character names.
   • Note the presence of historical spelling variants in the play.
   • Identify whether the character IDs in stage directions are consistent with other parts.

Report Structure

Based on the discovered issues, we need to compile a detailed report and organize the following information in a table:

Data Extraction Using the DraCor API

Resource Access

1. Get the List of All Plays: Use the API endpoint /corpora to obtain the available play libraries.
2. Select a Specific Play: Select the play to be studied through the /plays/{corpus_name} interface.
3. Extract Character Information: Use the /characters/{corpus_name}/{play_name} interface to obtain character data from the play.
4. Extract the Full Text: Use /full_text/{corpus_name}/{play_name} to get the full - text content of the play.

Tool Usage

1. Search for Plays: Use the search_plays tool to search for plays in the DraCor database based on keywords or other criteria.
2. Comparative Analysis: If you need to compare multiple plays, use this tool to analyze the similarities and differences between different plays.

Prompt Template

When conducting specific analysis, you can use the following prompt template:

"Your task is to analyze historical plays from the DraCor database and detect potential issues in character ID markings. Specifically:
1. Select a play and conduct a comprehensive analysis of character relationships, the full - text structure, and the play structure.
2. Detect all possible marking errors, including but not limited to:
   - Spelling variants of character names
   - Confusion or overlap of character names
   - Historical spelling variants
   - Consistency issues of character IDs in stage directions with other parts
3. Compile a detailed report listing the following information in a table:
   - Text ID (unique identifier of the play)
   - Character ID in the existing database
   - Problematic variants found in the text
   - Type of error (such as spelling difference, confusion, etc.)
   - Specific problem description and cause analysis

Please analyze the following play: [Play Name]"

Project Configuration and Execution

Environment Setup

• Python Version: It is recommended to use Python 3.10 or higher.
• Install Dependencies: Install necessary libraries, including the Model Context Protocol Python SDK.

Execution Steps

1. Initialize the Project Directory Structure:
   • Create a new folder to store project - related files and data.
2. Configure the Settings File:
   • Create and edit the settings.py file to define parameters such as the base address of the DraCor API and RATE_LIMIT.
3. Write the MCP Script:
   • Use the Model Context Protocol to write a script to implement functions such as play selection, data extraction, and error detection.
4. Execute the Analysis and Generate a Report:
   • Start the script to automatically complete the play analysis and generate a problem report.

Report Generation

After the analysis is completed, the script will automatically generate a PDF or Excel file containing a summary of the issues and recommended repair solutions.

🔧 Technical Details

In the entire analysis process, we need to pay special attention to the following points:

1. Data Source Reliability: Ensure that the DraCor database used is up - to - date and from a reliable source.
2. Data Cleaning: Before in - depth analysis, perform preliminary cleaning on the extracted data, removing or correcting obvious errors or irrelevant information.
3. Multi - Angle Verification: Improve the accuracy of the analysis results by cross - comparing information from different sources or verifying with multiple methods.

📄 License

No license information is provided in the original document.

📚 Appendix

References

• Official documentation of the DraCor database
• User manual of the Model Context Protocol SDK
• Relevant academic papers or research reports

Contact Information

If you have any questions or suggestions, please contact the project administrator: [Contact Information]

⚠️ Important Note

This analysis instruction needs to be appropriately adjusted according to the content and data structure of the specific play.