Fatal编程技术网
  • javascript/
  • Javascript 如何构造正则表达式来拆分此文本？

Javascript 如何构造正则表达式来拆分此文本？

javascript html regex

Javascript 如何构造正则表达式来拆分此文本？,javascript,html,regex,Javascript,Html,Regex,大家好，我正在写一个脚本，主要思想是我有一个固定结构的文本，如下所示： "RBD|X|RBD|C|92173~GJHGWO.NAYE" "SAMBORNSiPOSSSTHRa" "RBD|X|RBD|C|92173~GJHGX4.NAYE" "SAMBORNSiPOSSSTHRa" "RBD|X|RBD|C|92173~GJHGX6.NAYE" "SAMBORNSiPOSSSTHRa" "RBD|X|RBD|C|92173~GJHGX8.NAYE" "SAMBORNSiPOSSSTHRa" "R

大家好，我正在写一个脚本，主要思想是我有一个固定结构的文本，如下所示：

"RBD|X|RBD|C|92173~GJHGWO.NAYE" "SAMBORNSiPOSSSTHRa"
"RBD|X|RBD|C|92173~GJHGX4.NAYE" "SAMBORNSiPOSSSTHRa"
"RBD|X|RBD|C|92173~GJHGX6.NAYE" "SAMBORNSiPOSSSTHRa"
"RBD|X|RBD|C|92173~GJHGX8.NAYE" "SAMBORNSiPOSSSTHRa"
"RBD|X|RBD|C|92173~GJHGXA.NAYE" "SAMBORNSiPOSSSTHRa"
"RBD|X|RBD|C|92173~GJHGXC.NAYE" "SAMBORNSiPOSSSTHRa"

splitWords = [RBD,X,RBD,C,92173,GJHGWO.NAYE,SAMBORNSiPOSSSTHRa]

<!DOCTYPE html>
<html>

<body>
<p id="demo"></p>

<textarea cols=150 rows=15 id="texto">
"RBD|X|RBD|C|92173~GJHGWO.NAYE" "SAMBORNSiPOSSSTHRa"
"RBD|X|RBD|C|92173~GJHGX4.NAYE" "SAMBORNSiPOSSSTHRa"
"RBD|X|RBD|C|92173~GJHGX6.NAYE" "SAMBORNSiPOSSSTHRa"
"RBD|X|RBD|C|92173~GJHGX8.NAYE" "SAMBORNSiPOSSSTHRa"
"RBD|X|RBD|C|92173~GJHGXA.NAYE" "SAMBORNSiPOSSSTHRa"
"RBD|X|RBD|C|92173~GJHGXC.NAYE" "SAMBORNSiPOSSSTHRa"
</textarea>

<script>
var splitWords = document.getElementById("texto").value.split("|");
document.write(splitWords.toString());
</script>

</body>
</html>
我想处理该文本，我想用以下符号分割该文本： |“~，管道双引号和~，我想创建一个数组来存储这些值，如下所示：

"RBD|X|RBD|C|92173~GJHGWO.NAYE" "SAMBORNSiPOSSSTHRa"
"RBD|X|RBD|C|92173~GJHGX4.NAYE" "SAMBORNSiPOSSSTHRa"
"RBD|X|RBD|C|92173~GJHGX6.NAYE" "SAMBORNSiPOSSSTHRa"
"RBD|X|RBD|C|92173~GJHGX8.NAYE" "SAMBORNSiPOSSSTHRa"
"RBD|X|RBD|C|92173~GJHGXA.NAYE" "SAMBORNSiPOSSSTHRa"
"RBD|X|RBD|C|92173~GJHGXC.NAYE" "SAMBORNSiPOSSSTHRa"

splitWords = [RBD,X,RBD,C,92173,GJHGWO.NAYE,SAMBORNSiPOSSSTHRa]

<!DOCTYPE html>
<html>

<body>
<p id="demo"></p>

<textarea cols=150 rows=15 id="texto">
"RBD|X|RBD|C|92173~GJHGWO.NAYE" "SAMBORNSiPOSSSTHRa"
"RBD|X|RBD|C|92173~GJHGX4.NAYE" "SAMBORNSiPOSSSTHRa"
"RBD|X|RBD|C|92173~GJHGX6.NAYE" "SAMBORNSiPOSSSTHRa"
"RBD|X|RBD|C|92173~GJHGX8.NAYE" "SAMBORNSiPOSSSTHRa"
"RBD|X|RBD|C|92173~GJHGXA.NAYE" "SAMBORNSiPOSSSTHRa"
"RBD|X|RBD|C|92173~GJHGXC.NAYE" "SAMBORNSiPOSSSTHRa"
</textarea>

<script>
var splitWords = document.getElementById("texto").value.split("|");
document.write(splitWords.toString());
</script>

</body>
</html>
为了实现这一目标，我尝试：

var splitWords = document.getElementById("texto").value.split("|");
document.write(stringArray.toString());
我得到：

"RBD,X,RBD,C,92173~GJHGWO.NAYE" "SAMBORNSiPOSSSTHRa" "RBD,X,RBD,C,92173~GJHGX4.NAYE" "SAMBORNSiPOSSSTHRa" "RBD,X,RBD,C,92173~GJHGX6.NAYE" "SAMBORNSiPOSSSTHRa" "RBD,X,RBD,C,92173~GJHGX8.NAYE" "SAMBORNSiPOSSSTHRa" "RBD,X,RBD,C,92173~GJHGXA.NAYE" "SAMBORNSiPOSSSTHRa" "RBD,X,RBD,C,92173~GJHGXC.NAYE" "SAMBORNSiPOSSSTHRa"
问题是，这只是用管道分割文本，我也想用其他符号分割文本，以获得我想要的输出。 完整的代码如下所示：

"RBD|X|RBD|C|92173~GJHGWO.NAYE" "SAMBORNSiPOSSSTHRa"
"RBD|X|RBD|C|92173~GJHGX4.NAYE" "SAMBORNSiPOSSSTHRa"
"RBD|X|RBD|C|92173~GJHGX6.NAYE" "SAMBORNSiPOSSSTHRa"
"RBD|X|RBD|C|92173~GJHGX8.NAYE" "SAMBORNSiPOSSSTHRa"
"RBD|X|RBD|C|92173~GJHGXA.NAYE" "SAMBORNSiPOSSSTHRa"
"RBD|X|RBD|C|92173~GJHGXC.NAYE" "SAMBORNSiPOSSSTHRa"

splitWords = [RBD,X,RBD,C,92173,GJHGWO.NAYE,SAMBORNSiPOSSSTHRa]

<!DOCTYPE html>
<html>

<body>
<p id="demo"></p>

<textarea cols=150 rows=15 id="texto">
"RBD|X|RBD|C|92173~GJHGWO.NAYE" "SAMBORNSiPOSSSTHRa"
"RBD|X|RBD|C|92173~GJHGX4.NAYE" "SAMBORNSiPOSSSTHRa"
"RBD|X|RBD|C|92173~GJHGX6.NAYE" "SAMBORNSiPOSSSTHRa"
"RBD|X|RBD|C|92173~GJHGX8.NAYE" "SAMBORNSiPOSSSTHRa"
"RBD|X|RBD|C|92173~GJHGXA.NAYE" "SAMBORNSiPOSSSTHRa"
"RBD|X|RBD|C|92173~GJHGXC.NAYE" "SAMBORNSiPOSSSTHRa"
</textarea>

<script>
var splitWords = document.getElementById("texto").value.split("|");
document.write(splitWords.toString());
</script>

</body>
</html>




“RBD | X | RBD | C | 92173~GJHGWO.NAYE”“samborniposssthra”
“RBD | X | RBD | C | 92173~GJHGX4.NAYE”“Samborniposssthra”
“RBD | X | RBD | C | 92173~GJHGX6.NAYE”“samborniposssthra”
“RBD | X | RBD | C | 92173~GJHGX8.NAYE”“samborniposssthra”
“RBD | X | RBD | C | 92173~GJHGXA.NAYE”“Sambornipossthra”
“RBD | X | RBD | C | 92173~GJHGXC.NAYE”“Samborniposssthra”
var splitWords=document.getElementById（“texto”）.value.split（“|”）；
document.write（splitWords.toString（））；
我非常感谢任何关于正则表达式的建议来实现这一点。

使用正则表达式：

str = '"RBD|X|RBD|C|92173~GJHGWO.NAYE" "SAMBORNSiPOSSSTHRa"';
str.split(/[\|"~\s]+/).filter(Boolean); // Output: ["RBD", "X", "RBD", "C", "92173", "GJHGWO.NAYE", "SAMBORNSiPOSSSTHRa"]
如果还想过滤句点，请将其添加到正则表达式的方括号中，并用反斜杠将其转义。

好的，让我们开始…获取
textarea
值并修剪它

var splitWords = document.getElementById("texto").value.trim();
首先，您需要替换
“
符号

splitWords = splitWords.replace(/"/g, '');
然后分割行，因为它就像表中的行

splitWords = splitWords.split('\n');
然后将每一行拆分为两行，
|
，
~
，

splitWords.forEach(function(rowValue,rowIndex) {
    splitWords[rowIndex] = rowValue.split(/[|~ ]/);
    console.log(rowIndex, splitWords[rowIndex]);
});
Console.log输出将为：

0 ["RBD", "X", "RBD", "C", "92173", "GJHGWO.NAYE", "SAMBORNSiPOSSSTHRa"]
1 ["RBD", "X", "RBD", "C", "92173", "GJHGX4.NAYE", "SAMBORNSiPOSSSTHRa"]
2 ["RBD", "X", "RBD", "C", "92173", "GJHGX6.NAYE", "SAMBORNSiPOSSSTHRa"]
3 ["RBD", "X", "RBD", "C", "92173", "GJHGX8.NAYE", "SAMBORNSiPOSSSTHRa"]
4 ["RBD", "X", "RBD", "C", "92173", "GJHGXA.NAYE", "SAMBORNSiPOSSSTHRa"]
5 ["RBD", "X", "RBD", "C", "92173", "GJHGXC.NAYE", "SAMBORNSiPOSSSTHRa"]
然后用二维数组做任何你想做的事我的建议是：

splitWords.forEach(function(rowValue,rowIndex) {
    splitWords[rowIndex] = rowValue.split(/[|~ ]/);
    console.log(rowIndex, splitWords[rowIndex]);
});


“RBD | X | RBD | C | 92173~GJHGWO.NAYE”“samborniposssthra”
“RBD | X | RBD | C | 92173~GJHGX4.NAYE”“Samborniposssthra”
“RBD | X | RBD | C | 92173~GJHGX6.NAYE”“samborniposssthra”
“RBD | X | RBD | C | 92173~GJHGX8.NAYE”“samborniposssthra”
“RBD | X | RBD | C | 92173~GJHGXA.NAYE”“Sambornipossthra”
“RBD | X | RBD | C | 92173~GJHGXC.NAYE”“Samborniposssthra”
var lines=document.getElementById（“texto”）.value.split（'\n'）；
var splitWords=lines.filter（函数（v）{返回v.length>0}）
.map（函数（当前值、索引）{
返回currentValue.trim（）.replace（/^“（[^“]+）”\s“（[^“]+）”$/，“$1$2”）.split（/[| ~]/）；
});
log（JSON.stringify（splitWords，null，4））；
text.split（/[\\\\\\~]/）split接受正则表达式。
/\\\\\\\\\\\\\\\\\\\\\./g
您要求一个正则表达式按特定字符分割文本，但这并不能解决您的问题：您希望得到一个多维数组，其中每行包含条目，其中每行用您的数据分隔为两个“单词”通过空格。@user138717您确定您的单个值不能包含任何用于拆分的字符，例如，不能使用“Sambornipossthra”而不是“SA BORNSiPOSSTHRa”吗等等？如果不是，最好使用更精细的正则表达式匹配策略。好的，谢谢，我会验证它。布尔构造函数的巧妙使用。我非常感谢支持，这非常有用。谢谢，这非常有用，我感谢支持。