如何使用谷歌脚本检查两个谷歌工作表，并将重复项移动到新工作表？

Question

I'm trying to do something which seems simple. I have a gigantic sheet of 20k contacts, and there are contacts with bad emails. I've compiled a list of the bad emails I want to pull, and want to write a script which finds the emails from the "bad" list in the "20k" list, copies the whole row of each bad email to a "new" (generated) sheet, and then delete the row from the list of 20k.

Everything works until it needs to check for duplicates, copy them and delete the old ones (a nested for loop). Right now it copies everything (duplicate or not)multiple times, and then deletes the entire sheet. Here is the problem code:

 // Find duplicates from the two sheets and move them to the "FindDupes" sheet
  var dupes = false;
  var dataMDS = sourceSheetMDS.getDataRange().getValues();
  var dataETR = sourceSheetETR.getDataRange().getValues();
  for (i = numETRRows; i >= 0; i--) {
    for (j = numMDSRows; j >= 0; j--) {
      if  (sourceSheetETR[i,1] == sourceSheetMDS[j,1]) {
        dupes = true;

        // Copy the desired rows to the FindDupes sheet
        for (var k = 1; k <= numMDSCols; k++) {
          var sourceRange = sourceSheetMDS.getRange(1,k,j);
          var nextCol = newSheet.getLastColumn() + 1;
          sourceRange.copyTo(newSheet.getRange(1,nextCol,j));
        }
        sourceSheetMDS.deleteRow(j);
      }
    }
  }

Here is the whole project:

function findDuplicates() {

  // List the columns you want to check by number (A = 1)
  var CHECK_COLUMNS = [1];

  //Declare the Spreadsheet
  var ss = SpreadsheetApp.getActiveSpreadsheet();  

  // Get the active sheet and info about it
  // Main Database Sheet
  var sourceSheetMDS = ss.getSheetByName("test");
  var numMDSRows = sourceSheetMDS.getLastRow();
  var numMDSCols = sourceSheetMDS.getLastColumn();

  // Get the active sheet and info about it
  // Emails To Rremove Sheet
  var sourceSheetETR = ss.getSheetByName("Emails to Remove");
  var numETRRows = sourceSheetETR.getLastRow();
  var numETRCols = sourceSheetETR.getLastColumn();

  // Create the sheet of duplicates
  var ss = SpreadsheetApp.getActiveSpreadsheet();
  var newSheet = ss.insertSheet("FindDupes");

  // Find duplicates from the two sheets and move them to the "FindDupes" sheet
  var dupes = false;
  var dataMDS = sourceSheetMDS.getDataRange().getValues();
  var dataETR = sourceSheetETR.getDataRange().getValues();
  for (i = numETRRows; i >= 0; i--) {
    for (j = numMDSRows; j >= 0; j--) {
      if  (sourceSheetETR[i,1] == sourceSheetMDS[j,1]) {
        dupes = true;

        // Copy the desired rows to the FindDupes sheet
        for (var k = 1; k <= numMDSCols; k++) {
          var sourceRange = sourceSheetMDS.getRange(1,k,j);
          var nextCol = newSheet.getLastColumn() + 1;
          sourceRange.copyTo(newSheet.getRange(1,nextCol,j));
        }
        sourceSheetMDS.deleteRow(j);
      }
    }
  }


  // Alert the user with the results
  if (dupes) {
    Browser.msgBox("Possible duplicate(s) found, moved, and deleted.");
  } else {
    Browser.msgBox("No duplicates found.");
  }
};

Thank you!

Answer 1

Change

if  (sourceSheetETR[i,1] == sourceSheetMDS[j,1]) {
        dupes = true;
...

to

if  (dataETR[i,1] == dataMDS[j,1]) {
        dupes = true;
...

Explanation:

You have to compare values and not (not existant) sheet array entries.

Answer 2

I had to change a few things around because I couldn't get it to run properly.

 function findDuplicates() { // List the columns you want to check by number (A = 1) var CHECK_COLUMNS = [1]; //Declare the Spreadsheet var ss = SpreadsheetApp.getActiveSpreadsheet(); // Get the active sheet and info about it // Main Database Sheet var sourceSheetMDS = ss.getSheetByName("test"); var numMDSRows = sourceSheetMDS.getLastRow(); var numMDSCols = sourceSheetMDS.getLastColumn(); // Get the active sheet and info about it // Emails To Rremove Sheet var sourceSheetETR = ss.getSheetByName("Emails to Remove"); var numETRRows = sourceSheetETR.getLastRow(); var numETRCols = sourceSheetETR.getLastColumn(); // Create the sheet of duplicates var newSheet = ss.insertSheet("FindDupes"); // Find duplicates from the two sheets and move them to the "FindDupes" sheet var dupes = false; var dataMDS = sourceSheetMDS.getDataRange().getValues().reverse(); var dataETR = sourceSheetETR.getDataRange().getValues(); var rowsToDelete = [] dataETR.forEach(function (emailToRemoveRow) { var emailToRemove = emailToRemoveRow[0] dataMDS.forEach(function (dataRow, j) { var emailOfData = dataRow[0] if (emailToRemove == emailOfData) { dupes = true; // Copy the desired rows to the FindDupes sheet newSheet.appendRow(dataRow) rowsToDelete.push(j) } }) }) rowsToDelete.sort(function (a, b) { return b - a; }).forEach(function (rowIndex) { sourceSheetMDS.deleteRow(rowIndex); }) // Alert the user with the results if (dupes) { Browser.msgBox("Possible duplicate(s) found, moved, and deleted."); } else { Browser.msgBox("No duplicates found."); } };

and I am still a little confused because check_columns is not getting used. So where exactly is the email column? And what does the emails to remove sheet looks like? This code above is assuming that the email to remove sheet only has a single column which has the emails we want to remove, and the test sheet has the emails in its first column.