#!/usr/bin/env python3 """ Novel Character Relationship Graph Generator (Corrected Names) Extracts entities and relationships from novel character notes and generates visualizable relationship graph. """ import os import re import json from pathlib import Path from typing import Dict, List, Any class NovelCharacterGraph: def __init__(self, characters_path: str): self.characters_path = Path(characters_path) self.characters = {} self.relationships = [] def load_characters(self): """Load all character markdown files""" md_files = list(self.characters_path.rglob('*.md')) for md_file in md_files: self.load_character_file(md_file) def load_character_file(self, file_path: Path): """Load and parse a character file""" with open(file_path, 'r', encoding='utf-8') as f: content = f.read() # Extract name (first H1) title_match = re.search(r'^#\s+(.+)$', content, re.MULTILINE) name = title_match.group(1) if title_match else file_path.stem # Skip relationship graph file if '关系图谱' in name: return # Generate ID char_id = self.generate_id(name) # Extract properties properties = { 'name': name, 'file': str(file_path.relative_to(self.characters_path.parent)) } # Extract age age_match = re.search(r'\*\*年龄\*\*:\s*(\d+)', content) if age_match: properties['age'] = age_match.group(1) # Extract gender gender_match = re.search(r'\*\*性别\*\*:\s*([男女])', content) if gender_match: properties['gender'] = gender_match.group(1) # Extract occupation occupation_match = re.search(r'\*\*职业\*\*:\s*([^\n]+)', content) if occupation_match: properties['occupation'] = occupation_match.group(1).strip() # Extract status status_match = re.search(r'\*\*状态\*\*:\s*([^\n]+)', content) if status_match: properties['status'] = status_match.group(1).strip() # Extract relationships from [[link]] format link_matches = re.findall(r'\[\[([^\]]+)\]\]', content) for link in link_matches: link_id = self.generate_id(link) self.relationships.append({ 'from': char_id, 'to': link_id, 'type': 'mentioned' }) # Extract specific relationships from content self.extract_relationships_from_content(content, char_id) # Add character self.characters[char_id] = { 'id': char_id, 'type': 'Character', 'properties': properties } def extract_relationships_from_content(self, content: str, char_id: str): """Extract relationships from content sections""" # Family relationships if '## 家庭关系' in content: family_section = re.search(r'## 家庭关系\s*\n(.*?)(?=##|$)', content, re.DOTALL) if family_section: # Extract mother mother_match = re.search(r'- \*\*母亲\*\*: \[\[([^\]]+)\]\]', family_section.group(1)) if mother_match: mother_id = self.generate_id(mother_match.group(1)) self.relationships.append({ 'from': char_id, 'to': mother_id, 'type': 'mother_of' }) # Extract father father_match = re.search(r'- \*\*父亲\*\*: \[\[([^\]]+)\]\]', family_section.group(1)) if father_match: father_id = self.generate_id(father_match.group(1)) self.relationships.append({ 'from': char_id, 'to': father_id, 'type': 'father_of' }) # Extract son son_match = re.search(r'- \*\*儿子\*\*: \[\[([^\]]+)\]\]', family_section.group(1)) if son_match: son_id = self.generate_id(son_match.group(1)) self.relationships.append({ 'from': char_id, 'to': son_id, 'type': 'son_of' }) # Extract wife wife_match = re.search(r'- \*\*妻子\*\*: \[\[([^\]]+)\]\]', family_section.group(1)) if wife_match: wife_id = self.generate_id(wife_match.group(1)) self.relationships.append({ 'from': char_id, 'to': wife_id, 'type': 'wife_of' }) # Extract husband husband_match = re.search(r'- \*\*丈夫\*\*: \[\[([^\]]+)\]\]', family_section.group(1)) if husband_match: husband_id = self.generate_id(husband_match.group(1)) self.relationships.append({ 'from': char_id, 'to': husband_id, 'type': 'husband_of' }) def generate_id(self, name: str) -> str: """Generate consistent ID from name""" normalized = re.sub(r'[^a-z0-9\u4e00-\u9fff]+', '_', name.lower()).strip('_') return f"char_{normalized}" def visualize_text(self): """Generate ASCII text visualization""" print("=" * 60) print("《杀了婆婆的我却无人追责？》人物关系图谱") print("=" * 60) # Print characters print("\n【人物列表】") for char_id, char in self.characters.items(): props = char['properties'] print(f"\n {props.get('name', 'Unknown')}") if 'age' in props: print(f" 年龄: {props['age']}") if 'gender' in props: print(f" 性别: {props['gender']}") if 'occupation' in props: print(f" 职业: {props['occupation']}") if 'status' in props: print(f" 状态: {props['status']}") # Print relationships print("\n【人物关系】") for rel in self.relationships: from_char = self.characters.get(rel['from']) to_char = self.characters.get(rel['to']) if from_char and to_char: from_name = from_char['properties']['name'] to_name = to_char['properties']['name'] rel_type = rel['type'] print(f"\n {from_name} --[{rel_type}]--> {to_name}") # Print ASCII graph print("\n【ASCII 关系图】") self.print_ascii_graph() def print_ascii_graph(self): """Print simple ASCII relationship graph""" print(""" ┌─────────────┐ │ 顾国强 │ │ (已故) │ └──────┬──────┘ │ │ 夫妻 │ ┌──────▼──────┐ │ 刘婉清 │ │ (68岁) │ │ 婆婆 │ └──────┬──────┘ │ ┌───────────┼───────────┐ │ │ │ 母子 控制压迫 婆媳 │ │ │ ┌────▼────┐ │ ┌────▼────┐ │ 顾长风 │ │ │ 叶知秋 │ │ (35岁) │ │ │ (28岁) │ │ 丈夫 │ │ │ 女主 │ └────┬────┘ │ └────┬────┘ │ │ │ 夫妻 想要 记忆 │ 遗产 混乱 │ │ │ └───────────┼───────────┘ │ 调查案件 │ ┌──────▼──────┐ │ 张明远 │ │ (所长) │ └─────────────┘ """) def export_json(self, output_path: str): """Export to JSON for further processing""" output = { 'characters': list(self.characters.values()), 'relationships': self.relationships } with open(output_path, 'w', encoding='utf-8') as f: json.dump(output, f, ensure_ascii=False, indent=2) print(f"\n✅ 导出到: {output_path}") if __name__ == '__main__': import argparse parser = argparse.ArgumentParser(description='Novel Character Relationship Graph (Corrected Names)') parser.add_argument('--path', type=str, default='/root/.openclaw/workspace/novel/characters', help='Path to character notes') parser.add_argument('--export', type=str, help='Export to JSON file') args = parser.parse_args() # Create graph graph = NovelCharacterGraph(args.path) # Load characters graph.load_characters() # Visualize graph.visualize_text() # Export if requested if args.export: graph.export_json(args.export)