JSON Schema Generator Tutorial — Validate Any JSON Structure

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://example.com/schemas/user.json",
  "title": "User",
  "description": "A user object in our system",
  "type": "object",
  "required": ["id", "email", "name"],
  "properties": {
    "id": {
      "type": "integer",
      "minimum": 1,
      "description": "Unique user identifier"
    },
    "email": {
      "type": "string",
      "format": "email",
      "description": "User email address"
    },
    "name": {
      "type": "string",
      "minLength": 1,
      "maxLength": 100
    },
    "age": {
      "type": "integer",
      "minimum": 0,
      "maximum": 150
    },
    "role": {
      "type": "string",
      "enum": ["admin", "user", "moderator"]
    },
    "tags": {
      "type": "array",
      "items": { "type": "string" },
      "uniqueItems": true,
      "maxItems": 20
    },
    "address": {
      "type": "object",
      "required": ["city", "country"],
      "properties": {
        "street": { "type": "string" },
        "city": { "type": "string" },
        "country": { "type": "string", "minLength": 2, "maxLength": 2 }
      },
      "additionalProperties": false
    },
    "createdAt": {
      "type": "string",
      "format": "date-time"
    },
    "score": {
      "type": ["number", "null"],
      "minimum": 0,
      "maximum": 100
    }
  },
  "additionalProperties": false
}

import Ajv from 'ajv';
import addFormats from 'ajv-formats'; // adds email, date-time, uri, etc.

const ajv = new Ajv({ allErrors: true }); // show ALL errors (not just first)
addFormats(ajv);

const userSchema = {
  type: 'object',
  required: ['id', 'email', 'name'],
  properties: {
    id: { type: 'integer', minimum: 1 },
    email: { type: 'string', format: 'email' },
    name: { type: 'string', minLength: 1, maxLength: 100 },
    role: { type: 'string', enum: ['admin', 'user', 'moderator'] },
    age: { type: 'integer', minimum: 0 },
  },
  additionalProperties: false,
};

// Compile schema once, validate many times (compile is expensive)
const validate = ajv.compile(userSchema);

// ✅ Valid data
const validUser = { id: 1, email: 'alice@example.com', name: 'Alice', role: 'admin' };
console.log(validate(validUser));  // true

// ❌ Invalid data — multiple errors
const invalidUser = { id: 0, email: 'not-an-email', name: '', unknownField: true };
console.log(validate(invalidUser));  // false
console.log(validate.errors);
// [
//   { instancePath: '/id', message: 'must be >= 1' },
//   { instancePath: '/email', message: 'must match format "email"' },
//   { instancePath: '/name', message: 'must NOT have fewer than 1 characters' },
//   { instancePath: '', keyword: 'additionalProperties', params: { additionalProperty: 'unknownField' } }
// ]

// Utility function for clean error messages:
function validateUser(data) {
  const valid = validate(data);
  if (!valid) {
    const errors = validate.errors.map(e => `${e.instancePath || 'root'}: ${e.message}`);
    throw new Error('Validation failed:\n' + errors.join('\n'));
  }
  return data;
}

// Express.js middleware using Ajv:
function validateBody(schema) {
  const validate = ajv.compile(schema);
  return (req, res, next) => {
    if (validate(req.body)) {
      next();
    } else {
      res.status(400).json({ errors: validate.errors });
    }
  };
}

app.post('/users', validateBody(userSchema), createUserHandler);

# pip install genson
from genson import SchemaBuilder
import json

# Sample JSON data representing a typical response
sample_data = {
    "id": 123,
    "name": "Alice Johnson",
    "email": "alice@example.com",
    "scores": [95, 87, 92],
    "active": True,
    "address": {
        "city": "Boston",
        "country": "USA"
    }
}

# Build schema from sample
builder = SchemaBuilder()
builder.add_object(sample_data)
schema = builder.to_schema()

print(json.dumps(schema, indent=2))
# {
#   "$schema": "http://json-schema.org/schema#",
#   "type": "object",
#   "properties": {
#     "id": {"type": "integer"},
#     "name": {"type": "string"},
#     "email": {"type": "string"},
#     "scores": {"type": "array", "items": {"type": "integer"}},
#     "active": {"type": "boolean"},
#     "address": {
#       "type": "object",
#       "properties": {
#         "city": {"type": "string"},
#         "country": {"type": "string"}
#       },
#       "required": ["city", "country"]
#     }
#   },
#   "required": ["id", "name", "email", "scores", "active", "address"]
# }

# Add multiple samples to handle union types and optional fields
builder2 = SchemaBuilder()
builder2.add_object({"id": 123, "name": "Alice", "role": "admin"})
builder2.add_object({"id": "abc", "name": "Bob"})   # id can be string too
builder2.add_object({"id": 456, "name": "Carol", "age": 30})  # age is optional

schema2 = builder2.to_schema()
# "id" becomes {"type": ["integer", "string"]}
# "age" is absent from required (only present in 1 of 3 samples)
print(json.dumps(schema2, indent=2))