从电子表格中的单元格值解析字符串和对象

Question

我得到了包含令人讨厌的值的电子表格，并且为此而苦苦挣扎。所需数据在 A 列的每个单元格中。单元格的值为{"p0":70,"u3":71,"s7110":40},t45,{"t78":60,"s3310":15},p37,p36,{"p29":44,"s8110":95},p85,p14,{"s2710":41},u47。此类值的数量约为 1000。我必须解析这些值。我需要来自这些值的字符串和对象。我可以忽略解析值的顺序。我无法手动解析。所以我决定使用脚本。

我尝试使用“split”进行解析。

var sheet = SpreadsheetApp.getActiveSheet();
var values = sheet.getRange("A1:A" + sheet.getLastRow()).getValues();
var result = [];
for (var i = 0; i < values.length; i++)
{
  result.push(values[i][0].split(","));
}

我得到t45,p37,p36,p85,p14,u47 作为字符串。但是“拆分”也会拆分所有对象。例如，{"p0":70,"u3":71,"s7110":40} 拆分为 {"p0":70、"u3":71、"s7110":40}。有办法解决吗？

示例值是这个。每一行都在单元格 A1、A2、A3、A4、A5 中。

{"p0":70,"u3":71,"s7110":40},t45,{"t78":60,"s3310":15},p37,p36,{"p29":44,"s8110":95},p85,p14,{"s2710":41},u47
s6610,{"t25":70,"u8":43,"p35":86},u85,u74,{"s7710":83},{"p70":70,"u67":84},{"u71":43,"s1210":73},{"u45":84,"s710":15},{"u14":79,"p22":45},p31
u73,u12,{"t51":98,"u57":96},u31,p41,s1110,s6610,p55,{"t57":71,"s7510":83,"u62":17},u73
t50,{"t83":22,"p18":76},{"p47":12,"s8710":18,"u11":35},{"t14":74,"u72":51},{"p74":21,"t77":77},{"u62":84,"s3010":11},p81,u36,p67,{"t79":12,"u2":70,"s6010":98}
{"u54":51,"t31":31},t56,s4110,{"s3110":84,"t25":92,"p80":19},s3210,{"p65":54,"s8510":45},{"t73":78,"s6210":11},{"s2110":98,"p11":16},{"p61":55,"t88":75},p38

非常感谢您抽出宝贵时间。对于我不成熟的问题，我很抱歉。

Answer 1

B1：

=ARRAYFORMULA(REGEXEXTRACT(A1:A5&",",REGEXREPLACE(REGEXREPLACE(A1:A5&",","{.*?}","($0)"),"([A-Za-z]\d+),","($1),")))

我们用() 将除逗号, 之外的所有对象和字符串括起来，然后再将它们提取出来。

编辑：更简单的锚点：, 逗号后面不跟"

=ARRAYFORMULA(SUBSTITUTE(SPLIT(SUBSTITUTE(A1:A5,","&CHAR(34),"?"),","),"?",","&CHAR(34)))


=ARRAYFORMULA(split(REGEXREPLACE(A1:A5,"(,)([^"&CHAR(34)&"])","?$2"),"?"))

Answer 2

您可以使用 RegExp 将字符替换为可以在不影响其他任何内容的情况下找到的独特字符。

function myFunction() {
  var L,newArray,thisElement;

  var myStrng = '{"p0":70,"u3":71,"s7110":40},t45,{"t78":60,"s3310":15},p37,p36,{"p29":44,"s8110":95},p85,p14,{"s2710":41},u47 \
s6610,{"t25":70,"u8":43,"p35":86},u85,u74,{"s7710":83},{"p70":70,"u67":84},{"u71":43,"s1210":73},{"u45":84,"s710":15},{"u14":79,"p22":45},p31 \
u73,u12,{"t51":98,"u57":96},u31,p41,s1110,s6610,p55,{"t57":71,"s7510":83,"u62":17},u73 \
t50,{"t83":22,"p18":76},{"p47":12,"s8710":18,"u11":35},{"t14":74,"u72":51},{"p74":21,"t77":77},{"u62":84,"s3010":11},p81,u36,p67,{"t79":12,"u2":70,"s6010":98} \
{"u54":51,"t31":31},t56,s4110,{"s3110":84,"t25":92,"p80":19},s3210,{"p65":54,"s8510":45},{"t73":78,"s6210":11},{"s2110":98,"p11":16},{"p61":55,"t88":75},p38';

  var re = new RegExp("\},","g");
  var parsedObj = myStrng.replace(re,"}zq^");//Replace all }, characters with }zq^

  //Logger.log(parsedObj)

  parsedObj = parsedObj.replace(/,\{/g,"zq^{");//Replace all ,{ characters with zq^{

  //Logger.log(parsedObj)
  parsedObj = parsedObj.replace(/\}\{/g,"}zq^{");//Replace all back to back brackets
  parsedObj = parsedObj.replace(/\} \{/g,"}zq^{");//Replace all back to back brackets with a space between

  parsedObj = parsedObj.split("zq^");//split on zq^

  L = parsedObj.length;

  newArray = [];

  for (var i=0;i<L;i++) {
    thisElement = parsedObj[i];
    //Logger.log('thisElement: ' + thisElement)

    if (thisElement.indexOf("{") !== -1) {
      newArray.push(thisElement);
      continue;
    }

    if (thisElement.indexOf(",") !== -1) {
      thisElement = thisElement.split(",");

      for (var j =0;j<thisElement.length;j++) {
        newArray.push(thisElement[j]);
      }
      continue;
    }

    if (thisElement.indexOf(" ") !== -1) {
      thisElement = thisElement.split(" ");

      for (var j =0;j<thisElement.length;j++) {
        newArray.push(thisElement[j]);
      }
      continue;
    }

    newArray.push(thisElement);
  }

  L = newArray.length;

  for (var i=0;i<L;i++) {
    Logger.log(newArray[i])

  }
}