big-rag-modified

import mammoth from "mammoth";
import WordExtractor from "word-extractor";

/**
 * Parse DOCX files (.docx) using mammoth.
 */
export async function parseDOCX(filePath: string): Promise<string> {
  try {
    const result = await mammoth.extractRawText({ path: filePath });
    return result.value
      .replace(/\r\n/g, "\n")
      .replace(/\r/g, "\n")
      .replace(/\n{3,}/g, "\n\n")
      .replace(/ {2,}/g, " ")
      .trim();
  } catch (error) {
    console.error(`Error parsing DOCX file ${filePath}:`, error);
    return "";
  }
}

/**
 * Parse legacy Word binary files (.doc) using word-extractor.
 */
export async function parseDOC(filePath: string): Promise<string> {
  try {
    const extractor = new WordExtractor();
    const doc = await extractor.extract(filePath);
    return doc
      .getBody()
      .replace(/\r\n/g, "\n")
      .replace(/\r/g, "\n")
      .replace(/\n{3,}/g, "\n\n")
      .replace(/ {2,}/g, " ")
      .trim();
  } catch (error) {
    console.error(`Error parsing DOC file ${filePath}:`, error);
    return "";
  }
}