FastGPT/packages/global/common/string/markdown.ts

import { batchRun } from '../fn/utils';
import { getNanoid, simpleText } from './tools';
import type { ImageType } from '../../../service/worker/readFile/type';

/* Delete redundant text in markdown */
export const simpleMarkdownText = (rawText: string) => {
  rawText = simpleText(rawText);

  // Remove a line feed from a hyperlink or picture
  rawText = rawText.replace(/\[([^\]]+)\]\((.+?)\)/g, (match, linkText, url) => {
    const cleanedLinkText = linkText.replace(/\n/g, ' ').trim();

    if (!url) {
      return '';
    }

    return `[${cleanedLinkText}](${url})`;
  });

  // replace special #\.* ……
  const reg1 = /\\([#`!*()+-_\[\]{}\\.])/g;
  if (reg1.test(rawText)) {
    rawText = rawText.replace(reg1, '$1');
  }

  // replace \\n
  rawText = rawText.replace(/\\\\n/g, '\\n');

  // Remove headings and code blocks front spaces
  ['####', '###', '##', '#', '```', '~~~'].forEach((item, i) => {
    const reg = new RegExp(`\\n\\s*${item}`, 'g');
    if (reg.test(rawText)) {
      rawText = rawText.replace(new RegExp(`(\\n)( *)(${item})`, 'g'), '$1$3');
    }
  });

  return rawText.trim();
};

/**
 * format markdown
 * 1. upload base64
 * 2. replace \
 */
export const uploadMarkdownBase64 = async ({
  rawText,
  uploadImgController
}: {
  rawText: string;
  uploadImgController?: (base64: string) => Promise<string>;
}) => {
  if (uploadImgController) {
    // match base64, upload and replace it
    const base64Regex = /data:image\/.*;base64,([^\)]+)/g;
    const base64Arr = rawText.match(base64Regex) || [];

    // upload base64 and replace it
    await batchRun(
      base64Arr,
      async (base64Img) => {
        try {
          const str = await uploadImgController(base64Img);
          rawText = rawText.replace(base64Img, str);
        } catch (error) {
          rawText = rawText.replace(base64Img, '');
          rawText = rawText.replace(/!\[.*\]\(\)/g, '');
        }
      },
      20
    );
  }

  // Remove white space on both sides of the picture
  // const trimReg = /(!\[.*\]\(.*\))\s*/g;
  // if (trimReg.test(rawText)) {
  //   rawText = rawText.replace(trimReg, '$1');
  // }

  return rawText;
};

export const markdownProcess = async ({
  rawText,
  uploadImgController
}: {
  rawText: string;
  uploadImgController?: (base64: string) => Promise<string>;
}) => {
  const imageProcess = await uploadMarkdownBase64({
    rawText,
    uploadImgController
  });

  return simpleMarkdownText(imageProcess);
};

export const matchMdImgTextAndUpload = (text: string) => {
  const base64Regex = /!\[([^\]]*)\]\((data:image\/[^;]+;base64[^)]+)\)/g;
  const imageList: ImageType[] = [];

  text = text.replace(base64Regex, (match, altText, base64Url) => {
    const uuid = `IMAGE_${getNanoid(12)}_IMAGE`;
    const mime = base64Url.split(';')[0].split(':')[1];
    const base64 = base64Url.split(',')[1];

    imageList.push({
      uuid,
      base64,
      mime
    });

    // 保持原有的 alt 文本，只替换 base64 部分
    return `![${altText}](${uuid})`;
  });

  return {
    text,
    imageList
  };
};