62 lines
2.0 KiB
Python
62 lines
2.0 KiB
Python
from pathlib import Path
|
||
|
||
from review_agent.regulatory_review.services.text_extract import extract_text
|
||
|
||
|
||
def test_extract_text_reads_plain_text(tmp_path):
|
||
path = tmp_path / "说明书.txt"
|
||
path.write_text("产品名称：甲胎蛋白检测试剂盒\n储存条件：2-8℃", encoding="utf-8")
|
||
|
||
result = extract_text(path)
|
||
|
||
assert "甲胎蛋白" in result.text
|
||
assert result.status == "success"
|
||
assert result.content_hash
|
||
|
||
|
||
def test_extract_text_keeps_wrapped_product_name(tmp_path):
|
||
path = tmp_path / "申请表.txt"
|
||
path.write_text(
|
||
"产品名称：呼吸道合胞病毒、肺炎支原体核酸检测试剂盒\n"
|
||
"（荧光PCR法）\n"
|
||
"型号规格：24人份/盒\n",
|
||
encoding="utf-8",
|
||
)
|
||
|
||
result = extract_text(path)
|
||
|
||
assert result.field_candidates["产品名称"] == "呼吸道合胞病毒、肺炎支原体核酸检测试剂盒 （荧光PCR法）"
|
||
assert result.field_candidates["型号规格"] == "24人份/盒"
|
||
|
||
|
||
def test_extract_text_reports_unsupported_file(tmp_path):
|
||
path = tmp_path / "image.png"
|
||
path.write_bytes(b"png")
|
||
|
||
result = extract_text(path)
|
||
|
||
assert result.status == "unsupported"
|
||
assert result.text == ""
|
||
|
||
|
||
def test_extract_text_from_docx_preserves_table_text(tmp_path):
|
||
from docx import Document
|
||
|
||
path = tmp_path / "说明书.docx"
|
||
document = Document()
|
||
document.add_paragraph("【主要组成成分】")
|
||
table = document.add_table(rows=2, cols=2)
|
||
table.rows[0].cells[0].text = "组分"
|
||
table.rows[0].cells[1].text = "数量"
|
||
table.rows[1].cells[0].text = "PCR反应液"
|
||
table.rows[1].cells[1].text = "1管"
|
||
document.add_paragraph("【储存条件及有效期】")
|
||
document.add_paragraph("-20±5℃保存，有效期12个月。")
|
||
document.save(path)
|
||
|
||
result = extract_text(path)
|
||
|
||
assert result.status == "success"
|
||
assert "组分\t数量" in result.text
|
||
assert result.text.index("PCR反应液") < result.text.index("【储存条件及有效期】")
|