Outlook Email Body Parser

outlookEmailBodyParser.js

export default class OutlookEmailBodyParser {
  /** @type {String} */
  #body = null;
  /**
   * Creates an instance of the Outlook Email Body Parser
   * Next you call:
   * - getLatestResponse() to get the most recent message
   * @param {String} body
   */
  constructor(body) {
    this.#body = body;
  }
  /**
   * Returns the latest response
   */
  getLatestResponse = () => {
    const lines = this.#body.replace("/\r/g", "\n").split("\n");
    // any line that starts with a word, a color and a space, like From: , to: , Cc:, Date:
    const prologLine = /(^[A-Z]{2,8}:\s)/i;
    // any line that ends with a colon
    const lineEndsWithColon = /^.+(:)$/;
    // covers general patterns of first.last@email.domain
    const emailRegex = /[a-zA-Z0-9._-]+@[a-zA-Z0-9-]+\.[a-zA-Z]{2,6}/;
    // covers -------, _______, -----original message----, _______PREV______
    const breakRegex = /^([-_]+(\w{0,15}(\s|\s{0})){0,3}[-_]+)$/;
    // looks for a 4 digit number on the line, we grab it and see if it looks reasonable
    // meaning in compare is the 4 digit number starting with 19 or 20.
    const containsYear = /([/\s][0-9]{4})/;
    // looks for a time in formats 4:44, 16:44, 4:44 AM, 4:44 PM
    // we then look at capture groups to verify in range
    const containsTime = /\s([0-9]{1,2}):([0-9]{2})(\w{2}|\s\w{2}|:[0-9]{2}|.{0})/;
    // -- START --
    var breakOnLine = "";
    var fFoundLineBreak = false;
    var candidateLines = 0;
    var prevLine = "";
    for (const line of lines) {
      var gmailFoundCount = 0;
      var outlookFoundCount = 0;
      if (breakRegex.test(line)) {
        fFoundLineBreak = true;
        candidateLines++;
        prevLine = line;
        continue;
      }
      if (emailRegex.test(line)) {
        gmailFoundCount++;
        outlookFoundCount++;
      }
      if (prologLine.test(line)) outlookFoundCount++;
      if (lineEndsWithColon.test(line)) gmailFoundCount++;
      if (containsYear.test(line)) {
        const year = containsYear.exec(line);
        if (year.length === 2) {
          const num = Number.parseInt(year[0].trim());
          if (!Number.isNaN(num) && num > 1900 && num < 2100) {
            gmailFoundCount++;
            outlookFoundCount++;);
          }
        }
      }
      if (containsTime.test(line)) {
        const time = containsTime.exec(line);
        if (time.length >= 3) {
          const hour = Number.parseInt(time[1].trim());
          const min = Number.parseInt(time[2].trim());
          if (!Number.isNaN(hour) && !Number.isNaN(min) && hour >= 0 && hour <= 23 && min >= 0 && min <= 59) {
            gmailFoundCount++;
            outlookFoundCount++;
          }
        }
      }
      if (fFoundLineBreak) outlookFoundCount++;
      ////////////////////////////////////
      // VALIDATE OUTLOOK
      ////////////////////////////////////
      if (candidateLines >= 1 && outlookFoundCount > 2) {
        breakOnLine = prevLine;
        break;
      }
      ////////////////////////////////////
      // VALIDATE GMAIL
      ////////////////////////////////////
      if (gmailFoundCount >= 4) {
        breakOnLine = line;
        break;
      }
      if (candidateLines === 1 && gmailFoundCount === 1) {
        breakOnLine = prevLine;
        break;
      }
      ////////////////////////////////////
      // reset
      ////////////////////////////////////
      if (candidateLines === 3) candidateLines = 0;
      if (outlookFoundCount >= 2) candidateLines++;
      if (gmailFoundCount === 3) candidateLines++;
      if (candidateLines === 1) prevLine = line;
      fFoundLineBreak = false; // must set here
    }
    var latestResponse = this.#body;
    if (breakOnLine) {
      const pos = this.#body.indexOf(breakOnLine);
      latestResponse = this.#body.substring(0, pos);
    }
    // return
    return latestResponse;
  };
}