Spaces:
Running
Running
File size: 4,692 Bytes
d5f5654 2a50df2 8287176 d5f5654 8858793 d5f5654 8287176 d5f5654 ddf094a d5f5654 8287176 d5f5654 ddf094a d5f5654 8287176 d5f5654 ddf094a 8287176 ddf094a 47d2223 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 |
import json
import traceback
import mlcroissant as mlc
import func_timeout
WAIT_TIME = 5 * 60 # seconds
def validate_json(file_path):
"""Validate that the file is proper JSON."""
try:
with open(file_path, 'r') as f:
json_data = json.load(f)
return True, "✅ The file is valid JSON.", json_data
except json.JSONDecodeError as e:
error_message = f"❌ Invalid JSON format: {str(e)}"
return False, error_message, None
except Exception as e:
error_message = f"❌ Error reading file: {str(e)}"
return False, error_message, None
def validate_croissant(json_data):
"""Validate that the JSON follows Croissant schema."""
try:
dataset = mlc.Dataset(jsonld=json_data)
return True, "✅ The dataset passes Croissant validation."
except mlc.ValidationError as e:
error_details = traceback.format_exc()
error_message = f"❌ Validation failed: {str(e)}\n\n{error_details}"
return False, error_message
except Exception as e:
error_details = traceback.format_exc()
error_message = f"❌ Unexpected error during validation: {str(e)}\n\n{error_details}"
return False, error_message
def validate_records(json_data):
"""Validate that records can be generated within the time limit."""
try:
dataset = mlc.Dataset(jsonld=json_data)
record_sets = dataset.metadata.record_sets
if not record_sets:
return True, "✅ No record sets found to validate."
results = []
for record_set in record_sets:
try:
records = dataset.records(record_set=record_set.uuid)
print(records)
_ = func_timeout.func_timeout(WAIT_TIME, lambda: next(iter(records)))
results.append(f"✅ Record set '{record_set.uuid}' passed validation.")
except func_timeout.exceptions.FunctionTimedOut:
error_message = f"❌ Record set '{record_set.uuid}' generation took too long (>300s)"
return False, error_message
except Exception as e:
error_details = traceback.format_exc()
error_message = f"❌ Record set '{record_set.uuid}' failed: {str(e)}\n\n{error_details}"
return False, error_message
return True, "\n".join(results)
except Exception as e:
error_details = traceback.format_exc()
error_message = f"❌ Unexpected error during records validation: {str(e)}\n\n{error_details}"
return False, error_message
def generate_validation_report(file_path, json_data, validation_results):
"""Generate a detailed markdown report of the validation results."""
report = []
# Header
report.append("# CROISSANT VALIDATION REPORT")
report.append("=" * 80)
report.append("")
# Validation Results Section
report.append("## VALIDATION RESULTS")
report.append("-" * 80)
report.append(f"Starting validation for file: {file_path}")
# Process each validation step
for step_name, passed, message in validation_results:
report.append("")
report.append(f"### {step_name}")
report.append("✓" if passed else "❌")
report.append(message.replace("✅", "✓").replace("❌", "✗"))
# Add extra details for record sets if available
if step_name == "Records Generation Test" and json_data:
try:
dataset = mlc.Dataset(jsonld=json_data)
for record_set in dataset.metadata.record_sets:
report.append("")
report.append(f"#### Record Set: {record_set.uuid}")
report.append(f"Description: {record_set.description}")
if record_set.data_types:
report.append(f"Data Types: {record_set.data_types}")
report.append("")
report.append("Fields:")
for field in record_set.fields:
report.append(f"- {field.name} ({field.data_type})")
if field.description:
report.append(f" Description: {field.description}")
except Exception as e:
report.append(f"Error getting record set details: {str(e)}")
# JSON-LD Reference Section
report.append("")
report.append("## JSON-LD REFERENCE")
report.append("=" * 80)
report.append("")
report.append("```json")
report.append(json.dumps(json_data, indent=2))
report.append("```")
return "\n".join(report) |