inline-schema/src/parser.ts

import type { Schema, PrimitiveSchema, TupleSchema, ArraySchema, NamedSchema, ReferenceSchema, StringLiteralSchema, UnionSchema } from './types';

export class ParseError extends Error {
  constructor(message: string, public position?: number) {
    super(position !== undefined ? `${message} at position ${position}` : message);
    this.name = 'ParseError';
  }
}

export interface ReferenceInfo {
  /** Referenced table name (e.g., 'parts' from '@parts[]') */
  tableName: string;
  /** Whether it's an array reference */
  isArray: boolean;
}

class Parser {
  private input: string;
  private pos: number = 0;

  constructor(input: string) {
    this.input = input;
  }

  private peek(): string {
    return this.input[this.pos] || '';
  }

  private consume(): string {
    return this.input[this.pos++] || '';
  }

  private skipWhitespace(): void {
    while (this.pos < this.input.length && /\s/.test(this.input[this.pos])) {
      this.pos++;
    }
  }

  private match(str: string): boolean {
    return this.input.slice(this.pos, this.pos + str.length) === str;
  }

  private consumeStr(str: string): boolean {
    if (this.match(str)) {
      this.pos += str.length;
      return true;
    }
    return false;
  }

  getPosition(): number {
    return this.pos;
  }

  getInputLength(): number {
    return this.input.length;
  }

  parseSchema(): Schema {
    this.skipWhitespace();

    // Parse the first schema element
    let schema = this.parseSchemaInternal();
    this.skipWhitespace();

    // Check for array suffix: type[]
    if (this.consumeStr('[')) {
      this.skipWhitespace();
      if (!this.consumeStr(']')) {
        throw new ParseError('Expected ]', this.pos);
      }
      schema = { type: 'array', element: schema };
      this.skipWhitespace();
    }

    // Check for union type (| symbol)
    if (this.consumeStr('|')) {
      const members: Schema[] = [schema];
      
      while (true) {
        this.skipWhitespace();
        const member = this.parseSchemaInternal();
        members.push(member);
        this.skipWhitespace();
        
        if (!this.consumeStr('|')) {
          break;
        }
      }
      
      return {
        type: 'union',
        members
      };
    }

    return schema;
  }

  private parseSchemaInternal(): Schema {
    this.skipWhitespace();

    // Check for parentheses (grouping)
    if (this.consumeStr('(')) {
      this.skipWhitespace();
      const schema = this.parseSchema();  // Recursive call for nested unions
      this.skipWhitespace();
      
      if (!this.consumeStr(')')) {
        throw new ParseError('Expected )', this.pos);
      }
      
      // Check if there's an array suffix: (union)[]
      this.skipWhitespace();
      if (this.consumeStr('[')) {
        this.skipWhitespace();
        if (!this.consumeStr(']')) {
          throw new ParseError('Expected ]', this.pos);
        }
        return { type: 'array', element: schema };
      }
      
      return schema;
    }

    // Check for string literal syntax: "value" or 'value'
    if (this.peek() === '"' || this.peek() === "'") {
      return this.parseStringLiteralSchema();
    }

    // Check for reference syntax: @tablename[]
    if (this.consumeStr('@')) {
      return this.parseReferenceSchema();
    }

    if (this.consumeStr('string')) {
      if (this.consumeStr('[')) {
        this.skipWhitespace();
        if (!this.consumeStr(']')) {
          throw new ParseError('Expected ]', this.pos);
        }
        return { type: 'array', element: { type: 'string' } };
      }
      return { type: 'string' };
    }

    if (this.consumeStr('number')) {
      if (this.consumeStr('[')) {
        this.skipWhitespace();
        if (!this.consumeStr(']')) {
          throw new ParseError('Expected ]', this.pos);
        }
        return { type: 'array', element: { type: 'number' } };
      }
      return { type: 'number' };
    }

    if (this.consumeStr('int')) {
      if (this.consumeStr('[')) {
        this.skipWhitespace();
        if (!this.consumeStr(']')) {
          throw new ParseError('Expected ]', this.pos);
        }
        return { type: 'array', element: { type: 'int' } };
      }
      return { type: 'int' };
    }

    if (this.consumeStr('float')) {
      if (this.consumeStr('[')) {
        this.skipWhitespace();
        if (!this.consumeStr(']')) {
          throw new ParseError('Expected ]', this.pos);
        }
        return { type: 'array', element: { type: 'float' } };
      }
      return { type: 'float' };
    }

    if (this.consumeStr('boolean')) {
      if (this.consumeStr('[')) {
        this.skipWhitespace();
        if (!this.consumeStr(']')) {
          throw new ParseError('Expected ]', this.pos);
        }
        return { type: 'array', element: { type: 'boolean' } };
      }
      return { type: 'boolean' };
    }

    if (this.consumeStr('[')) {
      const elements: NamedSchema[] = [];
      this.skipWhitespace();

      if (this.peek() === ']') {
        this.consume();
        throw new ParseError('Empty array/tuple not allowed', this.pos);
      }

      elements.push(this.parseNamedSchema());
      this.skipWhitespace();

      if (this.consumeStr(';')) {
        const remainingElements: NamedSchema[] = [];
        while (true) {
          this.skipWhitespace();
          remainingElements.push(this.parseNamedSchema());
          this.skipWhitespace();

          if (!this.consumeStr(';')) {
            break;
          }
        }
        elements.push(...remainingElements);
      }

      this.skipWhitespace();

      if (!this.consumeStr(']')) {
        throw new ParseError('Expected ]', this.pos);
      }

      if (this.consumeStr('[')) {
        this.skipWhitespace();
        if (!this.consumeStr(']')) {
          throw new ParseError('Expected ]', this.pos);
        }
        if (elements.length === 1 && !elements[0].name) {
          return { type: 'array', element: elements[0].schema };
        }
        return { type: 'array', element: { type: 'tuple', elements } };
      }

      if (elements.length === 1 && !elements[0].name) {
        return { type: 'array', element: elements[0].schema };
      }
      return { type: 'tuple', elements };
    }

    let identifier = '';
    while (this.pos < this.input.length && /[a-zA-Z0-9\-_]/.test(this.peek())) {
      identifier += this.consume();
    }

    if (identifier.length > 0) {
      if (this.consumeStr('[')) {
        this.skipWhitespace();
        if (!this.consumeStr(']')) {
          throw new ParseError('Expected ]', this.pos);
        }
        return { type: 'array', element: { type: 'string' } };
      }
      return { type: 'string' };
    }

    throw new ParseError(`Unexpected character: ${this.peek()}`, this.pos);
  }

  private parseStringLiteralSchema(): Schema {
    const value = this.parseStringLiteral();
    return {
      type: 'stringLiteral',
      value
    };
  }

  private parseStringLiteral(): string {
    const quote = this.peek();
    if (quote !== '"' && quote !== "'") {
      throw new ParseError('Expected string literal with quotes', this.pos);
    }
    this.consume(); // Consume opening quote
    
    let value = '';
    while (this.pos < this.input.length) {
      const char = this.peek();
      
      if (char === '\\') {
        this.consume();
        const nextChar = this.consume();
        if (nextChar === '"' || nextChar === "'" || nextChar === '\\' || 
            nextChar === '|' || nextChar === ';' || nextChar === '(' || nextChar === ')') {
          value += nextChar;
        } else {
          value += '\\' + nextChar;
        }
      } else if (char === quote) {
        this.consume(); // Consume closing quote
        return value;
      } else {
        value += this.consume();
      }
    }
    
    throw new ParseError('Unterminated string literal', this.pos);
  }

  private parseNamedSchema(): NamedSchema {
    this.skipWhitespace();

    const startpos = this.pos;
    let identifier = '';

    while (this.pos < this.input.length && /[a-zA-Z0-9\-_]/.test(this.peek())) {
      identifier += this.consume();
    }

    if (identifier.length === 0) {
      const schema = this.parseSchema();
      return { schema };
    }

    this.skipWhitespace();

    if (this.consumeStr(':')) {
      this.skipWhitespace();
      const name = identifier;
      const schema = this.parseSchema();
      return { name, schema };
    } else {
      this.pos = startpos;
      const schema = this.parseSchema();
      return { schema };
    }
  }

  private parseReferenceSchema(): Schema {
    // Parse table name
    let tableName = '';
    while (this.pos < this.input.length && /[a-zA-Z0-9\-_]/.test(this.peek())) {
      tableName += this.consume();
    }

    if (tableName.length === 0) {
      throw new ParseError('Expected table name after @', this.pos);
    }

    this.skipWhitespace();

    // Check for array syntax
    if (this.consumeStr('[]')) {
      return {
        type: 'reference',
        tableName,
        isArray: true,
      };
    }

    // Single reference (non-array)
    return {
      type: 'reference',
      tableName,
      isArray: false,
    };
  }
}

export function parseSchema(schemaString: string): Schema {
  const parser = new Parser(schemaString.trim());
  const schema = parser.parseSchema();
  
  if (parser.getPosition() < parser.getInputLength()) {
    throw new ParseError('Unexpected input after schema', parser.getPosition());
  }
  
  return schema;
}