131 lines
4.4 KiB
Python
Executable File
131 lines
4.4 KiB
Python
Executable File
#!/usr/bin/env python3
|
||
"""
|
||
批量更新提示词文件，同步到20个阶段
|
||
"""
|
||
|
||
import re
|
||
from pathlib import Path
|
||
|
||
PROMPTS_DIR = Path("/home/xia-lab/wutx/00test/bbav5/prompts")
|
||
|
||
# 阶段名称映射（旧 -> 新）
|
||
STAGE_MAPPINGS = {
|
||
# 核心阶段重命名
|
||
'`identify`': '`gene-identify`',
|
||
'`motif`': '`motif-analysis`',
|
||
'`domain`': '`domain-analysis`',
|
||
'`promoter`': '`promoter-analysis`',
|
||
|
||
# 确保新阶段名称一致性
|
||
'阶段1：基因家族鉴定': '阶段1：基因家族鉴定 (`gene-identify`)',
|
||
'阶段2：系统发育分析': '阶段2：系统发育分析 (`phylogeny`)',
|
||
'阶段3：保守基序分析': '阶段3：保守基序分析 (`motif-analysis`)',
|
||
'阶段4：结构域分析': '阶段4：结构域分析 (`domain-analysis`)',
|
||
'阶段5：蛋白结构分析': '阶段5：蛋白结构分析 (`structure`)',
|
||
'阶段6：启动子分析': '阶段6：启动子分析 (`promoter-analysis`)',
|
||
'阶段7：共线性分析': '阶段7：共线性分析 (`synteny`)',
|
||
'阶段8：染色体定位': '阶段8：染色体定位 (`karyotype`)',
|
||
'阶段9：蛋白特性分析': '阶段9：蛋白特性分析 (`pep`)',
|
||
'阶段10：表达模式分析': '阶段10：表达模式分析 (`expression`)',
|
||
'阶段11：基因注释': '阶段11：基因注释 (`annotation`)',
|
||
|
||
# 新增阶段
|
||
'阶段12：Ka/Ks分析': '阶段12：Ka/Ks分析 (`kaks`)',
|
||
'阶段13：种间分析': '阶段13：种间分析 (`interspecies`)',
|
||
'阶段14：蛋白互作分析': '阶段14：蛋白互作分析 (`ppi`)',
|
||
'阶段15：基因家族汇总': '阶段15：基因家族汇总 (`summary`)',
|
||
'阶段16：RNA-seq质控': '阶段16：RNA-seq质控 (`rnaseq-qc`)',
|
||
'阶段17：RNA-seq比对': '阶段17：RNA-seq比对 (`rnaseq-align`)',
|
||
'阶段18：RNA-seq定量': '阶段18：RNA-seq定量 (`rnaseq-quant`)',
|
||
'阶段19：差异表达分析': '阶段19：差异表达分析 (`rnaseq-de`)',
|
||
'阶段20：富集分析': '阶段20：富集分析 (`rnaseq-enrich`)',
|
||
}
|
||
|
||
# 需要更新的文件
|
||
FILES_TO_UPDATE = [
|
||
'execution_agent.md',
|
||
'result_parser_agent.md',
|
||
'validator_agent.md',
|
||
'diagnosis_agent.md',
|
||
]
|
||
|
||
def update_file(filepath: Path) -> dict:
|
||
"""更新单个文件"""
|
||
content = filepath.read_text(encoding='utf-8')
|
||
original_content = content
|
||
|
||
changes = []
|
||
|
||
# 应用映射
|
||
for old, new in STAGE_MAPPINGS.items():
|
||
if old in content:
|
||
count = content.count(old)
|
||
content = content.replace(old, new)
|
||
changes.append(f"'{old}' -> '{new}' ({count}处)")
|
||
|
||
# 检查是否需要更新阶段数量说明
|
||
if '11个阶段' in content:
|
||
content = content.replace('11个阶段', '20个阶段')
|
||
changes.append("'11个阶段' -> '20个阶段'")
|
||
|
||
if '标准分析流程（11个阶段）' in content:
|
||
content = content.replace('标准分析流程（11个阶段）', '标准分析流程（20个阶段）')
|
||
changes.append("更新标题")
|
||
|
||
# 保存文件
|
||
if content != original_content:
|
||
filepath.write_text(content, encoding='utf-8')
|
||
return {
|
||
'file': filepath.name,
|
||
'updated': True,
|
||
'changes': changes
|
||
}
|
||
else:
|
||
return {
|
||
'file': filepath.name,
|
||
'updated': False,
|
||
'changes': []
|
||
}
|
||
|
||
def main():
|
||
print("=" * 60)
|
||
print("批量更新提示词文件")
|
||
print("=" * 60)
|
||
print()
|
||
|
||
results = []
|
||
for filename in FILES_TO_UPDATE:
|
||
filepath = PROMPTS_DIR / filename
|
||
if filepath.exists():
|
||
result = update_file(filepath)
|
||
results.append(result)
|
||
|
||
status = "✅ 已更新" if result['updated'] else "⏭️ 无需更新"
|
||
print(f"{status}: {filename}")
|
||
|
||
if result['changes']:
|
||
for change in result['changes']:
|
||
print(f" - {change}")
|
||
else:
|
||
print(f"❌ 文件不存在: {filename}")
|
||
|
||
print()
|
||
print("=" * 60)
|
||
print("更新汇总")
|
||
print("=" * 60)
|
||
|
||
updated_count = sum(1 for r in results if r['updated'])
|
||
print(f"已更新文件: {updated_count}/{len(FILES_TO_UPDATE)}")
|
||
print()
|
||
|
||
for r in results:
|
||
if r['updated']:
|
||
print(f"✅ {r['file']}")
|
||
for change in r['changes']:
|
||
print(f" - {change}")
|
||
|
||
print("=" * 60)
|
||
|
||
if __name__ == "__main__":
|
||
main()
|