Nexus/packages/application/src/use-cases/dispo-import/read-workbook.ts

import { stat } from "node:fs/promises";
import path from "node:path";

export type WorksheetCellValue = boolean | Date | number | string | null;
export type WorksheetMatrix = WorksheetCellValue[][];

// Path allowlist: dispo workbooks must live inside DISPO_IMPORT_DIR. Without
// this guard an admin (or a compromised admin token) could point the ExcelJS
// parser at any file the app process can read, reaching library CVEs on
// arbitrary filesystem paths. Default picks an in-repo `imports/` directory so
// local dev still works; production deployments should set DISPO_IMPORT_DIR
// explicitly to a dedicated volume.
function resolveImportDir(): string {
  const configured = process.env["DISPO_IMPORT_DIR"];
  const base = configured && configured.trim().length > 0 ? configured : path.resolve("imports");
  return path.resolve(base);
}

type ExcelJsModule = typeof import("exceljs");
type ExcelJsWorkbook = InstanceType<ExcelJsModule["Workbook"]>;
type ExcelJsXlsxReader = ExcelJsWorkbook["xlsx"] & {
  _processTableEntry?: (
    stream: unknown,
    model: Record<string, unknown>,
    name: string,
  ) => Promise<unknown>;
};

const DISPO_WORKBOOK_EXTENSION = ".xlsx";
export const MAX_DISPO_WORKBOOK_BYTES = 15 * 1024 * 1024;
export const MAX_DISPO_WORKBOOK_ROWS = 10000;
export const MAX_DISPO_WORKBOOK_COLUMNS = 1024;

const EXCELJS_IGNORE_WORKSHEET_NODES = ["tableParts"];
const EXCELJS_UNSUPPORTED_TABLE_FILTER_MARKER = '"name":"dateGroupItem"';

let _excelJs: ExcelJsModule | null = null;
const worksheetMatrixCache = new Map<string, Promise<WorksheetMatrix>>();

function normalizeExcelJsModule(
  module: ExcelJsModule | { default?: ExcelJsModule },
): ExcelJsModule {
  return "Workbook" in module ? module : (module.default as ExcelJsModule);
}

async function getExcelJS() {
  if (!_excelJs) {
    _excelJs = normalizeExcelJsModule(await import("exceljs"));
  }

  return _excelJs;
}

function trimTrailingNulls(row: WorksheetCellValue[]): WorksheetCellValue[] {
  let end = row.length;
  while (end > 0 && row[end - 1] === null) {
    end -= 1;
  }
  return row.slice(0, end);
}

function trimTrailingEmptyRows(rows: WorksheetMatrix): WorksheetMatrix {
  let end = rows.length;
  while (end > 0 && rows[end - 1]?.length === 0) {
    end -= 1;
  }
  return rows.slice(0, end);
}

function cloneWorksheetMatrix(rows: WorksheetMatrix): WorksheetMatrix {
  return rows.map((row) => row.slice());
}

async function validateWorkbookPath(workbookPath: string): Promise<string> {
  const importDir = resolveImportDir();
  const resolvedPath = path.resolve(importDir, workbookPath);

  // path.relative returns a string that either starts with ".." (or equals
  // "..") or is absolute when the resolved path escapes importDir. Both are
  // rejected — defence against `..` sequences, symlink-shaped escapes and
  // absolute-path injection via the tRPC surface.
  const relative = path.relative(importDir, resolvedPath);
  if (relative === ".." || relative.startsWith(`..${path.sep}`) || path.isAbsolute(relative)) {
    throw new Error(
      `Workbook path must be inside the configured import directory: "${workbookPath}"`,
    );
  }

  if (path.extname(resolvedPath).toLowerCase() !== DISPO_WORKBOOK_EXTENSION) {
    throw new Error(
      `Only ${DISPO_WORKBOOK_EXTENSION} workbooks are supported for dispo imports: "${resolvedPath}"`,
    );
  }

  const fileStat = await stat(resolvedPath);
  if (!fileStat.isFile()) {
    throw new Error(`Workbook path must point to a readable file: "${resolvedPath}"`);
  }

  if (fileStat.size <= 0) {
    throw new Error(`Workbook file is empty: "${resolvedPath}"`);
  }

  if (fileStat.size > MAX_DISPO_WORKBOOK_BYTES) {
    throw new Error(
      `Workbook file exceeds the ${MAX_DISPO_WORKBOOK_BYTES} byte import limit: "${resolvedPath}"`,
    );
  }

  return resolvedPath;
}

function normalizeWorksheetCellValue(value: unknown): WorksheetCellValue {
  if (value === undefined || value === null) {
    return null;
  }

  if (typeof value === "string" || typeof value === "number" || typeof value === "boolean") {
    return value;
  }

  if (value instanceof Date) {
    return value;
  }

  if (typeof value === "object") {
    const record = value as Record<string, unknown>;

    if ("result" in record) {
      return normalizeWorksheetCellValue(record.result);
    }

    if ("text" in record && typeof record.text === "string") {
      return record.text;
    }

    if ("hyperlink" in record && typeof record.hyperlink === "string") {
      return record.hyperlink;
    }

    if ("richText" in record && Array.isArray(record.richText)) {
      return record.richText
        .map((part) => {
          if (part && typeof part === "object" && "text" in part) {
            const text = (part as { text?: unknown }).text;
            return typeof text === "string" ? text : "";
          }
          return "";
        })
        .join("");
    }

    if ("error" in record && typeof record.error === "string") {
      return record.error;
    }
  }

  return String(value);
}

function assertWorksheetShape(
  rows: WorksheetMatrix,
  sheetName: string,
  workbookPath: string,
): void {
  if (rows.length > MAX_DISPO_WORKBOOK_ROWS) {
    throw new Error(
      `Worksheet "${sheetName}" in "${workbookPath}" exceeds the ${MAX_DISPO_WORKBOOK_ROWS} row import limit.`,
    );
  }

  const widestRow = rows.reduce((max, row) => Math.max(max, row.length), 0);
  if (widestRow > MAX_DISPO_WORKBOOK_COLUMNS) {
    throw new Error(
      `Worksheet "${sheetName}" in "${workbookPath}" exceeds the ${MAX_DISPO_WORKBOOK_COLUMNS} column import limit.`,
    );
  }
}

function isUnsupportedExcelJsTableFilterError(error: unknown): boolean {
  return error instanceof Error && error.message.includes(EXCELJS_UNSUPPORTED_TABLE_FILTER_MARKER);
}

function patchExcelJsTableCompatibility(workbook: ExcelJsWorkbook): void {
  const reader = workbook.xlsx as ExcelJsXlsxReader;
  const originalProcessTableEntry = reader._processTableEntry;

  if (typeof originalProcessTableEntry !== "function") {
    return;
  }

  reader._processTableEntry = async function processTableEntryWithCompatibilityFallback(
    stream,
    model,
    name,
  ) {
    try {
      return await originalProcessTableEntry.call(this, stream, model, name);
    } catch (error) {
      if (isUnsupportedExcelJsTableFilterError(error)) {
        return undefined;
      }

      throw error;
    }
  };
}

export async function readWorksheetMatrix(
  workbookPath: string,
  sheetName: string,
): Promise<WorksheetMatrix> {
  const resolvedPath = await validateWorkbookPath(workbookPath);
  const cacheKey = `${resolvedPath}::${sheetName}`;
  const cachedMatrix = worksheetMatrixCache.get(cacheKey);
  if (cachedMatrix) {
    return cloneWorksheetMatrix(await cachedMatrix);
  }

  const matrixPromise = (async () => {
    const ExcelJS = await getExcelJS();
    const workbook = new ExcelJS.Workbook();
    patchExcelJsTableCompatibility(workbook);
    await workbook.xlsx.readFile(resolvedPath, { ignoreNodes: EXCELJS_IGNORE_WORKSHEET_NODES });

    const worksheet = workbook.getWorksheet(sheetName);
    if (!worksheet) {
      throw new Error(`Worksheet "${sheetName}" not found in workbook "${resolvedPath}"`);
    }

    const rows: WorksheetMatrix = [];
    for (let rowNumber = 1; rowNumber <= worksheet.rowCount; rowNumber += 1) {
      const row = worksheet.getRow(rowNumber);
      const cells: WorksheetCellValue[] = [];

      for (let columnNumber = 1; columnNumber <= row.cellCount; columnNumber += 1) {
        cells.push(normalizeWorksheetCellValue(row.getCell(columnNumber).value));
      }

      rows.push(trimTrailingNulls(cells));
    }

    const normalizedRows = trimTrailingEmptyRows(rows);

    assertWorksheetShape(normalizedRows, sheetName, resolvedPath);

    return normalizedRows;
  })();

  worksheetMatrixCache.set(cacheKey, matrixPromise);

  try {
    return cloneWorksheetMatrix(await matrixPromise);
  } catch (error) {
    worksheetMatrixCache.delete(cacheKey);
    throw error;
  }
}

export function getCellString(
  rows: WorksheetMatrix,
  rowNumber: number,
  columnNumber: number,
): string | null {
  const value = rows[rowNumber - 1]?.[columnNumber - 1];
  if (value === null || value === undefined) {
    return null;
  }

  if (value instanceof Date) {
    return value.toISOString();
  }

  return String(value);
}

export function toColumnLetter(columnNumber: number): string {
  let current = columnNumber;
  let result = "";

  while (current > 0) {
    const remainder = (current - 1) % 26;
    result = String.fromCharCode(65 + remainder) + result;
    current = Math.floor((current - 1) / 26);
  }

  return result;
}