javascript - 通过带有正则表达式的拆分函数拆分表情符号字符串

标签 javascript regex unicode emoji

我想使用 Javascript 的 split 函数来拆分表情符号字符串。在 stackoverflow 中有很多这样的问题,但我找不到任何完整的解决方案。所以我用我自己的方式来做:

a) 将拆分函数与正则表达式结合使用。

b) 通过正则表达式 unicode 匹配拆分表情符号字符:从\uD800 到\uDBFF 和从\uDC00 到\uDFFF。

c) 在此正则表达式中,排除带零连接符 (\u200D) 和变体选择器 (\uFE0F) 字符。 所以我这样写:

var p = '👦🏼👧🏼👩🏼👧🏾👧🏿👩‍👩‍👧‍👧👭👫👨‍❤️‍💋‍👨';

并将其拆分:

var split = p.split(/(?![\u200D\uFE0F])([\uD800-\uDBFF][\uDC00-\uDFFF])/);

但是结果是错误的:(

["", "👦", "", "🏼", "", "👧", "", "🏼", "", "👩", "", "🏼", "", "👧", "", "🏾", "", "👧", "", "🏿", "", "👩", "‍", "👩", "‍", "👧", "‍", "👧", "", "👭", "", "👫", "", "👨", "‍❤️‍", "💋", "‍", "👨", ""]

我是否正确使用了正则表达式的排除选择器?如果正确,是我的想法造成的错误吗? 预期结果需要为:["👦🏼", "👧🏼", "👩🏼", "👧🏾", "👧🏿", "👩‍👩‍👧‍👧", "👭", "👫", "👨‍❤️‍💋‍👨"]

===

我想更新信息。我为我的网站解决了这个问题:https://www.emojionline.org .你可以测试。我只使用一本包含所有表情符号的字典,并使用替换功能将每个表情符号替换为 |emoji|。我可以用符号 | 拆分字符串表情符号。效果很好:)

最佳答案

我扩展了 emoji-regex Mathias Bynens 的 [\uD800-\uDBFF][\uDC00-\uDFFF](?:[\u200D\uFE0F][\uD800-\uDBFF][\uDC00-\uDFFF]){2,}选择。它匹配一个常见的 2 字节表情符号,后跟 2 个或更多序列(这可以用 {2,} 限制量词控制)零宽度连接符或变体选择器,再一次匹配常见的 2 字节表情符号字符。

如果没有替代项,结果是 [ '👦🏼','👧🏼','👩🏼','👧🏾','👧🏿','👩‍👩‍👧','👧','👭','👫','👨‍❤️‍💋‍👨' ] .

var p = 'my family 👦🏼👧🏼👩🏼👧🏾👧🏿👩‍👩‍👧‍👧👭👫👨‍❤️‍💋‍👨 here';
var rx = /([\uD800-\uDBFF][\uDC00-\uDFFF](?:[\u200D\uFE0F][\uD800-\uDBFF][\uDC00-\uDFFF]){2,}|\uD83D\uDC69(?:\u200D(?:(?:\uD83D\uDC69\u200D)?\uD83D\uDC67|(?:\uD83D\uDC69\u200D)?\uD83D\uDC66)|\uD83C[\uDFFB-\uDFFF])|\uD83D\uDC69\u200D(?:\uD83D\uDC69\u200D)?\uD83D\uDC66\u200D\uD83D\uDC66|\uD83D\uDC69\u200D(?:\uD83D\uDC69\u200D)?\uD83D\uDC67\u200D(?:\uD83D[\uDC66\uDC67])|\uD83C\uDFF3\uFE0F\u200D\uD83C\uDF08|(?:\uD83C[\uDFC3\uDFC4\uDFCA]|\uD83D[\uDC6E\uDC71\uDC73\uDC77\uDC81\uDC82\uDC86\uDC87\uDE45-\uDE47\uDE4B\uDE4D\uDE4E\uDEA3\uDEB4-\uDEB6]|\uD83E[\uDD26\uDD37-\uDD39\uDD3D\uDD3E\uDDD6-\uDDDD])(?:\uD83C[\uDFFB-\uDFFF])\u200D[\u2640\u2642]\uFE0F|\uD83D\uDC69(?:\uD83C[\uDFFB-\uDFFF])\u200D(?:\uD83C[\uDF3E\uDF73\uDF93\uDFA4\uDFA8\uDFEB\uDFED]|\uD83D[\uDCBB\uDCBC\uDD27\uDD2C\uDE80\uDE92])|(?:\uD83C[\uDFC3\uDFC4\uDFCA]|\uD83D[\uDC6E\uDC6F\uDC71\uDC73\uDC77\uDC81\uDC82\uDC86\uDC87\uDE45-\uDE47\uDE4B\uDE4D\uDE4E\uDEA3\uDEB4-\uDEB6]|\uD83E[\uDD26\uDD37-\uDD39\uDD3C-\uDD3E\uDDD6-\uDDDF])\u200D[\u2640\u2642]\uFE0F|\uD83C\uDDFD\uD83C\uDDF0|\uD83C\uDDF6\uD83C\uDDE6|\uD83C\uDDF4\uD83C\uDDF2|\uD83C\uDDE9(?:\uD83C[\uDDEA\uDDEC\uDDEF\uDDF0\uDDF2\uDDF4\uDDFF])|\uD83C\uDDF7(?:\uD83C[\uDDEA\uDDF4\uDDF8\uDDFA\uDDFC])|\uD83C\uDDE8(?:\uD83C[\uDDE6\uDDE8\uDDE9\uDDEB-\uDDEE\uDDF0-\uDDF5\uDDF7\uDDFA-\uDDFF])|(?:\u26F9|\uD83C[\uDFCB\uDFCC]|\uD83D\uDD75)(?:\uFE0F\u200D[\u2640\u2642]|(?:\uD83C[\uDFFB-\uDFFF])\u200D[\u2640\u2642])\uFE0F|(?:\uD83D\uDC41\uFE0F\u200D\uD83D\uDDE8|\uD83D\uDC69(?:\uD83C[\uDFFB-\uDFFF])\u200D[\u2695\u2696\u2708]|\uD83D\uDC69\u200D[\u2695\u2696\u2708]|\uD83D\uDC68(?:(?:\uD83C[\uDFFB-\uDFFF])\u200D[\u2695\u2696\u2708]|\u200D[\u2695\u2696\u2708]))\uFE0F|\uD83C\uDDF2(?:\uD83C[\uDDE6\uDDE8-\uDDED\uDDF0-\uDDFF])|\uD83D\uDC69\u200D(?:\uD83C[\uDF3E\uDF73\uDF93\uDFA4\uDFA8\uDFEB\uDFED]|\uD83D[\uDCBB\uDCBC\uDD27\uDD2C\uDE80\uDE92]|\u2764\uFE0F\u200D(?:\uD83D\uDC8B\u200D(?:\uD83D[\uDC68\uDC69])|\uD83D[\uDC68\uDC69]))|\uD83C\uDDF1(?:\uD83C[\uDDE6-\uDDE8\uDDEE\uDDF0\uDDF7-\uDDFB\uDDFE])|\uD83C\uDDEF(?:\uD83C[\uDDEA\uDDF2\uDDF4\uDDF5])|\uD83C\uDDED(?:\uD83C[\uDDF0\uDDF2\uDDF3\uDDF7\uDDF9\uDDFA])|\uD83C\uDDEB(?:\uD83C[\uDDEE-\uDDF0\uDDF2\uDDF4\uDDF7])|[#\*0-9]\uFE0F\u20E3|\uD83C\uDDE7(?:\uD83C[\uDDE6\uDDE7\uDDE9-\uDDEF\uDDF1-\uDDF4\uDDF6-\uDDF9\uDDFB\uDDFC\uDDFE\uDDFF])|\uD83C\uDDE6(?:\uD83C[\uDDE8-\uDDEC\uDDEE\uDDF1\uDDF2\uDDF4\uDDF6-\uDDFA\uDDFC\uDDFD\uDDFF])|\uD83C\uDDFF(?:\uD83C[\uDDE6\uDDF2\uDDFC])|\uD83C\uDDF5(?:\uD83C[\uDDE6\uDDEA-\uDDED\uDDF0-\uDDF3\uDDF7-\uDDF9\uDDFC\uDDFE])|\uD83C\uDDFB(?:\uD83C[\uDDE6\uDDE8\uDDEA\uDDEC\uDDEE\uDDF3\uDDFA])|\uD83C\uDDF3(?:\uD83C[\uDDE6\uDDE8\uDDEA-\uDDEC\uDDEE\uDDF1\uDDF4\uDDF5\uDDF7\uDDFA\uDDFF])|\uD83C\uDFF4\uDB40\uDC67\uDB40\uDC62(?:\uDB40\uDC77\uDB40\uDC6C\uDB40\uDC73|\uDB40\uDC73\uDB40\uDC63\uDB40\uDC74|\uDB40\uDC65\uDB40\uDC6E\uDB40\uDC67)\uDB40\uDC7F|\uD83D\uDC68(?:\u200D(?:\u2764\uFE0F\u200D(?:\uD83D\uDC8B\u200D)?\uD83D\uDC68|(?:(?:\uD83D[\uDC68\uDC69])\u200D)?\uD83D\uDC66\u200D\uD83D\uDC66|(?:(?:\uD83D[\uDC68\uDC69])\u200D)?\uD83D\uDC67\u200D(?:\uD83D[\uDC66\uDC67])|\uD83C[\uDF3E\uDF73\uDF93\uDFA4\uDFA8\uDFEB\uDFED]|\uD83D[\uDCBB\uDCBC\uDD27\uDD2C\uDE80\uDE92])|(?:\uD83C[\uDFFB-\uDFFF])\u200D(?:\uD83C[\uDF3E\uDF73\uDF93\uDFA4\uDFA8\uDFEB\uDFED]|\uD83D[\uDCBB\uDCBC\uDD27\uDD2C\uDE80\uDE92]))|\uD83C\uDDF8(?:\uD83C[\uDDE6-\uDDEA\uDDEC-\uDDF4\uDDF7-\uDDF9\uDDFB\uDDFD-\uDDFF])|\uD83C\uDDF0(?:\uD83C[\uDDEA\uDDEC-\uDDEE\uDDF2\uDDF3\uDDF5\uDDF7\uDDFC\uDDFE\uDDFF])|\uD83C\uDDFE(?:\uD83C[\uDDEA\uDDF9])|\uD83C\uDDEE(?:\uD83C[\uDDE8-\uDDEA\uDDF1-\uDDF4\uDDF6-\uDDF9])|\uD83C\uDDF9(?:\uD83C[\uDDE6\uDDE8\uDDE9\uDDEB-\uDDED\uDDEF-\uDDF4\uDDF7\uDDF9\uDDFB\uDDFC\uDDFF])|\uD83C\uDDEC(?:\uD83C[\uDDE6\uDDE7\uDDE9-\uDDEE\uDDF1-\uDDF3\uDDF5-\uDDFA\uDDFC\uDDFE])|\uD83C\uDDFA(?:\uD83C[\uDDE6\uDDEC\uDDF2\uDDF3\uDDF8\uDDFE\uDDFF])|\uD83C\uDDEA(?:\uD83C[\uDDE6\uDDE8\uDDEA\uDDEC\uDDED\uDDF7-\uDDFA])|\uD83C\uDDFC(?:\uD83C[\uDDEB\uDDF8])|(?:\u26F9|\uD83C[\uDFCB\uDFCC]|\uD83D\uDD75)(?:\uD83C[\uDFFB-\uDFFF])|(?:\uD83C[\uDFC3\uDFC4\uDFCA]|\uD83D[\uDC6E\uDC71\uDC73\uDC77\uDC81\uDC82\uDC86\uDC87\uDE45-\uDE47\uDE4B\uDE4D\uDE4E\uDEA3\uDEB4-\uDEB6]|\uD83E[\uDD26\uDD37-\uDD39\uDD3D\uDD3E\uDDD6-\uDDDD])(?:\uD83C[\uDFFB-\uDFFF])|(?:[\u261D\u270A-\u270D]|\uD83C[\uDF85\uDFC2\uDFC7]|\uD83D[\uDC42\uDC43\uDC46-\uDC50\uDC66\uDC67\uDC70\uDC72\uDC74-\uDC76\uDC78\uDC7C\uDC83\uDC85\uDCAA\uDD74\uDD7A\uDD90\uDD95\uDD96\uDE4C\uDE4F\uDEC0\uDECC]|\uD83E[\uDD18-\uDD1C\uDD1E\uDD1F\uDD30-\uDD36\uDDD1-\uDDD5])(?:\uD83C[\uDFFB-\uDFFF])|\uD83D\uDC68(?:\u200D(?:(?:(?:\uD83D[\uDC68\uDC69])\u200D)?\uD83D\uDC67|(?:(?:\uD83D[\uDC68\uDC69])\u200D)?\uD83D\uDC66)|\uD83C[\uDFFB-\uDFFF])|(?:[\u261D\u26F9\u270A-\u270D]|\uD83C[\uDF85\uDFC2-\uDFC4\uDFC7\uDFCA-\uDFCC]|\uD83D[\uDC42\uDC43\uDC46-\uDC50\uDC66-\uDC69\uDC6E\uDC70-\uDC78\uDC7C\uDC81-\uDC83\uDC85-\uDC87\uDCAA\uDD74\uDD75\uDD7A\uDD90\uDD95\uDD96\uDE45-\uDE47\uDE4B-\uDE4F\uDEA3\uDEB4-\uDEB6\uDEC0\uDECC]|\uD83E[\uDD18-\uDD1C\uDD1E\uDD1F\uDD26\uDD30-\uDD39\uDD3D\uDD3E\uDDD1-\uDDDD])(?:\uD83C[\uDFFB-\uDFFF])?|(?:[\u231A\u231B\u23E9-\u23EC\u23F0\u23F3\u25FD\u25FE\u2614\u2615\u2648-\u2653\u267F\u2693\u26A1\u26AA\u26AB\u26BD\u26BE\u26C4\u26C5\u26CE\u26D4\u26EA\u26F2\u26F3\u26F5\u26FA\u26FD\u2705\u270A\u270B\u2728\u274C\u274E\u2753-\u2755\u2757\u2795-\u2797\u27B0\u27BF\u2B1B\u2B1C\u2B50\u2B55]|\uD83C[\uDC04\uDCCF\uDD8E\uDD91-\uDD9A\uDDE6-\uDDFF\uDE01\uDE1A\uDE2F\uDE32-\uDE36\uDE38-\uDE3A\uDE50\uDE51\uDF00-\uDF20\uDF2D-\uDF35\uDF37-\uDF7C\uDF7E-\uDF93\uDFA0-\uDFCA\uDFCF-\uDFD3\uDFE0-\uDFF0\uDFF4\uDFF8-\uDFFF]|\uD83D[\uDC00-\uDC3E\uDC40\uDC42-\uDCFC\uDCFF-\uDD3D\uDD4B-\uDD4E\uDD50-\uDD67\uDD7A\uDD95\uDD96\uDDA4\uDDFB-\uDE4F\uDE80-\uDEC5\uDECC\uDED0-\uDED2\uDEEB\uDEEC\uDEF4-\uDEF8]|\uD83E[\uDD10-\uDD3A\uDD3C-\uDD3E\uDD40-\uDD45\uDD47-\uDD4C\uDD50-\uDD6B\uDD80-\uDD97\uDDC0\uDDD0-\uDDE6])|(?:[#\*0-9\xA9\xAE\u203C\u2049\u2122\u2139\u2194-\u2199\u21A9\u21AA\u231A\u231B\u2328\u23CF\u23E9-\u23F3\u23F8-\u23FA\u24C2\u25AA\u25AB\u25B6\u25C0\u25FB-\u25FE\u2600-\u2604\u260E\u2611\u2614\u2615\u2618\u261D\u2620\u2622\u2623\u2626\u262A\u262E\u262F\u2638-\u263A\u2640\u2642\u2648-\u2653\u2660\u2663\u2665\u2666\u2668\u267B\u267F\u2692-\u2697\u2699\u269B\u269C\u26A0\u26A1\u26AA\u26AB\u26B0\u26B1\u26BD\u26BE\u26C4\u26C5\u26C8\u26CE\u26CF\u26D1\u26D3\u26D4\u26E9\u26EA\u26F0-\u26F5\u26F7-\u26FA\u26FD\u2702\u2705\u2708-\u270D\u270F\u2712\u2714\u2716\u271D\u2721\u2728\u2733\u2734\u2744\u2747\u274C\u274E\u2753-\u2755\u2757\u2763\u2764\u2795-\u2797\u27A1\u27B0\u27BF\u2934\u2935\u2B05-\u2B07\u2B1B\u2B1C\u2B50\u2B55\u3030\u303D\u3297\u3299]|\uD83C[\uDC04\uDCCF\uDD70\uDD71\uDD7E\uDD7F\uDD8E\uDD91-\uDD9A\uDDE6-\uDDFF\uDE01\uDE02\uDE1A\uDE2F\uDE32-\uDE3A\uDE50\uDE51\uDF00-\uDF21\uDF24-\uDF93\uDF96\uDF97\uDF99-\uDF9B\uDF9E-\uDFF0\uDFF3-\uDFF5\uDFF7-\uDFFF]|\uD83D[\uDC00-\uDCFD\uDCFF-\uDD3D\uDD49-\uDD4E\uDD50-\uDD67\uDD6F\uDD70\uDD73-\uDD7A\uDD87\uDD8A-\uDD8D\uDD90\uDD95\uDD96\uDDA4\uDDA5\uDDA8\uDDB1\uDDB2\uDDBC\uDDC2-\uDDC4\uDDD1-\uDDD3\uDDDC-\uDDDE\uDDE1\uDDE3\uDDE8\uDDEF\uDDF3\uDDFA-\uDE4F\uDE80-\uDEC5\uDECB-\uDED2\uDEE0-\uDEE5\uDEE9\uDEEB\uDEEC\uDEF0\uDEF3-\uDEF8]|\uD83E[\uDD10-\uDD3A\uDD3C-\uDD3E\uDD40-\uDD45\uDD47-\uDD4C\uDD50-\uDD6B\uDD80-\uDD97\uDDC0\uDDD0-\uDDE6])\uFE0F)/;
var res = p.split(rx).filter(Boolean);
document.body.innerHTML = res;

关于javascript - 通过带有正则表达式的拆分函数拆分表情符号字符串,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/44062544/

相关文章:

javascript - 使用 JavaScript 跟踪对象键的有效方法

Firefox 中的 javascript 页面导航错误

javascript - ng-模式/ng-显示 AngularJS

regexp_replace 就像我给它一个全局标志一样,但我没有

c++ - 在 Windows 上使用 C++ 将希伯来语字符串放入变量中

regex - 为什么这个带有 2 字节 unicode 字符的正则表达式在匹配时为左值发出 "uninitialized"警告?

javascript - 如何改进javascript中提取xml节点?

javascript - 为什么要在函数定义调用对中编写全局代码?

正则表达式:在由边界定义的组中,仅匹配 XX

c++ - 单例日志类中运算符 << 的问题