html-textify/dist/index.js

Convert html to plain text

"use strict";
var __defProp = Object.defineProperty;
var __getOwnPropDesc = Object.getOwnPropertyDescriptor;
var __getOwnPropNames = Object.getOwnPropertyNames;
var __hasOwnProp = Object.prototype.hasOwnProperty;
var __export = (target, all) => {
  for (var name in all)
    __defProp(target, name, { get: all[name], enumerable: true });
};
var __copyProps = (to, from, except, desc) => {
  if (from && typeof from === "object" || typeof from === "function") {
    for (let key of __getOwnPropNames(from))
      if (!__hasOwnProp.call(to, key) && key !== except)
        __defProp(to, key, { get: () => from[key], enumerable: !(desc = __getOwnPropDesc(from, key)) || desc.enumerable });
  }
  return to;
};
var __toCommonJS = (mod) => __copyProps(__defProp({}, "__esModule", { value: true }), mod);

// src/index.ts
var index_exports = {};
__export(index_exports, {
  textify: () => textify
});
module.exports = __toCommonJS(index_exports);

// src/utils/preserveFormat.ts
function preserveFormat({
  html,
  ignoreTags = []
}) {
  if (!html) return "";
  html = html.replace(/>\s+</g, "><");
  html = !ignoreTags.includes("br") ? html.replace(/<br\s*\/?>/gi, "\n") : html;
  html = html.replace(
    /<\/(h[1-6]|p)>/gi,
    (match, tag) => ignoreTags.includes(tag.toLowerCase()) ? match : "\n\n"
  );
  html = html.replace(
    /<(b|strong)>(.*?)<\/\1>/gi,
    (match, tag, content) => ignoreTags.includes(tag.toLowerCase()) ? match : `**${content}**`
  );
  html = html.replace(
    /<(i|em)>(.*?)<\/\1>/gi,
    (match, tag, content) => ignoreTags.includes(tag.toLowerCase()) ? match : `*${content}*`
  );
  html = !ignoreTags.includes("a") ? html.replace(
    /<a\s+href="(.*?)".*?>(.*?)<\/a>/gi,
    (_m, href, text) => `${text} (${href})`
  ) : html;
  html = html.replace(/<ol>(.*?)<\/ol>/gis, (match, content) => {
    if (ignoreTags.includes("ol")) return match;
    let counter = 0;
    return content.replace(
      /<li>(.*?)<\/li>/gi,
      (liMatch, liContent) => ignoreTags.includes("li") ? liMatch : `${++counter}. ${liContent}
`
    );
  });
  html = html.replace(/<ul>(.*?)<\/ul>/gis, (match, content) => {
    if (ignoreTags.includes("ul")) return match;
    return content.replace(
      /<li>(.*?)<\/li>/gi,
      (liMatch, liContent) => ignoreTags.includes("li") ? liMatch : `- ${liContent}
`
    );
  });
  html = !ignoreTags.includes("blockquote") ? html.replace(
    /<blockquote>(.*?)<\/blockquote>/gis,
    (_m, content) => content.replace(/<br\s*\/?>/gi, "\n").trim().split("\n").map((line) => `> ${line.trim()}`).join("\n")
  ) : html;
  html = html.replace(
    /<table>(.*?)<\/table>/gis,
    (match, tableContent) => {
      if (ignoreTags.includes("table")) return match;
      return tableContent.replace(/<tr>(.*?)<\/tr>/gi, (trMatch, rowContent) => {
        if (ignoreTags.includes("tr")) return trMatch;
        return rowContent.replace(
          /<t[dh]>(.*?)<\/t[dh]>/gi,
          (cellMatch, cellContent) => ignoreTags.includes("td") || ignoreTags.includes("th") ? cellMatch : `${cellContent}	`
        ).trim().replace(/\t$/, "") + "\n";
      }).trim();
    }
  );
  if (ignoreTags.length === 0) {
    html = html.replace(/<[^>]+>/g, "");
  } else {
    html = html.replace(
      /<\/?([a-z0-9]+)[^>]*>/gi,
      (match, tag) => ignoreTags.includes(tag.toLowerCase()) ? match : ""
    );
  }
  html = html.replace(/&nbsp;/gi, " ").replace(/&amp;/gi, "&").replace(/&lt;/gi, "<").replace(/&gt;/gi, ">");
  html = html.replace(/\n{3,}/g, "\n\n").trim();
  return html;
}

// src/utils/wrapByLength.ts
function wrapByLength(text, length) {
  if (length <= 0) {
    throw new Error("wrap length must be greater than 0");
  }
  const words = text.trim().split(/\s+/);
  const lines = [];
  let line = "";
  for (const word of words) {
    if ((line + " " + word).trim().length > length) {
      if (line) lines.push(line.trim());
      line = word;
    } else {
      line += " " + word;
    }
  }
  if (line) lines.push(line.trim());
  return lines.join("\n");
}

// src/utils/wrapByWords.ts
function wrapByWords(text, count) {
  const words = text.trim().split(/\s+/);
  const lines = [];
  for (let i = 0; i < words.length; i += count) {
    lines.push(words.slice(i, i + count).join(" "));
  }
  return lines.join("\n");
}

// src/index.ts
function textify({
  html,
  preserveFormatting = true,
  ignoreTags = [],
  wrapLength,
  wrapWords
}) {
  if (!html) return "";
  if (preserveFormatting) {
    html = preserveFormat({ html, ignoreTags });
  } else {
    if (ignoreTags.length === 0) {
      html = html.replace(/<[^>]+>/g, "").trim();
    } else {
      const IG = new Set(ignoreTags.map((t) => t.toLowerCase()));
      html = html.replace(
        /<\/?([a-z][a-z0-9-]*)\b[^>]*>/gi,
        (match, tag) => IG.has(tag.toLowerCase()) ? match : ""
      ).trim();
    }
  }
  if (wrapWords && wrapWords > 0) {
    html = wrapByWords(html, wrapWords);
  } else if (wrapLength && wrapLength > 0) {
    html = wrapByLength(html, wrapLength);
  }
  return html;
}
// Annotate the CommonJS export names for ESM import in node:
0 && (module.exports = {
  textify
});