inline-schema/src/csv-loader/loader.ts

import { parse } from 'csv-parse/sync';
import { parseSchema, createValidator, parseValue } from '../index.js';
import type { Schema, ReferenceSchema } from '../types.js';
import * as fs from 'fs';
import * as path from 'path';

export interface CsvLoaderOptions {
  delimiter?: string;
  quote?: string;
  escape?: string;
  bom?: boolean;
  comment?: string | false;
  trim?: boolean;
  /** Generate TypeScript declaration file (.d.ts) */
  emitTypes?: boolean;
  /** Output directory for generated type files (relative to output path) */
  typesOutputDir?: string;
  /** Write .d.ts files to disk (useful for dev server) */
  writeToDisk?: boolean;
  /** Base directory for resolving referenced CSV files (default: directory of current file) */
  refBaseDir?: string;
  /** Primary key field name for referenced tables (default: 'id') */
  defaultPrimaryKey?: string;
  /** Current file path (used to resolve relative references) */
  currentFilePath?: string;
}

export interface CsvParseResult {
  /** Parsed CSV data as array of objects */
  data: Record<string, unknown>[];
  /** Generated TypeScript type definition string (if emitTypes is true) */
  typeDefinition?: string;
  /** Property configurations for the CSV columns */
  propertyConfigs: PropertyConfig[];
  /** Referenced table names */
  references: Set<string>;
}

interface PropertyConfig {
  name: string;
  schema: any;
  validator: (value: unknown) => boolean;
  parser: (valueString: string) => unknown;
  /** Whether this property is a reference to another table */
  isReference?: boolean;
  /** Referenced table name (if isReference is true) */
  referenceTableName?: string;
  /** Whether it's an array reference */
  referenceIsArray?: boolean;
}

/** Cache for loaded referenced tables */
const referenceTableCache = new Map<string, Record<string, unknown>[]>();

/**
 * Parse and resolve a reference value.
 * Loads the referenced table and replaces IDs with actual objects.
 */
function parseReferenceValue(
  schema: ReferenceSchema,
  valueString: string,
  refBaseDir: string | undefined,
  defaultPrimaryKey: string,
  currentFilePath: string | undefined
): unknown {
  // Determine the directory to search for referenced files
  const baseDir = refBaseDir || (currentFilePath ? path.dirname(currentFilePath) : process.cwd());
  
  // Build the referenced file path
  const fileName = `${schema.tableName}.csv`;
  const refFilePath = path.isAbsolute(fileName)
    ? fileName
    : path.join(baseDir, fileName);
  
  // Load the referenced table (use cache if already loaded)
  let refTable: Record<string, unknown>[];
  if (referenceTableCache.has(refFilePath)) {
    refTable = referenceTableCache.get(refFilePath)!;
  } else {
    try {
      const refContent = fs.readFileSync(refFilePath, 'utf-8');
      const refResult = parseCsv(refContent, {
        currentFilePath: refFilePath,
        emitTypes: false,
      });
      refTable = refResult.data;
      referenceTableCache.set(refFilePath, refTable);
    } catch (error) {
      throw new Error(
        `Failed to load referenced table "${schema.tableName}" from ${refFilePath}: ${error instanceof Error ? error.message : String(error)}`
      );
    }
  }
  
  // Build a lookup map by primary key
  const primaryKeyMap = new Map<string, Record<string, unknown>>();
  refTable.forEach(row => {
    const pkValue = row[defaultPrimaryKey];
    if (pkValue !== undefined) {
      primaryKeyMap.set(String(pkValue), row);
    }
  });
  
  // Parse the value string to extract IDs
  const valueParser = new ReferenceValueParser(valueString.trim());
  const ids = valueParser.parseIds(schema.isArray);
  
  // Resolve IDs to actual objects
  if (schema.isArray) {
    return ids.map(id => {
      const obj = primaryKeyMap.get(id);
      if (!obj) {
        throw new Error(
          `Reference to "${schema.tableName}" with ${defaultPrimaryKey}="${id}" not found`
        );
      }
      return obj;
    });
  } else {
    // Single reference (first ID if array provided)
    const id = ids[0];
    const obj = primaryKeyMap.get(id);
    if (!obj) {
      throw new Error(
        `Reference to "${schema.tableName}" with ${defaultPrimaryKey}="${id}" not found`
      );
    }
    return obj;
  }
}

/**
 * Parser for reference values (extracts IDs from value string)
 */
class ReferenceValueParser {
  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 consumeStr(str: string): boolean {
    if (this.input.slice(this.pos, this.pos + str.length) === str) {
      this.pos += str.length;
      return true;
    }
    return false;
  }

  parseIds(isArray: boolean): string[] {
    this.skipWhitespace();

    if (isArray) {
      // Parse array format: [id1; id2; id3]
      if (this.peek() === '[') {
        this.consume();
      }

      this.skipWhitespace();

      if (this.peek() === ']') {
        this.consume();
        return [];
      }

      const ids: string[] = [];
      while (true) {
        this.skipWhitespace();
        let id = '';
        while (this.pos < this.input.length && this.peek() !== ';' && this.peek() !== ']') {
          id += this.consume();
        }
        const trimmedId = id.trim();
        if (trimmedId) {
          ids.push(trimmedId);
        }
        this.skipWhitespace();

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

      this.skipWhitespace();
      if (this.peek() === ']') {
        this.consume();
      }

      return ids;
    } else {
      // Parse single ID
      let id = '';
      while (this.pos < this.input.length) {
        const char = this.peek();
        if (char === ';' || char === ']' || char === ',') {
          break;
        }
        id += this.consume();
      }
      return [id.trim()];
    }
  }
}

/**
 * Convert a schema to TypeScript type string
 */
function schemaToTypeString(schema: Schema, resourceNames?: Map<string, string>): string {
  switch (schema.type) {
    case 'string':
      return 'string';
    case 'number':
    case 'int':
    case 'float':
      return 'number';
    case 'boolean':
      return 'boolean';
    case 'reference': {
      // Use the resource name mapping if provided, otherwise capitalize table name
      const typeName = resourceNames?.get(schema.tableName) || 
        schema.tableName.charAt(0).toUpperCase() + schema.tableName.slice(1);
      return schema.isArray ? `readonly ${typeName}[]` : typeName;
    }
    case 'array':
      if (schema.element.type === 'tuple') {
        const tupleElements = schema.element.elements.map((el) => {
          const typeStr = schemaToTypeString(el.schema, resourceNames);
          return el.name ? `readonly ${el.name}: ${typeStr}` : typeStr;
        });
        return `readonly [${tupleElements.join(', ')}]`;
      }
      return `readonly ${schemaToTypeString(schema.element, resourceNames)}[]`;
    case 'tuple':
      const tupleElements = schema.elements.map((el) => {
        const typeStr = schemaToTypeString(el.schema, resourceNames);
        return el.name ? `readonly ${el.name}: ${typeStr}` : typeStr;
      });
      return `readonly [${tupleElements.join(', ')}]`;
    default:
      return 'unknown';
  }
}

/**
 * Generate TypeScript interface for the CSV data
 */
function generateTypeDefinition(
  resourceName: string,
  propertyConfigs: PropertyConfig[],
  references: Set<string>,
  currentFilePath?: string
): string {
  const typeName = resourceName ? `${resourceName}Table` : 'Table';
  
  // Generate import statements for referenced tables
  const imports: string[] = [];
  const resourceNames = new Map<string, string>();
  
  references.forEach(tableName => {
    // Convert table name to type name (parts -> Part, recipes -> Recipe)
    // Remove trailing 's' to get singular form, then capitalize
    let singularName = tableName;
    if (singularName.endsWith('s') && singularName.length > 1) {
      singularName = singularName.slice(0, -1);
    }
    const typeBase = singularName.charAt(0).toUpperCase() + singularName.slice(1);
    resourceNames.set(tableName, typeBase);
    
    // Import from relative path
    const importPath = currentFilePath 
      ? `./${tableName}.csv`
      : `../${tableName}.csv`;
    imports.push(`import type { ${typeBase} } from '${importPath}';`);
  });
  
  const importSection = imports.length > 0 ? imports.join('\n') + '\n\n' : '';
  
  const properties = propertyConfigs
    .map((config) => `    readonly ${config.name}: ${schemaToTypeString(config.schema, resourceNames)};`)
    .join('\n');

  return `${importSection}type ${typeName} = readonly {
${properties}
}[];

declare const data: ${typeName};
export default data;
`;
}

/**
 * Parse CSV content string into structured data with schema validation.
 * This is a standalone function that doesn't depend on webpack/rspack LoaderContext.
 *
 * @param content - CSV content string (must have at least headers + schema row + 1 data row)
 * @param options - Parsing options
 * @returns CsvParseResult containing parsed data and optional type definitions
 */
export function parseCsv(
  content: string,
  options: CsvLoaderOptions & { resourceName?: string } = {}
): CsvParseResult {
  const delimiter = options.delimiter ?? ',';
  const quote = options.quote ?? '"';
  const escape = options.escape ?? '\\';
  const bom = options.bom ?? true;
  const comment = options.comment === false ? undefined : (options.comment ?? '#');
  const trim = options.trim ?? true;
  const emitTypes = options.emitTypes ?? true;
  const refBaseDir = options.refBaseDir;
  const defaultPrimaryKey = options.defaultPrimaryKey ?? 'id';

  const records = parse(content, {
    delimiter,
    quote,
    escape,
    bom,
    comment,
    trim,
    skip_empty_lines: true,
    relax_column_count: true,
  });

  if (records.length < 2) {
    throw new Error('CSV must have at least 2 rows: headers and schemas');
  }

  const headers = records[0];
  const schemas = records[1];

  if (headers.length !== schemas.length) {
    throw new Error(
      `Header count (${headers.length}) does not match schema count (${schemas.length})`
    );
  }

  const propertyConfigs: PropertyConfig[] = headers.map((header: string, index: number) => {
    const schemaString = schemas[index];
    const schema = parseSchema(schemaString);
    
    const config: PropertyConfig = {
      name: header,
      schema,
      validator: createValidator(schema),
      parser: (valueString: string) => parseValue(schema, valueString),
    };
    
    // Check if it's a reference type
    if (schema.type === 'reference') {
      config.isReference = true;
      config.referenceTableName = schema.tableName;
      config.referenceIsArray = schema.isArray;
      // Override parser for reference fields
      config.parser = (valueString: string) => {
        return parseReferenceValue(schema, valueString, refBaseDir, defaultPrimaryKey, options.currentFilePath);
      };
    }
    
    return config;
  });

  // Collect all referenced tables
  const references = new Set<string>();
  propertyConfigs.forEach(config => {
    if (config.isReference && config.referenceTableName) {
      references.add(config.referenceTableName);
    }
  });

  const dataRows = records.slice(2);
  const objects = dataRows.map((row: string[], rowIndex: number) => {
    const obj: Record<string, unknown> = {};
    propertyConfigs.forEach((config, colIndex) => {
      const rawValue = row[colIndex] ?? '';
      try {
        const parsed = config.parser(rawValue);
        // Skip validation for reference fields (validation happens during reference resolution)
        if (!config.isReference && !config.validator(parsed)) {
          throw new Error(
            `Validation failed for property "${config.name}" at row ${rowIndex + 3}: ${rawValue}`
          );
        }
        obj[config.name] = parsed;
      } catch (error) {
        if (error instanceof Error) {
          throw new Error(
            `Failed to parse property "${config.name}" at row ${rowIndex + 3}, column ${colIndex + 1}: ${error.message}`
          );
        }
        throw error;
      }
    });
    return obj;
  });

  const result: CsvParseResult = {
    data: objects,
    propertyConfigs,
    references,
  };

  if (emitTypes) {
    result.typeDefinition = generateTypeDefinition(
      options.resourceName || '', 
      propertyConfigs,
      references,
      options.currentFilePath
    );
  }

  return result;
}

/**
 * Generate JavaScript module code from CSV content.
 * Returns a string that can be used as a module export.
 *
 * @param content - CSV content string
 * @param options - Parsing options
 * @returns JavaScript module code string
 */
export function csvToModule(
  content: string,
  options: CsvLoaderOptions & { resourceName?: string } = {}
): { js: string; dts?: string } {
  const result = parseCsv(content, options);

  const json = JSON.stringify(result.data, null, 2);
  const js = `export default ${json};`;

  return {
    js,
    dts: result.typeDefinition,
  };
}