我将深入探讨我的问题，如果您不想阅读所有内容，可以跳至 TL;DR

我想做什么

我需要存储一个可以由用户编辑的"file"(文本文档)。如果我有原始文件(可能很大)

Lorem ipsum dolor sit amet

并且用户要进行更改:

Foo ipsum amet_ sit

基本上，我有原始字符串和用户编辑的字符串。我想找到差异，“编辑”。防止存储非常大 字符串的副本。我想存储原件和“编辑”。然后将编辑应用到原件。有点像重复数据删除。问题是我不知道编辑会有多不同，我还需要能够将这些编辑应用于字符串。

尝试

因为文本可能很大，我想知道在不存储两个单独版本的情况下存储对文本的编辑的最“有效”方式是什么。我的第一个猜测是:

var str = 'Original String of text...'.split(' ') || [],
    mod = 'Modified String of text...'.split(' ') || [], i, edits = [];

for (i = 0; i < str.length; i += 1) {
    edits.push(str[i]===mod[i] ? undefined : mod[i]);
}

console.log(edits); // ["Modified", null, null, null] (desired output)

然后返回:

for (i = 0; i < str.length; i += 1) {
    str[i] = edits[i] || str[i];
}
str.join(' '); // "Modified String of text..."

Basically, I'm trying to split the text by spaces into arrays. Compare the arrays and store the differences. Then apply the differences to generate the modified version

问题

但是如果改变空格的数量，就会出现问题:

str:文本的原始字符串... mod:OriginalString of text...

输出:OriginalString of text... text...

我想要的输出:OriginalString of text...

即使我将 str.length 与 mod.length 和 edits.length 切换为:

// Get edits
var str = 'Original String of text...'.split(' ') || [],
    mod = 'Modified String of text...'.split(' ') || [], i, edits = [];

for (i = 0; i < mod.length; i += 1) {
    edits.push(str[i]===mod[i] ? undefined : mod[i]);
}

// Apply edits
var final = [];
for (i = 0; i < edits.length; i += 1) {
    final[i] = edits[i] || str[i];
}
final = final.join(' ');

edits 将是:["ModifiedString", "of", "text..."] 结果使整个“存储编辑”变得毫无用处。更糟糕的是，如果要添加/删除一个词。如果 str 成为 Original String of lots of text...。输出仍然是相同的。

我知道我这样做的方式有很多缺陷，但我想不出任何其他方式。

片段:

document.getElementById('go').onclick = function() {
  var str = document.getElementById('a').value.split(' ') || [],
    mod = document.getElementById('b').value.split(' ') || [],
    i, edits = [];

  for (i = 0; i < mod.length; i += 1) {
    edits.push(str[i] === mod[i] ? undefined : mod[i]);
  }

  // Apply edits
  var final = [];
  for (i = 0; i < edits.length; i += 1) {
    final[i] = edits[i] || str[i];
  }
  final = final.join(' ');
  alert(final);
};

document.getElementById('go2').onclick = function() {
  var str = document.getElementById('a').value.split(' ') || [],
    mod = document.getElementById('b').value.split(' ') || [],
    i, edits = [];

  for (i = 0; i < str.length; i += 1) {
    edits.push(str[i] === mod[i] ? undefined : mod[i]);
  }

  for (i = 0; i < str.length; i += 1) {
    str[i] = edits[i] || str[i];
  }
  alert(str.join(' ')); // "Modified String of text..."
};

Base String:
<input id="a">
<br/>Modified String:
<input id="b" />
<br/>
<button id="go">Second method</button>
<button id="go2">First Method</button>

长话短说:

如何找到两个字符串之间的变化？

我正在处理大量文本，每个文本可能大约 兆字节 百千字节。这是在浏览器上运行

最佳答案

编辑:添加了可以处理多个文本区域的修改脚本。

Here is the JSFiddle对于具有多个可编辑文本区域的页面。 (不要忘记打开开发工具来查看编辑。)您只需要为每个文本区域分配一个唯一的 ID。然后，使用这些 id 作为键并使用每个 textarea 的 edits 数组作为值创建一个映射。这是更新后的脚本:

'use strict';

function Edit(type, position, text) {
  this.type = type;
  this.position = position;
  this.text = text;
}

var ADD = 'add';
var DELETE = 'delete';

var textAreaEditsMap = {};

var cursorStart = -1;
var cursorEnd = -1;
var currentEdit = null;
var deleteOffset = 1;

window.addEventListener('load', function() {
  var textareas = document.getElementsByClassName('text-editable');

  for (var i = 0; i < textareas.length; ++i) {
    var textarea = textareas.item(i);
    var id = textarea.getAttribute('id');

    textAreaEditsMap[id] = [];
    textarea.addEventListener('mouseup', handleMouseUp);
    textarea.addEventListener('keydown', handleKeyDown);
    textarea.addEventListener('keypress', handleKeyPress);
  }
});

function handleMouseUp(event) {
  cursorStart = this.selectionStart;
  cursorEnd = this.selectionEnd;
  currentEdit = null;
}

function handleKeyDown(event) {

  cursorStart = this.selectionStart;
  cursorEnd = this.selectionEnd;

  if (event.keyCode >= 35 && event.keyCode <= 40) { // detect cursor movement keys
    currentEdit = null;
  }

  // deleting text
  if (event.keyCode === 8 || event.keyCode === 46) {
    if (currentEdit != null && currentEdit.type !== 'delete') {
      currentEdit = null;
    }

    if (cursorStart !== cursorEnd) { // Deleting highlighted text
      var edit = new Edit(DELETE, cursorStart, this.innerHTML.substring(cursorStart, cursorEnd));
      textAreaEditsMap[this.getAttribute('id')].push(edit);
      currentEdit = null;

    } else if (event.keyCode === 8) { // backspace
      if (currentEdit == null) {
        deleteOffset = 1;
        var edit = new Edit(DELETE, cursorStart, this.innerHTML[cursorStart - 1]);
        textAreaEditsMap[this.getAttribute('id')].push(edit);
        currentEdit = edit;
      } else {
        ++deleteOffset;
        currentEdit.text = this.innerHTML[cursorStart - 1] + currentEdit.text;
      }

    } else if (event.keyCode === 46) { // delete
      if (currentEdit == null) {
        deleteOffset = 1;
        var edit = new Edit(DELETE, cursorStart, this.innerHTML[cursorStart]);
        textAreaEditsMap[this.getAttribute('id')].push(edit);
        currentEdit = edit;

      } else {
        currentEdit.text += this.innerHTML[cursorStart + deleteOffset++];
      }
    }
  }

  console.log(textAreaEditsMap)
}

function handleKeyPress(event) {

  if (currentEdit != null && currentEdit.type !== 'add') {
    currentEdit = null;
  }

  if (currentEdit == null) {
    currentEdit = new Edit(ADD, cursorStart, String.fromCharCode(event.charCode));
    textAreaEditsMap[this.getAttribute('id')].push(currentEdit);
  } else {
    currentEdit.text += String.fromCharCode(event.charCode);
  }

  console.log(textAreaEditsMap);
}

带有仅处理一个文本区域的原始脚本的原始帖子如下:

我制作了一个示例脚本来满足您的需求。我放了一个 working example在 JSFiddle 上。确保在 JSFiddle 示例页面上按 ctrl+shift+J 以打开开发工具，以便您可以看到在进行编辑时记录的编辑数组。编辑按时间顺序添加到 edits 数组，因此您可以通过按相反的时间顺序(即向后迭代数组)应用逆向(即，将已删除的文本添加回来；删除添加的文本)恢复到原始文本。我没有从上下文菜单或通过键绑定(bind)处理复制、粘贴、撤消或重做，但我认为您应该能够使用此示例作为指南来处理这些事情。这是脚本:

'use strict';

function Edit(type, position, text) {
  this.type = type;
  this.position = position;
  this.text = text;
}

window.addEventListener('load', function() {
  var ADD = 'add';
  var DELETE = 'delete';

  var cursorStart = -1;
  var cursorEnd = -1;
  var edits = [];
  var currentEdit = null;
  var deleteOffset = 1;

  var textarea = document.getElementById('saved-text');

  textarea.addEventListener('mouseup', function(event) {
    cursorStart = this.selectionStart;
    cursorEnd = this.selectionEnd;
    currentEdit = null;
  });

  textarea.addEventListener('keydown', function(event) {

    cursorStart = this.selectionStart;
    cursorEnd = this.selectionEnd;

    if(event.keyCode >= 35 && event.keyCode <= 40) { // detect cursor movement keys
      currentEdit = null;
    }

    // deleting text
    if(event.keyCode === 8 || event.keyCode === 46) {
      if(currentEdit != null && currentEdit.type !== 'delete') {
        currentEdit = null;
      }

      if(cursorStart !== cursorEnd) {
        var edit = new Edit(DELETE, cursorStart, textarea.innerHTML.substring(cursorStart, cursorEnd));
        edits.push(edit);
        currentEdit = null;

      } else if (event.keyCode === 8) { // backspace
        if (currentEdit == null) {
          deleteOffset = 1;
          var edit = new Edit(DELETE, cursorStart, textarea.innerHTML[cursorStart - 1]);
          edits.push(edit);
          currentEdit = edit;
        } else {
          ++deleteOffset;
          currentEdit.text = textarea.innerHTML[cursorStart - 1] + currentEdit.text;
        }

      } else if (event.keyCode === 46) { // delete
        if(currentEdit == null) {
          deleteOffset = 1;
          var edit = new Edit(DELETE, cursorStart, textarea.innerHTML[cursorStart]);
          edits.push(edit);
          currentEdit = edit;

        } else {
          currentEdit.text += textarea.innerHTML[cursorStart + deleteOffset++];
        }
      }
    }

    console.log(edits)
  });

  textarea.addEventListener('keypress', function(event) {

    if(currentEdit != null && currentEdit.type !== 'add') {
      currentEdit = null;
    }

    // adding text
    if(currentEdit == null) {
      currentEdit = new Edit(ADD, cursorStart, String.fromCharCode(event.charCode));
      edits.push(currentEdit);
    } else {
      currentEdit.text += String.fromCharCode(event.charCode);
    }

    console.log(edits);
  });

});

关于javascript - 从两个字符串中抓取编辑，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/30688983/