Files
DEMO-AGENT/tests/test_regulatory_info_package_field_extract.py

89 lines
4.0 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
import json
from review_agent.regulatory_info_package.schemas import InstructionExtractResult
from review_agent.regulatory_info_package.services.field_extract import extract_fields_by_rules, run_parallel_extract
def test_extract_fields_by_rules_finds_product_name_and_storage():
instruction = InstructionExtractResult(
source_file_name="目标产品说明书.docx",
paragraphs=["产品名称:新型冠状病毒检测试剂盒", "储存条件2-8℃保存"],
sections={},
tables=[],
component_tables=[],
front_text="产品名称:新型冠状病毒检测试剂盒\n储存条件2-8℃保存",
)
result = extract_fields_by_rules(instruction)
assert result["product_name"]["value"] == "新型冠状病毒检测试剂盒"
assert result["storage_condition"]["value"] == "2-8℃保存"
def test_extract_fields_by_rules_uses_registrant_or_manufacturer_for_applicant():
instruction = InstructionExtractResult(
source_file_name="目标产品说明书.docx",
paragraphs=[
"注册人/售后服务单位名称:卡尤迪生物科技宜兴有限公司",
"生产企业名称:卡尤迪生物科技宜兴有限公司",
"生产企业住所宜兴经济技术开发区杏里路10号宜兴光电产业园4幢101室、102室",
"联系方式: 0510-80330909, 0510-80330919",
"生产地址江苏省宜兴经济技术开发区杏里路10号宜兴光电产业园4幢102室",
],
sections={},
tables=[],
component_tables=[],
front_text="",
)
result = extract_fields_by_rules(instruction)
assert result["applicant_name"]["value"] == "卡尤迪生物科技宜兴有限公司"
assert result["manufacturer_name"]["value"] == "卡尤迪生物科技宜兴有限公司"
assert result["applicant_address"]["value"] == "宜兴经济技术开发区杏里路10号宜兴光电产业园4幢101室、102室"
assert result["applicant_contact"]["value"] == "0510-80330909, 0510-80330919"
assert result["production_address"]["value"] == "江苏省宜兴经济技术开发区杏里路10号宜兴光电产业园4幢102室"
def test_extract_fields_by_rules_serializes_component_table_and_notes():
instruction = InstructionExtractResult(
source_file_name="目标产品说明书.docx",
paragraphs=[],
sections={"【主要组成成分】": "表1 规格A大包装试剂盒组成成分\n注:不同批号试剂盒中各组分不得互换使用。"},
tables=[],
component_tables=[
{
"header": ["组分", "主要组成成分", "规格24人份/盒)", "规格48人份/盒)"],
"rows": [
["PCR反应液 I", "逆转录酶、Taq酶", "840μL/管×1管", "840μL/管×2管"],
["阳性对照品", "含目的片段的假病毒", "600μL/管×2管", "1200μL/管×2管"],
],
}
],
front_text="",
)
result = extract_fields_by_rules(instruction)
payload = json.loads(result["component_table"]["value"])
assert payload["header"][0:2] == ["组分", "主要组成成分"]
assert payload["rows"][0][0] == "PCR反应液 I"
assert result["component_notes"]["value"] == "表1 规格A大包装试剂盒组成成分\n注:不同批号试剂盒中各组分不得互换使用。"
def test_run_parallel_extract_keeps_rule_result_when_llm_fails():
instruction = InstructionExtractResult(
source_file_name="目标产品说明书.docx",
paragraphs=["产品名称:测试产品"],
sections={},
tables=[],
component_tables=[],
front_text="产品名称:测试产品",
)
result = run_parallel_extract(instruction, llm_extract_func=lambda _instruction: (_ for _ in ()).throw(ValueError("bad llm")))
assert result["regex_results"]["product_name"]["value"] == "测试产品"
assert result["llm_results"] == {}
assert result["llm_error"]