Eliminate newlines in google app script using regex
I'm trying to write part of an add-on for Google Docs that eliminates newlines within selected text using replaceText
. The obvious text.replaceText("\n","");
gives the error Invalid argument: searchPattern
. I get the same error with text.replaceText("\r","");
. The following attempts do nothing: text.replaceText("/\n/","");
, text.replaceText("/\r/","");
. I don't know why Google App Script does not allow for the recognition of newlines in regex.
I am aware that there is an add-on that does this already, but I want to incorporate this function into my add-on.
This error occurs even with the basic
DocumentApp.getActiveDocument().getBody().textReplace("\n","");
My full function:
function removeLineBreaks() {
var selection = DocumentApp.getActiveDocument().getSelection();
if (selection) {
var elements = selection.getRangeElements();
for (var i = 0; i < elements.length; i++) {
var element = elements[i];
// Only deal with text elements
if (element.getElement().editAsText) {
var text = element.getElement().editAsText();
if (element.isPartial()) {
text.replaceText("\n","");
}
// Deal with fully selected text
else {
text.replaceText("\n","");
}
}
}
}
// No text selected
else {
DocumentApp.getUi().alert('No text selected. Please select some text and try again.');
}
}
Solution 1:
It seems that in replaceText
, to remove soft returns entered with Shift-ENTER, you can use \v
:
.replaceText("\\v+", "")
If you want to remove all "other" control characters (C0, DEL and C1 control codes), you may use
.replaceText("\\p{Cc}+", "")
Note that the \v
pattern is a construct supported by JavaScript regex engine, and is considered to match a vertical tab character (≡ \013
) by the RE2 regex library used in most Google products.
Solution 2:
The Google Apps Script function replaceText() still doesn't accept escape characters, but I was able to get around this by using getText(), then the generic JavaScript replace(), then setText():
var doc = DocumentApp.getActiveDocument();
var body = doc.getBody();
var bodyText = body.getText();
//DocumentApp.getUi().alert( "Does document contain \\t? " + /\t/.test( bodyText ) ); // \n true, \r false, \t true
bodyText = bodyText.replace( /\n/g, "" );
bodyText = bodyText.replace( /\t/g, "" );
body.setText( bodyText );
This worked within a Doc. Not sure if the same is possible within a Sheet (and, even if it were, you'd probably have to run this once cell at a time).
Solution 3:
here is my pragmatic solution to eliminate newlines in Google Docs, or, more exact, to eliminate newlines from Gmail message.getPlainBody(). It looks that Google uses '\r\n\r\n' as a plain EOL and '\r\n' as a manuell Linefeed (Shift-Enter). The code should be self explainable. It might help to get alone with the newline problem in Docs. A solution possibly not very elegant, but works like a charm :-)
function GetEmails2Doc() {
var doc = DocumentApp.getActiveDocument();
var body = doc.getBody();
var pc = 0; // Paragraph Counter
var label = GmailApp.getUserLabelByName("_Send2Sheet");
var threads = label.getThreads();
var i = threads.length;
// LOOP Messages within a THREAT
for (i=threads.length-1; i>=0; i--) {
for (var j = 0; j < messages.length; j++) {
var message = messages[j];
/* Here I do some ...
body.insertParagraph(pc++, Utilities.formatDate(message.getDate(), "GMT",
"dd.MM.yyyy (HH:mm)")).setHeading(DocumentApp.ParagraphHeading.HEADING4)
str = message.getFrom() + ' to: ' + message.getTo();
if (message.getCc().length >0) str = str + ", Cc: " + message.getCc();
if (message.getBcc().length >0) str = str + ", Bcc: " + message.getBcc();
body.insertParagraph(pc++,str);
*/
// Body !!
var str = processBody(message.getPlainBody()).split("pEOL");
Logger.log(str.length + " EOLs");
for (var k=0; k<str.length; k++) body.insertParagraph(pc++,str[k]);
}
}
}
function processBody(tx) {
var s = tx.split(/\r\n\r\n/g);
// it looks like message.getPlainBody() [of mail] uses \r\n\r\n as EOL
// so, I first substitute the 'EOL's with the string pattern "pEOL"
// to be replaced with body.insertParagraph in the main function
tx = '';
for (k=0; k<s.length; k++) tx = tx + s[k] + "pEOL";
// then replace all remaining simple \r\n with a blank
s = tx.split(/\r\n/g);
tx = '';
for (k=0; k<s.length; k++) tx = tx + s[k] + " ";
return tx;
}