validation.py

import mlcroissant._src.operation_graph.operations.download as dl_mod
import requests
import os

HF_TOKEN = os.environ.get("HF_TOKEN")
print("[DEBUG] HF_TOKEN is", "set" if HF_TOKEN else "missing")

# Only send HF credentials when downloading from huggingface.co.
# The default get_basic_auth_from_env() applies auth to ALL URLs, which
# causes non-HF hosts (e.g. OpenML) to return 400 Bad Request.
_orig_download_from_http = dl_mod.Download._download_from_http

def _hf_aware_download(self, filepath):
    url = self.node.content_url or ""
    if HF_TOKEN and "huggingface.co" in url:
        os.environ["CROISSANT_BASIC_AUTH_USERNAME"] = "hf_user"
        os.environ["CROISSANT_BASIC_AUTH_PASSWORD"] = HF_TOKEN
    else:
        os.environ.pop("CROISSANT_BASIC_AUTH_USERNAME", None)
        os.environ.pop("CROISSANT_BASIC_AUTH_PASSWORD", None)
    return _orig_download_from_http(self, filepath)

dl_mod.Download._download_from_http = _hf_aware_download

import logging
import mlcroissant as mlc
import func_timeout
import json
import traceback

# Suppress noisy mlcroissant pattern-matching warnings
logging.getLogger("root").addFilter(
    lambda r: "Could not match" not in r.getMessage()
)
logging.getLogger().addFilter(
    lambda r: "Could not match" not in r.getMessage()
)

WAIT_TIME = 10 * 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 try_generate_record(record_collection):
    try:
        for i, record in enumerate(record_collection):
            if i == 0:
                break
        return "success"
    except Exception as e:
        return e

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.", "pass"
        
        results = []
        
        for record_set in record_sets:
            try:
                result = func_timeout.func_timeout(
                    WAIT_TIME,
                    lambda: try_generate_record(dataset.records(record_set=record_set.uuid))
                )

                if isinstance(result, Exception):
                    raise result  # re-raise actual error outside timeout

                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 (>10 minutes)."
                return False, error_message, "warning"

            except Exception as e:
                error_details = traceback.format_exc()
                error_message = (
                    f"Record set '{record_set.uuid}' failed due to generation error:\n\n"
                    f"```text\n{str(e)}\n\n{error_details}```"
                )
                return False, error_message, "warning"
        
        return True, "\n".join(results), "pass"
    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, "error"
    
RAI_FIELDS = [
    "rai:dataLimitations",
    "rai:dataBiases",
    "rai:personalSensitiveInformation",
    "rai:dataUseCases",
    "rai:dataSocialImpact",
    "rai:hasSyntheticData",
    "prov:wasGeneratedBy",
]

RAI_GUIDELINES_URL = "https://neurips.cc/Conferences/2026/EvaluationsDatasetsHosting"

def validate_rai(json_data):
    """Check that all required Responsible AI metadata fields are present."""
    missing = [field for field in RAI_FIELDS if field not in json_data]
    if not missing:
        return True, "All required Responsible AI metadata fields are present."
    missing_list = "\n".join(f"- `{f}`" for f in missing)
    message = (
        f"The following required Responsible AI metadata fields are missing:\n{missing_list}\n\n"
        f"Please refer to the <a href='{RAI_GUIDELINES_URL}' target='_blank'>NeurIPS guidelines for instructions</a> on how to add them."
        f"You can use our <a href='https://huggingface.co/spaces/JoaquinVanschoren/croissant-rai-checker' target='_blank'>online RAI editing tool</a> to help you."
    )
    return False, message

def generate_validation_report(filename, json_data, results):
    """Generate a detailed validation report in markdown format."""
    report = []
    report.append("# CROISSANT VALIDATION REPORT")
    report.append("=" * 80)
    report.append("## VALIDATION RESULTS")
    report.append("-" * 80)
    report.append(f"Starting validation for file: {filename}")

    # Add validation results
    for result in results:
        if len(result) == 4:
            test_name, passed, message, status = result
        else:
            test_name, passed, message = result
            status = "pass" if passed else "error"

        report.append(f"### {test_name}")
        if status == "pass":
            report.append("✓")
        elif status == "warning":
            report.append("?")  # Question mark for warning
        else:
            report.append("✗")
        report.append(message.strip())  # Remove any trailing newlines

    # Add JSON-LD reference
    report.append("## JSON-LD REFERENCE")
    report.append("=" * 80)
    report.append("```json")
    report.append(json.dumps(json_data, indent=2))
    report.append("```")

    return "\n".join(report)