将数组添加到多维数组或对象中

时间:2018-05-17 07:40:12

标签: javascript

我正在将wysiwyg生成的内容解析为React中的目录小部件。

到目前为止,我正在遍历标题并将它们添加到数组中。

如何将它们全部集成到一个多维数组或对象中(最好的方法),使它看起来更像:

h1-1
    h2-1
        h3-1

h1-2
    h2-2
        h3-2

h1-3
    h2-3
        h3-3

然后我可以在UI中使用有序列表进行渲染。

const str = "<h1>h1-1</h1><h2>h2-1</h2><h3>h3-1</h3><p>something</p><h1>h1-2</h1><h2>h2-2</h2><h3>h3-2</h3>";

const patternh1 = /<h1>(.*?)<\/h1>/g;
const patternh2 = /<h2>(.*?)<\/h2>/g;
const patternh3 = /<h3>(.*?)<\/h3>/g;

let h1s = [];
let h2s = [];
let h3s = [];

let matchh1, matchh2, matchh3;

while (matchh1 = patternh1.exec(str))
    h1s.push(matchh1[1])

while (matchh2 = patternh2.exec(str))
    h2s.push(matchh2[1])
    
while (matchh3 = patternh3.exec(str))
    h3s.push(matchh3[1])
    
console.log(h1s)
console.log(h2s)
console.log(h3s)

5 个答案:

答案 0 :(得分:13)

我不了解您,但我讨厌使用正则表达式解析HTML。相反,我认为让DOM处理这个问题更好:

const str = `<h1>h1-1</h1>
  <h3>h3-1</h3>
  <h3>h3-2</h3>
  <p>something</p>
  <h1>h1-2</h1>
  <h2>h2-2</h2>
  <h3>h3-2</h3>`;

const wrapper = document.createElement('div');
wrapper.innerHTML = str.trim();

let tree = [];
let leaf = null;

for (const node of wrapper.querySelectorAll("h1, h2, h3, h4, h5, h6")) {
  const nodeLevel = parseInt(node.tagName[1]);
  const newLeaf = {
    level: nodeLevel,
    text: node.textContent,
    children: [],
    parent: leaf
  };

  while (leaf && newLeaf.level <= leaf.level)
    leaf = leaf.parent;

  if (!leaf)
    tree.push(newLeaf);
  else
    leaf.children.push(newLeaf);

  leaf = newLeaf;
}

console.log(tree);

此答案不需要h3关注h2;如果您愿意,h3可以关注h1。如果要将其转换为有序列表,也可以这样做:

const str = `<h1>h1-1</h1>
      <h3>h3-1</h3>
      <h3>h3-2</h3>
      <p>something</p>
      <h1>h1-2</h1>
      <h2>h2-2</h2>
      <h3>h3-2</h3>`;

const wrapper = document.createElement('div');
wrapper.innerHTML = str.trim();

let tree = [];
let leaf = null;

for (const node of wrapper.querySelectorAll("h1, h2, h3, h4, h5, h6")) {
  const nodeLevel = parseInt(node.tagName[1]);
  const newLeaf = {
    level: nodeLevel,
    text: node.textContent,
    children: [],
    parent: leaf
  };

  while (leaf && newLeaf.level <= leaf.level)
    leaf = leaf.parent;

  if (!leaf)
    tree.push(newLeaf);
  else
    leaf.children.push(newLeaf);

  leaf = newLeaf;
}


const ol = document.createElement("ol");

(function makeOl(ol, leaves) {
  for (const leaf of leaves) {
    const li = document.createElement("li");
    li.appendChild(new Text(leaf.text));

    if (leaf.children.length > 0) {
      const subOl = document.createElement("ol");
      makeOl(subOl, leaf.children);
      li.appendChild(subOl);
    }

    ol.appendChild(li);
  }
})(ol, tree);

// add it to the DOM
document.body.appendChild(ol);

// or get it as text
const result = ol.outerHTML;

由于HTML是由DOM而不是正则表达式解析的,因此,如果h1标记具有属性,则此解决方案不会遇到任何错误。

答案 1 :(得分:8)

您可以简单地收集所有f2 <- function(str1){ v1 <- strsplit(str1, ",")[[1]] mean(get(v1[1])[[v1[2]]], na.rm = TRUE) } string1 <- "df,col1" f2(string1) #[1] 3 ,然后迭代它们以构建一个树:

使用ES6 (我推断这可以通过h*const的使用来确定

let

但是因为你的html标题本身不在树形结构中(我猜这是你的用例),这只能在某些假设下工作,例如:除非const str = ` <h1>h1-1</h1> <h2>h2-1</h2> <h3>h3-1</h3> <p>something</p> <h1>h1-2</h1> <h2>h2-2</h2> <h3>h3-2</h3> ` const patternh = /<h(\d)>(.*?)<\/h(\d)>/g; let hs = []; let matchh; while (matchh = patternh.exec(str)) hs.push({ lev: matchh[1], text: matchh[2] }) console.log(hs) // constructs a tree with the format [{ value: ..., children: [{ value: ..., children: [...] }, ...] }, ...] const add = (res, lev, what) => { if (lev === 0) { res.push({ value: what, children: [] }); } else { add(res[res.length - 1].children, lev - 1, what); } } // reduces all hs found into a tree using above method starting with an empty list const tree = hs.reduce((res, { lev, text }) => { add(res, lev-1, text); return res; }, []); console.log(tree); 高于<h3>且高于<h2>,否则您无法拥有<h1>。它还假设一个较低级别的标题将始终属于一个更高级别的最新标题。

如果您想进一步使用树结构,例如为TOC呈现代表性有序列表,您可以执行以下操作:

// function to render a bunch of <li>s
const renderLIs = children => children.map(child => `<li>${renderOL(child)}</li>`).join('');

// function to render an <ol> from a tree node
const renderOL = tree => tree.children.length > 0 ? `<ol>${tree.value}${renderLIs(tree.children)}</ol>` : tree.value;

// use a root node for the TOC
const toc = renderOL({ value: 'TOC', children: tree });

console.log(toc);

希望它有所帮助。

答案 2 :(得分:5)

您想要做的事情被称为(a)的变体文档大纲,例如。从文档标题创建嵌套列表,尊重其层次结构。

使用DOM和DOMParser API的浏览器的简单实现如下(放入HTML页面并在ES5中编码以便于测试):

<!DOCTYPE html>
<html>
<head>
<title>Document outline</title>
</head>
<body>
<div id="outline"></div>
<script>

// test string wrapped in a document (and body) element
var str = "<html><body><h1>h1-1</h1><h2>h2-1</h2><h3>h3-1</h3><p>something</p><h1>h1-2</h1><h2>h2-2</h2><h3>h3-2</h3></body></html>";

// util for traversing a DOM and emit SAX startElement events
function emitSAXLikeEvents(node, handler) {
    handler.startElement(node)
    for (var i = 0; i < node.children.length; i++)
        emitSAXLikeEvents(node.children.item(i), handler)
    handler.endElement(node)
}

var outline = document.getElementById('outline')
var rank = 0
var context = outline
emitSAXLikeEvents(
    (new DOMParser()).parseFromString(str, "text/html").body,
    {
        startElement: function(node) {
            if (/h[1-6]/.test(node.localName)) {
                var newRank = +node.localName.substr(1, 1)

                // set context li node to append
                while (newRank <= rank--)
                    context = context.parentNode.parentNode

                rank = newRank

                // create (if 1st li) or
                // get (if 2nd or subsequent li) ol element
                var ol
                if (context.children.length > 0)
                    ol = context.children[0]
                else {
                    ol = document.createElement('ol')
                    context.appendChild(ol)
                }

                // create and append li with text from
                // heading element
                var li = document.createElement('li')
                li.appendChild(
                  document.createTextNode(node.innerText))
                ol.appendChild(li)

                context = li
            }
        },
        endElement: function(node) {}
    })
</script>
</body>
</html>

我首先将您的片段解析为Document,然后遍历它以创建类似SAX的startElement()调用。在startElement()函数中,根据最近创建的列表项(如果有)的等级检查标题元素的等级。然后在正确的层次结构级别附加新的列表项,并且可能创建ol元素作为其容器。注意算法,因为它赢得了&#34;跳跃&#34;从层次结构中的h1h3,但可以很容易地进行调整。

如果你想在node.js上创建一个大纲/内容表,可以使代码在服务器端运行,但需要一个像样的HTML解析库(对于node.js的DOMParser polyfill,可以这么说) 。还有用于创建轮廓的https://github.com/h5o/h5o-jshttps://github.com/hoyois/html5outliner包,但我还没有对其进行测试。据推测,这些软件包还可以处理角落案例,例如iframequote元素中的标题元素,这些元素通常不会出现在文档大纲中。

创建HTML5大纲的主题历史悠久;见例如。 http://html5doctor.com/computer-says-no-to-html5-document-outline/。 HTML4的实践是不使用分区根(在HTML5用语中)包装元素,用于在同一层次结构级别进行切片和放置标题和内容,这被称为&#34;平面标记&#34 ;。 SGML具有RANK功能,可用于处理H1H2等排名元素,并可用于推断省略的section元素,从而自动创建大纲,类似HTML4&#34;扁平地球标记&#34;在简单的情况下(例如,只允许section或其他单个元素作为切片根)。

答案 3 :(得分:2)

我将使用单个正则表达式获取<hx></hx>内容,然后使用方法xArray.reduce对其进行排序。

以下是基础 ,但尚未结束

// The string you need to parse
const str = "\
 <h1>h1-1</h1>\
 <h2>h2-1</h2>\
 <h3>h3-1</h3>\
 <p>something</p>\
 <h1>h1-2</h1>\
 <h2>h2-2</h2>\
 <h3>h3-2</h3>";

// The regex that will cut down the <hx>something</hx>
const regex = /<h[0-9]{1}>(.*?)<\/h[0-9]{1}>/g;

// We get the matches now
const matches = str.match(regex);

// We match the hx togethers as requested
const matchesSorted = Object.values(matches.reduce((tmp, x) => {
  // We get the number behind hx ---> the x
  const hNumber = x[2];

  // If the container do not exist, create it
  if (!tmp[hNumber]) {
    tmp[hNumber] = [];
  }

  // Push the new parsed content into the array
  // 4 is to start after <hx>
  // length - 9 is to get all except <hx></hx>
  tmp[hNumber].push(x.substr(4, x.length - 9));

  return tmp;
}, {}));

console.log(matchesSorted);

在解析html内容时,我想了解一些特殊情况,例如\nspace的存在。例如,请查看以下非工作代码段:

// The string you need to parse
const str = "\
 <h1>h1-1\n\
 </h1>\
 <h2>  h2-1</h2>\
 <h3>h3-1</h3>\
 <p>something</p>\
 <h1>h1-2  </h1>\
 <h2>h2-2 \n\
 </h2>\
 <h3>h3-2</h3>";

// The regex that will cut down the <hx>something</hx>
const regex = /<h[0-9]{1}>(.*?)<\/h[0-9]{1}>/g;

// We get the matches now
const matches = str.match(regex);

// We match the hx togethers as requested
const matchesSorted = Object.values(matches.reduce((tmp, x) => {
  // We get the number behind hx ---> the x
  const hNumber = x[2];

  // If the container do not exist, create it
  if (!tmp[hNumber]) {
    tmp[hNumber] = [];
  }

  // Push the new parsed content into the array
  // 4 is to start after <hx>
  // length - 9 is to get all except <hx></hx>
  tmp[hNumber].push(x.substr(4, x.length - 9));

  return tmp;
}, {}));

console.log(matchesSorted);

我们必须添加.replace().trim()才能删除不需要的\nspaces

使用此代码段

// The string you need to parse
const str = "\
 <h1>h1-1\n\
 </h1>\
 <h2>  h2-1</h2>\
 <h3>h3-1</h3>\
 <p>something</p>\
 <h1>h1-2  </h1>\
 <h2>h2-2 \n\
 </h2>\
 <h3>h3-2</h3>";

// Remove all unwanted \n
const preparedStr = str.replace(/(\r\n\t|\n|\r\t)/gm, "");

// The regex that will cut down the <hx>something</hx>
const regex = /<h[0-9]{1}>(.*?)<\/h[0-9]{1}>/g;

// We get the matches now
const matches = preparedStr.match(regex);

// We match the hx togethers as requested
const matchesSorted = Object.values(matches.reduce((tmp, x) => {
  // We get the number behind hx ---> the x
  const hNumber = x[2];

  // If the container do not exist, create it
  if (!tmp[hNumber]) {
    tmp[hNumber] = [];
  }

  // Push the new parsed content into the array
  // 4 is to start after <hx>
  // length - 9 is to get all except <hx></hx>
  // call trim() to remove unwanted spaces
  tmp[hNumber].push(x.substr(4, x.length - 9).trim());

  return tmp;
}, {}));

console.log(matchesSorted);

答案 4 :(得分:2)

我写这个代码适用于JQuery。 (请不要 DV 。以后可能有人需要jquery答案)

这个递归函数创建了li个字符串,如果一个项目有一些childern,它会将它们转换为ol

const str =
  "<div><h1>h1-1</h1><h2>h2-1</h2><h3>h3-1</h3></div><p>something</p><h1>h1-2</h1><h2>h2-2</h2><h3>h3-2</h3>";

function strToList(stri) {
  const tags = $(stri);

  function partToList(el) {
    let output = "<li>";
    if ($(el).children().length) {
      output += "<ol>";
      $(el)
        .children()
        .each(function() {
          output += partToList($(this));
        });
      output += "</ol>";
    } else {
      output += $(el).text();
    }
    return output + "</li>";
  }

  let output = "<ol>";

  tags.each(function(itm) {
    output += partToList($(this));
  });

  return output + "</ol>";
}

$("#output").append(strToList(str));
li {
  padding: 10px;
}
<script src="https://ajax.googleapis.com/ajax/libs/jquery/2.1.1/jquery.min.js"></script>

<div id="output"></div>

(此代码可以轻松转换为纯JS)