Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions cdisc_rules_engine/services/reporting/json_report.py
Original file line number Diff line number Diff line change
Expand Up @@ -77,5 +77,5 @@ def write_report(self):
f"Cannot create output directory '{output_dir}': {e.strerror}. "
f"Please provide a valid, writable path for the output file."
) from e
with open(self._output_name, "w") as f:
json.dump(report_data, f)
with open(self._output_name, "w", encoding="utf-8") as f:
json.dump(report_data, f, ensure_ascii=False, indent=2)
57 changes: 57 additions & 0 deletions tests/QARegressionTests/test_Issues/test_CoreIssue1023.py

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could we please move this test under regression testing instead? Regression testing folder has similar tests where we run the engine using subprocess.

Original file line number Diff line number Diff line change
@@ -0,0 +1,57 @@
import os
import subprocess
import json

import pytest
from conftest import get_python_executable


@pytest.mark.regression
class TestCoreIssue1023:

def test_dataset_utf8(self):
"""Test that the engine correctly handles dataset files with utf8 encoding"""
command = [
f"{get_python_executable()}",
"-m",
"core",
"validate",
"-s",
"sdtmig",
"-v",
"3.4",
"-r",
"CORE-000766",
"-e",
"utf8",
"-dp",
os.path.join("tests", "resources", "CoreIssue1023", "ae_utf8.json"),
"--output-format",
"json",
]
subprocess.run(command, check=True)

files = os.listdir()
json_files = [
file
for file in files
if file.startswith("CORE-Report-") and file.endswith(".json")
]
json_report_path = sorted(json_files)[-1]
# Open the JSON report file
json_report = json.load(open(json_report_path, "r", encoding="utf8"))
assert {
"Conformance_Details",
"Dataset_Details",
"Issue_Summary",
"Issue_Details",
"Rules_Report",
}.issubset(json_report.keys())
datasets = {x["filename"] for x in json_report["Dataset_Details"]}
assert datasets == {"AE"}
assert (
json_report["Issue_Details"][0]["USUBJID"]
== f"utf8:{b'\xe1\xbc\x87'.decode('utf8')}"
)
if os.path.exists(json_report_path):
os.remove(json_report_path)
319 changes: 319 additions & 0 deletions tests/resources/CoreIssue1023/ae_utf8.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,319 @@
{
"datasetJSONCreationDateTime": "2024-11-11T15:09:14",
"datasetJSONVersion": "1.1.0",
"fileOID": "www.cdisc.org/StudyMSGv2/1/Define-XML_2.1.0/2024-11-11/ae",
"dbLastModifiedDateTime": "2020-08-21T09:14:28",
"originator": "CDISC SDTM MSG Team",
"sourceSystem": {
"name": "SAS on X64_10PRO",
"version": "9.0401M7"
},
"studyOID": "cdisc.com/CDISCPILOT01",
"metaDataVersionOID": "MDV.MSGv2.0.SDTMIG.3.3.SDTM.1.7",
"metaDataRef": "define.xml",
"itemGroupOID": "IG.AE",
"records": 1,
"name": "AE",
"label": "Adverse Events",
"columns": [
{
"itemOID": "IT.AE.STUDYID",
"name": "STUDYID",
"label": "Study Identifier",
"dataType": "string",
"length": 12,
"keySequence": 1
},
{
"itemOID": "IT.AE.DOMAIN",
"name": "DOMAIN",
"label": "Domain Abbreviation",
"dataType": "string",
"length": 2
},
{
"itemOID": "IT.AE.USUBJID",
"name": "USUBJID",
"label": "Unique Subject Identifier",
"dataType": "string",
"length": 8,
"keySequence": 2
},
{
"itemOID": "IT.AE.AESEQ",
"name": "AESEQ",
"label": "Sequence Number",
"dataType": "integer"
},
{
"itemOID": "IT.AE.AELNKID",
"name": "AELNKID",
"label": "Link ID",
"dataType": "string",
"length": 50,
"keySequence": 5
},
{
"itemOID": "IT.AE.AETERM",
"name": "AETERM",
"label": "Reported Term for the Adverse Event",
"dataType": "string",
"length": 200
},
{
"itemOID": "IT.AE.AELLT",
"name": "AELLT",
"label": "Lowest Level Term",
"dataType": "string",
"length": 1
},
{
"itemOID": "IT.AE.AELLTCD",
"name": "AELLTCD",
"label": "Lowest Level Term Code",
"dataType": "string",
"length": 1
},
{
"itemOID": "IT.AE.AEDECOD",
"name": "AEDECOD",
"label": "Dictionary-Derived Term",
"dataType": "string",
"length": 1,
"keySequence": 3
},
{
"itemOID": "IT.AE.AEPTCD",
"name": "AEPTCD",
"label": "Preferred Term Code",
"dataType": "string",
"length": 1
},
{
"itemOID": "IT.AE.AEHLT",
"name": "AEHLT",
"label": "High Level Term",
"dataType": "string",
"length": 1
},
{
"itemOID": "IT.AE.AEHLTCD",
"name": "AEHLTCD",
"label": "High Level Term Code",
"dataType": "string",
"length": 1
},
{
"itemOID": "IT.AE.AEHLGT",
"name": "AEHLGT",
"label": "High Level Group Term",
"dataType": "string",
"length": 1
},
{
"itemOID": "IT.AE.AEHLGTCD",
"name": "AEHLGTCD",
"label": "High Level Group Term Code",
"dataType": "string",
"length": 1
},
{
"itemOID": "IT.AE.AEBODSYS",
"name": "AEBODSYS",
"label": "Body System or Organ Class",
"dataType": "string",
"length": 1
},
{
"itemOID": "IT.AE.AEBDSYCD",
"name": "AEBDSYCD",
"label": "Body System or Organ Class Code",
"dataType": "string",
"length": 1
},
{
"itemOID": "IT.AE.AESOC",
"name": "AESOC",
"label": "Primary System Organ Class",
"dataType": "string",
"length": 1
},
{
"itemOID": "IT.AE.AESOCCD",
"name": "AESOCCD",
"label": "Primary System Organ Class Code",
"dataType": "string",
"length": 1
},
{
"itemOID": "IT.AE.AESEV",
"name": "AESEV",
"label": "Severity/Intensity",
"dataType": "string",
"length": 8
},
{
"itemOID": "IT.AE.AESER",
"name": "AESER",
"label": "Serious Event",
"dataType": "string",
"length": 1
},
{
"itemOID": "IT.AE.AEACN",
"name": "AEACN",
"label": "Action Taken with Study Treatment",
"dataType": "string",
"length": 16
},
{
"itemOID": "IT.AE.AEREL",
"name": "AEREL",
"label": "Causality",
"dataType": "string",
"length": 16
},
{
"itemOID": "IT.AE.AEOUT",
"name": "AEOUT",
"label": "Outcome of Adverse Event",
"dataType": "string",
"length": 32
},
{
"itemOID": "IT.AE.AESCAN",
"name": "AESCAN",
"label": "Involves Cancer",
"dataType": "string",
"length": 1
},
{
"itemOID": "IT.AE.AESCONG",
"name": "AESCONG",
"label": "Congenital Anomaly or Birth Defect",
"dataType": "string",
"length": 1
},
{
"itemOID": "IT.AE.AESDISAB",
"name": "AESDISAB",
"label": "Persist or Signif Disability/Incapacity",
"dataType": "string",
"length": 1
},
{
"itemOID": "IT.AE.AESDTH",
"name": "AESDTH",
"label": "Results in Death",
"dataType": "string",
"length": 1
},
{
"itemOID": "IT.AE.AESHOSP",
"name": "AESHOSP",
"label": "Requires or Prolongs Hospitalization",
"dataType": "string",
"length": 1
},
{
"itemOID": "IT.AE.AESLIFE",
"name": "AESLIFE",
"label": "Is Life Threatening",
"dataType": "string",
"length": 1
},
{
"itemOID": "IT.AE.AESOD",
"name": "AESOD",
"label": "Occurred with Overdose",
"dataType": "string",
"length": 1
},
{
"itemOID": "IT.AE.EPOCH",
"name": "EPOCH",
"label": "Epoch",
"dataType": "string",
"length": 9
},
{
"itemOID": "IT.AE.AESTDTC",
"name": "AESTDTC",
"label": "Start Date/Time of Adverse Event",
"dataType": "date",
"keySequence": 4
},
{
"itemOID": "IT.AE.AEENDTC",
"name": "AEENDTC",
"label": "End Date/Time of Adverse Event",
"dataType": "date"
},
{
"itemOID": "IT.AE.AESTDY",
"name": "AESTDY",
"label": "Study Day of Start of Adverse Event",
"dataType": "integer"
},
{
"itemOID": "IT.AE.AEENDY",
"name": "AEENDY",
"label": "Study Day of End of Adverse Event",
"dataType": "integer"
},
{
"itemOID": "IT.AE.AEENRTPT",
"name": "AEENRTPT",
"label": "End Relative to Reference Time Point",
"dataType": "string",
"length": 7
},
{
"itemOID": "IT.AE.AEENTPT",
"name": "AEENTPT",
"label": "End Reference Time Point",
"dataType": "date"
}
],
"rows": [
[
"CDISCPILOT01",
"AE",
"utf8:ἇ",
9,
"9",
"SUDDEN DEATH",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"SEVERE",
"Y",
"DRUG WITHDRAWN",
"NOT RELATED",
"FATAL",
"N",
"N",
"N",
"Y",
"N",
"Y",
"N",
"TREATMENT",
"2013-01-14",
"2013-01-14",
61,
61,
"",
""
]
]
}
Loading
Loading