Phy Test Data Factory

Schema-driven test data factory generator. Reads your database schema or model definitions — Prisma schema, SQLAlchemy models, Django models, TypeORM entities, Zod schemas, Pydantic models, or raw SQL DDL — and generates ready-to-use factory functions with realistic fake data. Outputs TypeScript factory files using Faker.js, Python conftest.py using factory_boy + Faker, or raw SQL INSERT seed scripts. Respects foreign key relationships (seeds parents before children), handles enums, nullable fields, unique constraints, and generates edge-case variants (empty strings, max-length values, boundary dates). Zero external API — pure local file analysis + code generation. Triggers on "generate test data", "seed database", "test fixtures", "factory functions", "fake data from schema", "/test-data-factory".

# Test Data Factory

Writing test setup is slower than writing the test itself. You have a `User` model with 12 fields, a `Post` model that requires a User, and an `Order` model that requires both. Every test file re-invents the same `createTestUser()` boilerplate — with slightly different hardcoded values that don't cover edge cases.

Paste your schema and get a complete factory module: realistic Faker-powered defaults for every field, relationship-aware ordering, and one-line overrides for specific test scenarios.

**Reads any schema format. Outputs TypeScript, Python, or SQL. Zero external APIs.**

---

## Trigger Phrases

- "generate test data", "seed my database", "test fixtures"
- "factory functions", "fake data from schema", "test data setup"
- "create test factories", "Faker from schema", "factory_boy setup"
- "generate seed data", "populate test database"
- "I need fake users/orders/products for testing"
- "/test-data-factory"

---

## How to Provide Input

```bash
# Option 1: Prisma schema
/test-data-factory schema.prisma
/test-data-factory prisma/schema.prisma

# Option 2: SQLAlchemy / Django models file
/test-data-factory models.py
/test-data-factory app/models.py

# Option 3: TypeORM entities directory
/test-data-factory src/entities/

# Option 4: Zod schemas file
/test-data-factory src/schemas/user.schema.ts

# Option 5: Raw SQL DDL
/test-data-factory --sql migrations/001_initial.sql

# Option 6: Output format override
/test-data-factory schema.prisma --output typescript
/test-data-factory models.py --output python
/test-data-factory schema.prisma --output sql

# Option 7: Include edge-case variants
/test-data-factory schema.prisma --edge-cases

# Option 8: Specific count
/test-data-factory schema.prisma --count 50
```

---

## Step 1: Detect and Parse Schema

### Prisma Schema Parser

```python
import re
from dataclasses import dataclass, field
from typing import Any

@dataclass
class PrismaField:
    name: str
    type: str
    is_optional: bool = False
    is_list: bool = False
    is_id: bool = False
    is_unique: bool = False
    is_auto: bool = False
    default: Any = None
    relation: str | None = None
    enum_values: list[str] = field(default_factory=list)

def parse_prisma_schema(schema_text: str) -> dict:
    """Parse Prisma schema into model definitions."""
    models = {}
    enums = {}

    # Parse enums first
    for enum_match in re.finditer(r'enum\s+(\w+)\s*\{([^}]+)\}', schema_text, re.DOTALL):
        enum_name = enum_match.group(1)
        values = [v.strip() for v in enum_match.group(2).split('\n')
                  if v.strip() and not v.strip().startswith('//')]
        enums[enum_name] = values

    # Parse models
    for model_match in re.finditer(r'model\s+(\w+)\s*\{([^}]+)\}', schema_text, re.DOTALL):
        model_name = model_match.group(1)
        body = model_match.group(2)
        fields = []

        for line in body.split('\n'):
            line = line.strip()
            if not line or line.startswith('//') or line.startswith('@@'):
                continue
            # Parse field: name type? modifiers
            parts = line.split()
            if len(parts) < 2:
                continue

            fname = parts[0]
            ftype_raw = parts[1]

            is_optional = ftype_raw.endswith('?')
            is_list = ftype_raw.endswith('[]')
            ftype = ftype_raw.rstrip('?').rstrip('[]')

            is_id = '@id' in line
            is_unique = '@unique' in line
            is_auto = '@default(autoincrement())' in line or '@default(auto())' in line or '@default(uuid())' in line or '@default(cuid())' in line
            is_relation = '@relation' in line

            default_match = re.search(r'@default\((.+?)\)', line)
            default_val = default_match.group(1) if default_match else None

            fields.append(PrismaField(
                name=fname,
                type=ftype,
                is_optional=is_optional,
                is_list=is_list,
                is_id=is_id,
                is_unique=is_unique,
                is_auto=is_auto,
                default=default_val,
                relation=ftype if is_relation and ftype[0].isupper() else None,
                enum_values=enums.get(ftype, []),
            ))

        models[model_name] = fields

    return {'models': models, 'enums': enums}
```

### SQL DDL Parser

```python
def parse_sql_ddl(sql_text: str) -> dict:
    """Parse CREATE TABLE statements."""
    models = {}

    for table_match in re.finditer(
        r'CREATE\s+TABLE\s+(?:IF\s+NOT\s+EXISTS\s+)?[`"]?(\w+)[`"]?\s*\(([^;]+)\)',
        sql_text, re.IGNORECASE | re.DOTALL
    ):
        table_name = table_match.group(1)
        columns_text = table_match.group(2)
        fields = []

        for col_line in columns_text.split(','):
            col_line = col_line.strip()
            if not col_line or col_line.upper().startswith(('PRIMARY', 'FOREIGN', 'UNIQUE', 'INDEX', 'KEY', 'CONSTRAINT')):
                continue

            col_match = re.match(r'[`"]?(\w+)[`"]?\s+(\w+)(\(\d+\))?(.*)$', col_line, re.IGNORECASE)
            if not col_match:
                continue

            fname = col_match.group(1)
            ftype = col_match.group(2).upper()
            rest = col_match.group(4).upper()
            is_nullable = 'NOT NULL' not in rest
            is_auto = 'AUTO_INCREMENT' in rest or 'SERIAL' in ftype
            is_unique = 'UNIQUE' in rest

            fields.append(PrismaField(
                name=fname,
                type=ftype,
                is_optional=is_nullable,
                is_auto=is_auto,
                is_unique=is_unique,
            ))

        models[table_name] = fields

    return {'models': models, 'enums': {}}
```

---

## Step 2: Map Types to Faker Functions

```python
# Prisma/TypeScript type → Faker.js function
FAKER_JS_MAP = {
    # Primitives
    'String':   'faker.lorem.words(3)',
    'Int':      'faker.number.int({ min: 1, max: 10000 })',
    'Float':    'faker.number.float({ min: 0, max: 1000, fractionDigits: 2 })',
    'Boolean':  'faker.datatype.boolean()',
    'DateTime': 'faker.date.recent({ days: 30 })',
    'BigInt':   'BigInt(faker.number.int({ min: 1, max: 1000000 }))',
    'Json':     '{}',
    'Bytes':    'Buffer.from(faker.string.alphanumeric(16))',

    # Semantic overrides (based on field name)
    'email':       'faker.internet.email()',
    'name':        'faker.person.fullName()',
    'firstName':   'faker.person.firstName()',
    'lastName':    'faker.person.lastName()',
    'username':    'faker.internet.username()',
    'password':    'faker.internet.password({ length: 12 })',
    'phone':       'faker.phone.number()',
    'address':     'faker.location.streetAddress()',
    'city':        'faker.location.city()',
    'country':     'faker.location.country()',
    'zipCode':     'faker.location.zipCode()',
    'url':         'faker.internet.url()',
    'imageUrl':    'faker.image.url()',
    'avatar':      'faker.image.avatar()',
    'bio':         'faker.lorem.paragraph()',
    'description': 'faker.lorem.sentences(2)',
    'title':       'faker.lorem.sentence()',
    'slug':        'faker.helpers.slugify(faker.lorem.words(3))',
    'color':       'faker.color.human()',
    'uuid':        'faker.string.uuid()',
    'ip':          'faker.internet.ip()',
    'createdAt':   'faker.date.past({ years: 1 })',
    'updatedAt':   'new Date()',
    'deletedAt':   'null',
    'publishedAt': 'faker.date.recent({ days: 90 })',
    'price':       'faker.number.float({ min: 0.99, max: 999.99, fractionDigits: 2 })',
    'amount':      'faker.number.int({ min: 1, max: 10000 })',
    'quantity':    'faker.number.int({ min: 1, max: 100 })',
    'score':       'faker.number.float({ min: 0, max: 5, fractionDigits: 1 })',
    'rating':      'faker.number.int({ min: 1, max: 5 })',
    'status':      None,  # replaced by enum values
    'role':        None,  # replaced by enum values
    'type'