root
74 lines
3.0 KiB
Python
74 lines
3.0 KiB
Python
|
|
from io import BytesIO
|
|
import zipfile
|
|
|
|
from backend.main import app
|
|
from fastapi.testclient import TestClient
|
|
|
|
client = TestClient(app)
|
|
|
|
|
|
def build_docx(paragraphs: list[str]) -> BytesIO:
|
|
document_xml = """<?xml version='1.0' encoding='UTF-8' standalone='yes'?>
|
|
<w:document xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">
|
|
<w:body>
|
|
{paras}
|
|
<w:sectPr>
|
|
<w:pgSz w:w="11906" w:h="16838"/>
|
|
<w:pgMar w:top="1440" w:right="1440" w:bottom="1440" w:left="1440" w:header="708" w:footer="708" w:gutter="0"/>
|
|
</w:sectPr>
|
|
</w:body>
|
|
</w:document>
|
|
"""
|
|
paras = "\n".join(f"<w:p><w:r><w:t>{paragraph}</w:t></w:r></w:p>" for paragraph in paragraphs)
|
|
buffer = BytesIO()
|
|
with zipfile.ZipFile(buffer, 'w', compression=zipfile.ZIP_DEFLATED) as archive:
|
|
archive.writestr('[Content_Types].xml', """<?xml version='1.0' encoding='UTF-8' standalone='yes'?>
|
|
<Types xmlns="http://schemas.openxmlformats.org/package/2006/content-types">
|
|
<Default Extension="rels" ContentType="application/vnd.openxmlformats-package.relationships+xml"/>
|
|
<Default Extension="xml" ContentType="application/xml"/>
|
|
<Override PartName="/word/document.xml" ContentType="application/vnd.openxmlformats-officedocument.wordprocessingml.document.main+xml"/>
|
|
</Types>
|
|
""")
|
|
archive.writestr('_rels/.rels', """<?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/officeDocument" Target="word/document.xml"/>
|
|
</Relationships>
|
|
""")
|
|
archive.writestr('word/document.xml', document_xml.format(paras=paras))
|
|
buffer.seek(0)
|
|
buffer.name = 'sample-report.docx'
|
|
return buffer
|
|
|
|
|
|
def test_admin_parse_doc_extracts_case_preview_from_docx() -> None:
|
|
file_obj = build_docx([
|
|
'Case ID: 124',
|
|
'Age: 16',
|
|
'Gender: female',
|
|
'Status: analyzed',
|
|
'Found alive: yes',
|
|
'Found distance km: 3.5',
|
|
'Who found: Search team 4',
|
|
'Notes: Found near the logging road',
|
|
])
|
|
|
|
response = client.post(
|
|
'/api/v1/admin/parse-doc',
|
|
files={'file': ('sample-report.docx', file_obj, 'application/vnd.openxmlformats-officedocument.wordprocessingml.document')},
|
|
)
|
|
|
|
assert response.status_code == 200
|
|
payload = response.json()
|
|
assert payload['parsed'] is True
|
|
assert payload['filename'] == 'sample-report.docx'
|
|
assert payload['preview']['case_id'] == '124'
|
|
assert payload['preview']['case']['age'] == 16
|
|
assert payload['preview']['case']['gender'] == 'female'
|
|
assert payload['preview']['case']['status'] == 'analyzed'
|
|
assert payload['preview']['case']['found_alive'] is True
|
|
assert payload['preview']['case']['found_distance_km'] == 3.5
|
|
assert payload['preview']['case']['who_found'] == 'Search team 4'
|
|
assert payload['preview']['case']['notes'] == 'Found near the logging road'
|
|
assert 'Case ID: 124' in payload['raw_text']
|