88ff04bef8
新增前端归档中心视图及相关工具函数，扩充知识库文档分类和 提取器支持多种格式，增强编排器报销查询的多维度检索，优 化本体规则和用户代理审核消息，前端完善报销创建和审批详 情交互细节，补充单元测试覆盖。
97 lines
3.8 KiB
Python
97 lines
3.8 KiB
Python
from __future__ import annotations
|
||
|
||
from zipfile import ZipFile
|
||
|
||
from app.services.knowledge_document_extractors import _extract_document_text_from_path
|
||
|
||
|
||
def test_extract_xlsx_document_text_builds_markdown_with_row_clues(tmp_path) -> None:
|
||
file_path = tmp_path / "company-expense-rules.xlsx"
|
||
_write_minimal_xlsx(
|
||
file_path,
|
||
sheet_name="报销标准",
|
||
rows=[
|
||
["费用类型", "标准", "说明"],
|
||
["住宿费", "500", "超标准需事前审批"],
|
||
["交通费", "据实", "保留发票"],
|
||
],
|
||
)
|
||
|
||
text = _extract_document_text_from_path(
|
||
file_path=file_path,
|
||
original_name="公司支出管理办法.xlsx",
|
||
mime_type="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
|
||
)
|
||
|
||
assert "# Excel 工作簿：公司支出管理办法.xlsx" in text
|
||
assert "## 工作表 1：报销标准" in text
|
||
assert "| 费用类型 | 标准 | 说明 |" in text
|
||
assert "费用类型=住宿费；标准=500；说明=超标准需事前审批" in text
|
||
assert "费用类型=交通费；标准=据实；说明=保留发票" in text
|
||
|
||
|
||
def test_extract_pptx_document_text_builds_markdown_slides(tmp_path) -> None:
|
||
file_path = tmp_path / "training.pptx"
|
||
slide_xml = """<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
|
||
<p:sld xmlns:a="http://schemas.openxmlformats.org/drawingml/2006/main"
|
||
xmlns:p="http://schemas.openxmlformats.org/presentationml/2006/main">
|
||
<p:cSld>
|
||
<p:spTree>
|
||
<p:sp><p:txBody><a:p><a:r><a:t>差旅报销培训</a:t></a:r></a:p></p:txBody></p:sp>
|
||
<p:sp><p:txBody><a:p><a:r><a:t>发票、审批、预算三项要素必须齐全</a:t></a:r></a:p></p:txBody></p:sp>
|
||
</p:spTree>
|
||
</p:cSld>
|
||
</p:sld>
|
||
"""
|
||
with ZipFile(file_path, "w") as archive:
|
||
archive.writestr("ppt/slides/slide1.xml", slide_xml)
|
||
|
||
text = _extract_document_text_from_path(
|
||
file_path=file_path,
|
||
original_name="报销培训.pptx",
|
||
mime_type="application/vnd.openxmlformats-officedocument.presentationml.presentation",
|
||
)
|
||
|
||
assert "# PowerPoint 演示文稿：报销培训.pptx" in text
|
||
assert "## 幻灯片 1" in text
|
||
assert "- 差旅报销培训" in text
|
||
assert "- 发票、审批、预算三项要素必须齐全" in text
|
||
|
||
|
||
def _write_minimal_xlsx(file_path, *, sheet_name: str, rows: list[list[str]]) -> None:
|
||
workbook_xml = f"""<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
|
||
<workbook xmlns="http://schemas.openxmlformats.org/spreadsheetml/2006/main"
|
||
xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships">
|
||
<sheets>
|
||
<sheet name="{sheet_name}" sheetId="1" r:id="rId1"/>
|
||
</sheets>
|
||
</workbook>
|
||
"""
|
||
rels_xml = """<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
|
||
<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">
|
||
<Relationship Id="rId1"
|
||
Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/worksheet"
|
||
Target="worksheets/sheet1.xml"/>
|
||
</Relationships>
|
||
"""
|
||
row_xml = "\n".join(
|
||
f'<row r="{row_index}">'
|
||
+ "".join(
|
||
f'<c r="{chr(65 + column_index)}{row_index}" t="inlineStr"><is><t>{cell}</t></is></c>'
|
||
for column_index, cell in enumerate(row)
|
||
)
|
||
+ "</row>"
|
||
for row_index, row in enumerate(rows, start=1)
|
||
)
|
||
sheet_xml = f"""<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
|
||
<worksheet xmlns="http://schemas.openxmlformats.org/spreadsheetml/2006/main">
|
||
<sheetData>
|
||
{row_xml}
|
||
</sheetData>
|
||
</worksheet>
|
||
"""
|
||
with ZipFile(file_path, "w") as archive:
|
||
archive.writestr("xl/workbook.xml", workbook_xml)
|
||
archive.writestr("xl/_rels/workbook.xml.rels", rels_xml)
|
||
archive.writestr("xl/worksheets/sheet1.xml", sheet_xml)
|