import json
import pandas as pd
def flatten_schema(schema, group="root", required_fields=None):
rows = []
properties = schema.get("properties", {})
required_fields = required_fields or []
for prop_name, prop_schema in properties.items():
full_required = prop_name in required_fields
if prop_schema.get("type") == "object" and "properties" in prop_schema:
sub_required = prop_schema.get("required", [])
nested_group = f"{group}.{prop_name}" if group != "root" else prop_name
rows.extend(flatten_schema(prop_schema, nested_group, sub_required))
else:
row = {
"Column Name": prop_name,
"Data Type": prop_schema.get("type", ""),
"Title": prop_schema.get("title", ""),
"Description": prop_schema.get("description", ""),
"Required": "Yes" if full_required else "No",
"Group": group,
"maxLength": prop_schema.get("maxLength", ""),
"Enum": ",".join(map(str, prop_schema.get("enum", []))) if "enum" in prop_schema else "",
"Pattern": prop_schema.get("pattern", ""),
"Minimum": prop_schema.get("minimum", ""),
"Maximum": prop_schema.get("maximum", ""),
"Default": prop_schema.get("default", "")
}
rows.append(row)
return rows
def json_schema_to_excel(json_file, excel_file="metadata_output.xlsx"):
with open(json_file, "r") as f:
schema = json.load(f)
root_required = schema.get("required", [])
flat_rows = flatten_schema(schema, required_fields=root_required)
df = pd.DataFrame(flat_rows, columns=[
"Column Name", "Data Type", "Title", "Description", "Required", "Group",
"maxLength", "Enum", "Pattern", "Minimum", "Maximum", "Default"
])
df.to_excel(excel_file, index=False)
print(f"✅ Metadata Excel file saved as {excel_file}")
if __name__ == "__main__":
json_schema_to_excel("output_schema.json")
No comments:
Post a Comment