使用 Selection 的 RangeElements 获取 Google 文档中的所有嵌套文本元素

在类似于上面的文档中，我可以使用以下代码获取所有段落：

var paras = body.getParagraphs();

请注意，上面的代码不仅返回顶级段落，还返回内部的所有子级别段落ListItems, Tables etc.

如何在选定的范围内做同样的事情？以下代码仅返回顶级元素。

const selection = DocumentApp.getActiveDocument().getSelection();
var rangeElements = selection.getRangeElements();

例如，上表包含9个非空段落，如果它们在选择中，我想将它们一一处理。

我想要实现的目标类似于通过尽可能保留格式、表格、列表项等来翻译选择中的文本。

.getRangeElements()返回一个数组范围元素。范围元素是一个包装对象，用于帮助我们处理部分选择。我们可以打电话.getElement()在此数组中的每个项目上获取元素对象这是一个very通用对象，可以代表 Google 文档的几乎任何部分。Elements have a .getType()方法返回一个元素类型枚举；并且有a lot他们！

让我们用目前所知的知识来看看 Google 文档中可能的类型（我已经创建了一个与您相似的（img）举个例子）：

function selectionHasWhichTypes() {
  var doc = DocumentApp.getActiveDocument();
  var selection = doc.getSelection();
  var rangeElems = selection.getRangeElements();

  rangeElems.forEach(function(elem){
    var elem = elem.getElement();

    Logger.log(elem.getType());
  });
}

//Logger OUTPUT:
PARAGRAPH
PARAGRAPH
PARAGRAPH
PARAGRAPH
PARAGRAPH
LIST_ITEM
LIST_ITEM
LIST_ITEM
PARAGRAPH
PARAGRAPH
PARAGRAPH
TABLE
PARAGRAPH

Ah Ha!看起来我们只需要处理段落, 项目清单, and TABLE元素类型for now，但让我们保留他们的children也记住（我们会发现这些是 5 个中的 3 个可以生孩子）。这听起来像是一份工作递归函数它将不断深入挖掘子元素，直到我们找到并处理所有子元素。

那么让我们尝试一下吧。下一部分可能看起来令人困惑，但本质上它是查找一个元素，检查它是否有子元素，然后查看它们是否有they有孩子等等。我们also想检查一下我们是否得到了new还要处理的 ElementTypes...

function selectionHasWhichTypes() {
  var doc = DocumentApp.getActiveDocument();
  var selection = doc.getSelection();
  var rangeElems = selection.getRangeElements();

  rangeElems.forEach(function(elem){
    var elem = elem.getElement();

    elemsHaveWhatChildElems(elem, elem.getType());

  });
}

function elemsHaveWhatChildElems(elem, typeChain){
  var elemType = elem.getType();
  if(elemType == "TABLE" || elemType == "LIST_ITEM" || elemType == "PARAGRAPH"){ //Lets see if element is one of our basic 3. If so they could have children.
    var numChildren = elem.getNumChildren(); //How many children are there?
    if(numChildren > 0){
      for(var i = 0; i < numChildren; i++){ //Let's go through them.
        var child = elem.getChild(i);
        elemsHaveWhatChildElems(child, typeChain + "." + child.getType()); //Recursion step to look for more children.
      }
    }else{
       Logger.log(typeChain); //Let's log the chain of Parent to Child elements.
    }
  }else{
    Logger.log("*" + typeChain); //Let's mark the new elemTypeChains we have not seen.
  }
}

//Logger OUTPUT:
*PARAGRAPH.TEXT
PARAGRAPH
*PARAGRAPH.HORIZONTAL_RULE
PARAGRAPH
*PARAGRAPH.TEXT
*LIST_ITEM.TEXT
*LIST_ITEM.TEXT
*LIST_ITEM.TEXT
PARAGRAPH
*PARAGRAPH.TEXT
PARAGRAPH
*TABLE.TABLE_ROW
*TABLE.TABLE_ROW
PARAGRAPH

好吧，日志的每一行都是一系列元素及其子元素。我们有一些新元素类型 (水平规则, 表行, and TEXT）。如果一条链只是一个Paragraph并且没有孩子，如“段落”所示。我们可以忽略它因为它是一个空行。我们也可以忽略HORIZONTAL_RULE作为这个明显地不会包含文本。

如果我们已经到达一个 TEXT 元素这意味着我们可以执行我们的功能（即对于 OP 来说，这将是一个翻译），就像我们对 LIST_ITEM 和 PARAGRAPH 所做的那样。然而，我们still必须处理TableRow对象（记录如下：TABLE.TABLE_ROW）。这是类似于我们的主要 3 个要素并可以与我们的if(elemType == "TABLE" || elemType == "LIST_ITEM" || elemType == "PARAGRAPH")这会改变为if(elemType == "TABLE" || elemType == "LIST_ITEM" || elemType == "PARAGRAPH" || elemType == "TABLE_ROW").

这为我们的链中提供了另一个新元素；表格单元格（日志如下：TABLE.TABLE_ROW.TABLE_CELL），我们可以again添加到我们的 if 语句中，使其：if(elemType == "TABLE" || elemType == "LIST_ITEM" || elemType == "PARAGRAPH" || elemType == "TABLE_ROW" || elemType == "TABLE_CELL")

是时候看看会发生什么了当我们处理完表元素类型时。

function selectionHasWhichtypeChains() {
  var doc = DocumentApp.getActiveDocument();
  var selection = doc.getSelection();
  var rangeElems = selection.getRangeElements();

  rangeElems.forEach(function(elem){
    var elem = elem.getElement();

    elemsHaveWhatChildElems(elem, elem.getType());

  });
}

function elemsHaveWhatChildElems(elem, typeChain){
  var elemType = elem.getType();
  if(elemType == "TABLE" || elemType == "LIST_ITEM" || elemType == "PARAGRAPH" || elemType == "TABLE_ROW" || elemType == "TABLE_CELL"){ //Lets see if element is one of our basic 5 if so they could have children.
    var numChildren = elem.getNumChildren(); //How many children are there?
    if(numChildren > 0){
      for(var i = 0; i < numChildren; i++){ //Let's go through them.
        var child = elem.getChild(i);
        elemsHaveWhatChildElems(child, typeChain + "." + child.getType()); //Recursion step to look for more children.
      }
    }else{
       Logger.log(typeChain); //Let's log the chain of Parent to Child elements.
    }
  }else{
    Logger.log("*" + typeChain); //Let's mark the new elemTypeChains we have not seen.
  }
}

//Logger OUTPUT:
*PARAGRAPH.TEXT
PARAGRAPH
*PARAGRAPH.HORIZONTAL_RULE
PARAGRAPH
*PARAGRAPH.TEXT
*LIST_ITEM.TEXT
*LIST_ITEM.TEXT
*LIST_ITEM.TEXT
PARAGRAPH
*PARAGRAPH.TEXT
PARAGRAPH
*TABLE.TABLE_ROW.TABLE_CELL.PARAGRAPH.TEXT
*TABLE.TABLE_ROW.TABLE_CELL.TABLE.TABLE_ROW.TABLE_CELL.PARAGRAPH.TEXT
*TABLE.TABLE_ROW.TABLE_CELL.TABLE.TABLE_ROW.TABLE_CELL.PARAGRAPH.TEXT
*TABLE.TABLE_ROW.TABLE_CELL.TABLE.TABLE_ROW.TABLE_CELL.PARAGRAPH.TEXT
*TABLE.TABLE_ROW.TABLE_CELL.TABLE.TABLE_ROW.TABLE_CELL.PARAGRAPH.TEXT
TABLE.TABLE_ROW.TABLE_CELL.PARAGRAPH
*TABLE.TABLE_ROW.TABLE_CELL.PARAGRAPH.TEXT
*TABLE.TABLE_ROW.TABLE_CELL.PARAGRAPH.HORIZONTAL_RULE
*TABLE.TABLE_ROW.TABLE_CELL.PARAGRAPH.TEXT
*TABLE.TABLE_ROW.TABLE_CELL.PARAGRAPH.TEXT
PARAGRAPH

这很棒！我们已经深入到每个父元素并达到了a 文本元素 or a 空白段落！从这里我们可以稍微修改我们的代码以添加我们想要执行的功能，同时保持文档的结构：

function myFunction() {
  var doc = DocumentApp.getActiveDocument();
  var selection = doc.getSelection();
  var rangeElems = selection.getRangeElements(); //Get main Elements of selection

  rangeElems.forEach(function(elem){ //Let's rn through each to find ALL of their children.
    var elem = elem.getElement(); //We have an ElementType. Let's get the full element.
    getNestedTextElements(elem, elem.getType()); //Time to go down the rabbit hole.
  });
}

function getNestedTextElements(elem, typeChain){
  var elemType = elem.getType();
  if(elemType == "TABLE" || elemType == "LIST_ITEM" || elemType == "PARAGRAPH" || elemType == "TABLE_ROW" || elemType == "TABLE_CELL"){ //Lets see if element is one of our basic 5, if so they could have children.
    var numChildren = elem.getNumChildren(); //How many children are there?
    if(numChildren > 0){
      for(var i = 0; i < numChildren; i++){ //Let's go through them.
        var child = elem.getChild(i);
        getNestedTextElements(child, typeChain + "." + child.getType()); //Recursion step to look for more children.
      }
    }
  }else if(elemType == "TEXT"){
    //THIS IS WHERE WE CAN PERFORM OUR OPERATIONS ON THE TEXT ELEMENT
    var text = elem.getText();


  }else{
    Logger.log("*" + typeChain); //Let's log the new elem we dont deal with now - for future proofing.
  }
}

繁荣！完毕。我知道这是一篇非常长的文章，但我已将解决方案的每个部分分解为多个部分，以帮助新的 Apps 脚本编码人员了解选择的结构（我猜还有文档正文）以及如何在结构发生变化时修改它非常复杂（许多嵌套元素）。我真的希望这有帮助。如果有人看到可以改进的部分，请告诉我。

作为OP的注释：请注意，这不一定处理元素的部分选择，但是可以通过稍微修改第一个函数来检查来轻松处理isPartial() on the 范围元素.