JSON Transformer Skill

Transform, manipulate, and analyze JSON data structures with advanced operations.

Instructions

You are a JSON transformation expert. When invoked:

1. Parse and Validate JSON:

   • Parse JSON from files, strings, or APIs
   • Validate JSON structure and schema
   • Handle malformed JSON gracefully
   • Pretty-print and format JSON
   • Detect and fix common JSON issues

2. Transform Data Structures:

   • Reshape nested objects and arrays
   • Flatten and unflatten structures
   • Extract specific paths (JSONPath, JMESPath)
   • Merge and combine JSON documents
   • Filter and map data

3. Advanced Operations:

   • Convert between JSON and other formats (CSV, YAML, XML)
   • Apply transformations (jq-style operations)
   • Query and search JSON data
   • Diff and compare JSON documents
   • Generate JSON from schemas

4. Data Manipulation:

   • Add, update, delete properties
   • Rename keys
   • Convert data types
   • Sort and deduplicate
   • Calculate aggregate values

Usage Examples

@json-transformer data.json
@json-transformer --flatten
@json-transformer --path "users[*].email"
@json-transformer --merge file1.json file2.json
@json-transformer --to-csv data.json
@json-transformer --validate schema.json

Basic JSON Operations

Parsing and Writing

Python

import json

# Parse JSON string
data = json.loads('{"name": "John", "age": 30}')

# Parse from file
with open('data.json', 'r') as f:
    data = json.load(f)

# Write JSON to file
with open('output.json', 'w') as f:
    json.dump(data, f, indent=2)

# Pretty print
print(json.dumps(data, indent=2, sort_keys=True))

# Compact output
compact = json.dumps(data, separators=(',', ':'))

# Handle special types
from datetime import datetime
import decimal

def json_encoder(obj):
    if isinstance(obj, datetime):
        return obj.isoformat()
    if isinstance(obj, decimal.Decimal):
        return float(obj)
    raise TypeError(f"Type {type(obj)} not serializable")

json.dumps(data, default=json_encoder)

JavaScript

// Parse JSON string
const data = JSON.parse('{"name": "John", "age": 30}');

// Parse from file (Node.js)
const fs = require('fs');
const data = JSON.parse(fs.readFileSync('data.json', 'utf8'));

// Write JSON to file
fs.writeFileSync('output.json', JSON.stringify(data, null, 2));

// Pretty print
console.log(JSON.stringify(data, null, 2));

// Custom serialization
const json = JSON.stringify(data, (key, value) => {
  if (value instanceof Date) {
    return value.toISOString();
  }
  return value;
}, 2);

jq (Command Line)

# Pretty print
cat data.json | jq '.'

# Compact output
cat data.json | jq -c '.'

# Sort keys
cat data.json | jq -S '.'

# Read from file, write to file
jq '.' input.json > output.json

Validation

Python (jsonschema)

from jsonschema import validate, ValidationError

# Define schema
schema = {
    "type": "object",
    "properties": {
        "name": {"type": "string"},
        "age": {"type": "number", "minimum": 0},
        "email": {"type": "string", "format": "email"}
    },
    "required": ["name", "email"]
}

# Validate data
data = {"name": "John", "email": "john@example.com", "age": 30}

try:
    validate(instance=data, schema=schema)
    print("Valid JSON")
except ValidationError as e:
    print(f"Invalid: {e.message}")

# Validate against JSON Schema draft
from jsonschema import Draft7Validator

validator = Draft7Validator(schema)
errors = list(validator.iter_errors(data))
for error in errors:
    print(f"Error at {'.'.join(str(p) for p in error.path)}: {error.message}")

JavaScript (ajv)

const Ajv = require('ajv');
const ajv = new Ajv();

const schema = {
  type: 'object',
  properties: {
    name: { type: 'string' },
    age: { type: 'number', minimum: 0 },
    email: { type: 'string', format: 'email' }
  },
  required: ['name', 'email']
};

const validate = ajv.compile(schema);

const data = { name: 'John', email: 'john@example.com', age: 30 };

if (validate(data)) {
  console.log('Valid JSON');
} else {
  console.log('Invalid:', validate.errors);
}

Data Extraction and Querying

JSONPath Queries

Python (jsonpath-ng)

from jsonpath_ng import jsonpath, parse

data = {
    "users": [
        {"name": "John", "age": 30, "email": "john@example.com"},
        {"name": "Jane", "age": 25, "email": "jane@example.com"}
    ]
}

# Extract all user names
jsonpath_expr = parse('users[*].name')
names = [match.value for match in jsonpath_expr.find(data)]
# Result: ['John', 'Jane']

# Extract emails of users over 25
jsonpath_expr = parse('users[?(@.age > 25)].email')
emails = [match.value for match in jsonpath_expr.find(data)]

# Nested extraction
data = {
    "company": {
        "departments": [
            {
                "name": "Engineering",
                "employees": [
                    {"name": "Alice", "salary": 100000},
                    {"name": "Bob", "salary": 90000}
                ]
            }
        ]
    }
}

jsonpath_expr = parse('company.departments[*].employees[*].name')
names = [match.value for match in jsonpath_expr.find(data)]

jq

# Extract field
echo '{"name": "John", "age": 30}' | jq '.name'

# Extract from array
echo '[{"name": "John"}, {"name": "Jane"}]' | jq '.[].name'

# Filter array
echo '[{"name": "John", "age": 30}, {"name": "Jane", "age": 25}]' | \
  jq '.[] | select(.age > 25)'

# Extract nested fields
cat data.json | jq '.users[].email'

# Multiple fields
cat data.json | jq '.users[] | {name: .name, email: .email}'

# Conditional extraction
cat data.json | jq '.users[] | select(.age > 25) | .email'

JMESPath Queries

Python (jmespath)

import jmespath

data = {
    "users": [
        {"name": "John", "age": 30, "tags": ["admin", "developer"]},
        {"name": "Jane", "age": 25, "tags": ["developer"]},
        {"name": "Bob", "age": 35, "tags": ["manager"]}
    ]
}

# Simple extraction
names = jmespath.search('users[*].name', data)
# Result: ['John', 'Jane', 'Bob']

# Filtering
admins = jmespath.search('users[?contains(tags, `admin`)]', data)

# Multiple conditions
senior_devs = jmespath.search(
    'users[?age > `28` && contains(tags, `developer`)]',
    data
)

# Projections
result = jmespath.search('users[*].{name: name, age: age}', data)

# Nested queries
data = {
    "departments": [
        {
            "name": "Engineering",
            "employees": [
                {"name": "Alice", "skills": ["Python", "Go"]},
                {"name": "Bob", "skills": ["JavaScript", "Python"]}
            ]
        }
    ]
}

python_devs = jmespath.search(
    'departments[*].employees[?contains(skills, `Python`)].name',
    data
)

Data Transformation

Flattening Nested JSON

Python

def flatten_json(nested_json, parent_key='', sep='.'):
    """
    Flatten nested JSON structure
    """
    items = []

    for key, value in nested_json.items():
        new_key = f"{parent_key}{sep}{key}" if parent_key else key

        if isinstance(value, dict):
            items.extend(flatten_json(value, new_key, sep=sep).items())
        elif isinstance(value, list):
            for i, item in enumerate(value):
                if isinstance(item, dict):
                    items.extend(flatten_json(item, f"{new_key}[{i}]", sep=sep).items())
                else:
                    items.append((f"{new_key}[{i}]", item))
        else:
            items.append((new_key, value))

    return dict(items)

# Example
nested = {
    "user": {
        "name": "John",
        "address": {
            "city": "New York",
            "zip": "10001"
        },
        "tags": ["admin", "developer"]
    }
}

flat = flatten_json(nested)
# Result: {
#     'user.name': 'John',
#     'user.address.city': 'New York',
#     'user.address.zip': '10001',
#     'user.tags[0]': 'admin',
#     'user.tags[1]': 'devel