Blame for archive/extract_batch_04_complete.py

#!/usr/bin/env python3
"""
完整整合Batch 04 - 所有剩余292条规则
从Google Notebook提取的578条规则中，整合所有未添加的规则
基于成功的integrate_all_rules.py模式
"""

import json
import re

# 读取Google Notebook提取的全部578条规则
print("=" * 80)
print("📖 Batch 04 规则提取 - 完整版")
print("=" * 80)
print("📖 读取Google Notebook规则文件...")

file_path = '/Volumes/sparksverse/agent-knowledge/mingli-knowledge/eastern/ziwei/interpretations/02-practical-divination rules.md'
with open(file_path, 'r', encoding='utf-8') as f:
    content = f.read()

# 从markdown中提取JSON数组
print("🔄 从Markdown提取JSON数组...")
start_idx = content.find('[')
end_idx = content.rfind(']')

if start_idx == -1 or end_idx == -1:
    print("❌ 未找到JSON数组边界")
    exit(1)

json_str = content[start_idx:end_idx+1]
print(f"✅ 找到JSON数组 (字符位置: {start_idx} - {end_idx})")

# 修复age_range字段的格式错误
print("🔧 修复已知格式问题...")
json_str = re.sub(r'"age_range"\s*:\s*,', '"age_range": [20, 70],', json_str)
json_str = re.sub(r'"age_range"\s*:\s*null', '"age_range": [20, 70]', json_str)
json_str = re.sub(r'"age_range"\s*:\s*\n', '"age_range": [20, 70],\n', json_str)

# 解析JSON
print("📊 解析JSON数据...")
try:
    all_rules = json.loads(json_str)
    print(f"✅ 成功解析 {len(all_rules)} 条规则")
except json.JSONDecodeError as e:
    print(f"❌ JSON解析错误: {e}")
    print(f"错误位置: 第{e.lineno}行，第{e.colno}列")
    exit(1)

# 读取已整合的规则ID
print("\n📊 读取已整合规则...")
import sys
sys.path.insert(0, '.')

try:
    from star_combination_rules import STAR_COMBINATION_RULES
    integrated_ids = set([rule['id'] for rule in STAR_COMBINATION_RULES])
    print(f"✅ 已整合规则数: {len(integrated_ids)}")
except Exception as e:
    print(f"❌ 无法读取现有规则库: {e}")
    exit(1)

# 筛选出未整合的规则
new_rules = []
for rule in all_rules:
    rule_id = rule.get('id', '')
    if rule_id not in integrated_ids:
        new_rules.append(rule)

print(f"\n📈 统计结果:")
print(f"   总规则数: {len(all_rules)}")
print(f"   已整合: {len(integrated_ids)}")
print(f"   待整合: {len(new_rules)}")
print(f"   覆盖率: {len(integrated_ids)/len(all_rules)*100:.1f}%")

if len(new_rules) == 0:
    print("\n✅ 所有规则都已经整合完毕！")
    exit(0)

# 为未整合的规则重新分配ID (从SC601开始)
print(f"\n🔢 重新分配规则ID...")
next_id = 601
id_mapping = {}

for rule in new_rules:
    old_id = rule['id']
    new_id = f'SC{next_id:03d}'
    id_mapping[old_id] = new_id
    rule['id'] = new_id
    next_id += 1

print(f"✅ 重新分配完成: SC601-SC{next_id-1:03d} ({len(new_rules)}条)")

# 修复格式问题
print("\n🔧 修复格式问题...")
fixed_count = 0

for rule in new_rules:
    # 修复age_range
    if 'age_range' not in rule or rule['age_range'] is None or rule['age_range'] == '':
        rule['age_range'] = [20, 70]
        fixed_count += 1

    # 修复effect_level中的"微WEAK"
    if rule.get('effect_level') == '微WEAK':
        rule['effect_level'] = 'VERY_WEAK'
        fixed_count += 1

    # 确保effect_level是有效值
    valid_levels = ['极强', '强', '中', '弱', '微弱', 'VERY_WEAK', 'STRONG', 'MEDIUM', 'WEAK', 'VERY_STRONG']
    if rule.get('effect_level') not in valid_levels:
        rule['effect_level'] = '中'
        fixed_count += 1

print(f"✅ 修复 {fixed_count} 处格式问题")

# 生成Python代码格式的规则
print("\n📝 生成Python代码...")

def format_rule_to_python(rule):
    """将规则转换为Python代码格式，使用正确的Enum语法"""

    # Category映射
    category_map = {
        '性格特质': 'RuleCategory.PERSONALITY',
        '事业财运': 'RuleCategory.CAREER',
        '婚姻感情': 'RuleCategory.RELATIONSHIP',
        '健康状况': 'RuleCategory.HEALTH',
        '运势走向': 'RuleCategory.FORTUNE',
        '才华能力': 'RuleCategory.TALENT',
        '人际交往': 'RuleCategory.SOCIAL'
    }

    # EffectLevel映射
    effect_map = {
        '极强': 'EffectLevel.VERY_STRONG',
        '强': 'EffectLevel.STRONG',
        '中': 'EffectLevel.MEDIUM',
        '弱': 'EffectLevel.WEAK',
        '微弱': 'EffectLevel.VERY_WEAK',
        'VERY_WEAK': 'EffectLevel.VERY_WEAK',
        'VERY_STRONG': 'EffectLevel.VERY_STRONG',
        'STRONG': 'EffectLevel.STRONG',
        'MEDIUM': 'EffectLevel.MEDIUM',
        'WEAK': 'EffectLevel.WEAK'
    }

    category = category_map.get(rule['category'], 'RuleCategory.PERSONALITY')
    effect = effect_map.get(rule['effect_level'], 'EffectLevel.MEDIUM')

    # 格式化stars_required
    stars_str = str(rule['stars_required'])

    # 格式化palace_types
    palace_str = str(rule['palace_types'])

    # 格式化conditions (使用安全的格式化方式)
    conditions = rule['conditions']
    conditions_str = "{\n        'same_palace': " + str(conditions.get('same_palace', False)) + ",\n"
    conditions_str += "        'transformations': " + str(conditions.get('transformations')) + ",\n"
    conditions_str += "        'brightness': " + str(conditions.get('brightness')) + ",\n"
    conditions_str += "        'palace_position': " + str(conditions.get('palace_position')) + "\n    }"

    # 格式化interpretations
    interp = rule['interpretations']
    interp_str = "{\n        'core_meaning': " + repr(interp.get('core_meaning', '')) + ",\n"
    interp_str += "        'personality': " + str(interp.get('personality', [])) + ",\n"
    interp_str += "        'career': " + str(interp.get('career', [])) + ",\n"
    interp_str += "        'relationship': " + str(interp.get('relationship', [])) + ",\n"
    interp_str += "        'fortune_timing': " + repr(interp.get('fortune_timing', '')) + ",\n"
    interp_str += "        'warnings': " + str(interp.get('warnings', [])) + "\n    }"

    return f"""    {{
        "id": "{rule['id']}",
        "name": "{rule['name']}",
        "category": {category},
        "stars_required": {stars_str},
        "palace_types": {palace_str},
        "conditions": {conditions_str},
        "interpretations": {interp_str},
        "effect_level": {effect},
        "compatibility_score": {rule['compatibility_score']},
        "age_range": {rule['age_range']},
        "source": "{rule['source']}"
    }}"""

# 生成所有新规则的Python代码
print("🔄 格式化292条规则...")
new_rules_code = ',\n'.join([format_rule_to_python(rule) for rule in new_rules])

# 保存为Python文件
output = f'''"""
Google Notebook 提取规则 - Batch 04 (全部剩余规则)
规则数量: {len(new_rules)}条 (SC601-SC{next_id-1:03d})
提取日期: 2025-12-13
来源: 南北派实战断诀 (138页专业典籍)
覆盖率: 新增后将达到 {(len(integrated_ids) + len(new_rules))/len(all_rules)*100:.1f}%
"""

from star_combination_rules import RuleCategory, EffectLevel

BATCH_04_RULES = [
{new_rules_code}
]
'''

output_file = 'rule_extraction_batch_04.py'
with open(output_file, 'w', encoding='utf-8') as f:
    f.write(output)

print(f"✅ 已生成: {output_file}")
print(f"   包含 {len(new_rules)} 条新规则")
print(f"   ID范围: SC601-SC{next_id-1:03d}")
print(f"   文件大小: {len(output) // 1024}KB")

# 统计信息
print("\n" + "=" * 80)
print("📊 Batch 04 新增规则分类统计")
print("=" * 80)

categories = {}
for rule in new_rules:
    cat = rule['category']
    categories[cat] = categories.get(cat, 0) + 1

for cat, count in sorted(categories.items(), key=lambda x: -x[1]):
    print(f"  {cat}: {count}条")

print("\n" + "=" * 80)
print("📈 规则库扩展进度总览")
print("=" * 80)
print(f"  当前版本: v3.11.0 (320条)")
print(f"  Batch 04新增: {len(new_rules)}条")
print(f"  新版本: v3.12.0 ({len(integrated_ids) + len(new_rules)}条)")
print(f"  Google Notebook总提取: {len(all_rules)}条")
print(f"  新覆盖率: {(len(integrated_ids) + len(new_rules))/len(all_rules)*100:.1f}%")
print(f"  增长率: +{len(new_rules)/len(integrated_ids)*100:.1f}% (相比v3.11.0)")
print("=" * 80)

print("\n✅ Batch 04整合准备完成！")
print(f"📝 下一步: 运行 merge_batch_04.py 将这{len(new_rules)}条规则合并到系统中")
print(f"🚀 预期效果: 匹配率从2.5%提升至8-10% (基于专家调查)")