Page Organization by text (unique ID number on page). Script needed?

Forum|Forum|2 years ago
June 5, 2023
2 replies
1953 views

Hello. Need to organize 2500 pages. Each page has searchable text containing a key ID on each page. I need to organize the pages by this ID. How can this be accomplished? Thank you.

This topic has been closed for replies.

bebarth

Community Expert

Yes, that can be done with a script.

The key ID is always at the same place on each page?

@+

O

OCD BObAuthor

Participating Frequently

Thank you for the response. It is in the same general area on each page. Some time I have to add the numbebecause the scanned doc is not egible. Can you point me in the direction of a pre made scrip?

O

OCD BObAuthor

Participating Frequently

Hi,

Here is the script I did for you:

d0=new Date();
starting=util.printd("mm/dd/yy – HH:MM:ss",d0);
var theIDs=[];
var noIDs=[];
for (var p=0; p<this.numPages; p++) {
	var found=0;
	var numWords=this.getPageNumWords(p);
	if (this.getPageNumWords(p)) {
		for (var i=0; i<this.getPageNumWords(p); i++) {
			if (this.getPageNthWord(p,i,true).toUpperCase()=="DEVICE" && this.getPageNthWord(p,i+1,true)=="NO") {
				theIDs.push([Number(this.getPageNthWord(p,i+2,true)),p]);
				found++;
				break;
			} else if (this.getPageNthWord(p,i,true).toUpperCase().indexOf("DE")==0 && this.getPageNthWord(p,i+2,true)=="NO") {
				theIDs.push([Number(this.getPageNthWord(p,i+3,true)),p]);
				found++;
				break;
			} else if (this.getPageNthWord(p,i,true).toUpperCase()=="ID" && !isNaN(Number(this.getPageNthWord(p,i+1,true)))) {
				theIDs.push([Number(this.getPageNthWord(p,i+1,true)),p]);
				found++;
				break;
			}
		}
	}
	if (!found) noIDs.push(p);
}
if (theIDs.length) {
	theIDs.sort(function(a, b){return a[0]-b[0]});
	var newDoc=app.newDoc();
	for (var i=0; i<theIDs.length; i++) {
		newDoc.insertPages ({
			nPage: newDoc.numPages-1,
			cPath: this.path,
			nStart: theIDs[i][1]
		});
	}
	newDoc.deletePages(0);
	if (noIDs.length) {
		for (var i=0; i<noIDs.length; i++) {
			newDoc.insertPages ({
				nPage: newDoc.numPages-1,
				cPath: this.path,
				nStart: noIDs[i]
			});
		}
	}
	newDoc.saveAs(this.path.replace(/.pdf$/i," \(Sorted\).pdf"));
	df=new Date();
	ending=util.printd("mm/dd/yy – HH:MM:ss",df);
	temps=(df.valueOf()-d0.valueOf())/1000/60;
	var theMinutes=parseInt(temps);
	var theSeconds=(temps-theMinutes)*60;
	var theSeconds=parseInt(theSeconds*10)/10;
	var theTime="";
	if (theMinutes>0) {
		if (theMinutes==1) var theTime="1 minute";
		else var theTime=theMinutes+" minutes";
	}
	if (theSeconds>0) {
		if (theSeconds<2) var theTime=theTime+" "+theSeconds+" second";
		else var theTime=theTime+" "+theSeconds+" seconds";
	}
	var theTime=theTime.replace(/^\s+|\s+$/gm,"");
	var plurial=theIDs.length>1?"s":"";
	var txt="Process starting: "+starting+"\rProcess ending: "+ending+"\rProcess duration: "+theTime+"\r\r"+theIDs.length+" reference"+plurial+" sorted.";
	if (noIDs.length) {
		var plurial=noIDs.length>1?"s":"";
		txt+="\r"+noIDs.length+" page"+plurial+" without any ID found.";
	}
	console.clear();
	console.println(txt);
	app.alert(txt,3);
}

With this script the attached file has been generated in about 1 second, but that will take more time for your 2500-page file and maybe you would prefer this other script which will show you the progress of the process.

d0=new Date();
starting=util.printd("mm/dd/yy – HH:MM:ss",d0);
var theIDs=[];
var noIDs=[];
for (var p=0; p<this.numPages; p++) {
	console.clear();
	console.println("Process starting: "+starting);
	console.println("Processing the page #"+(p+1)+"/"+this.numPages);
	var found=0;
	var numWords=this.getPageNumWords(p);
	if (this.getPageNumWords(p)) {
		for (var i=0; i<this.getPageNumWords(p); i++) {
			if (this.getPageNthWord(p,i,true).toUpperCase()=="DEVICE" && this.getPageNthWord(p,i+1,true)=="NO") {
				theIDs.push([Number(this.getPageNthWord(p,i+2,true)),p]);
				found++;
				break;
			} else if (this.getPageNthWord(p,i,true).toUpperCase().indexOf("DE")==0 && this.getPageNthWord(p,i+2,true)=="NO") {
				theIDs.push([Number(this.getPageNthWord(p,i+3,true)),p]);
				found++;
				break;
			} else if (this.getPageNthWord(p,i,true).toUpperCase()=="ID" && !isNaN(Number(this.getPageNthWord(p,i+1,true)))) {
				theIDs.push([Number(this.getPageNthWord(p,i+1,true)),p]);
				found++;
				break;
			}
		}
	}
	if (!found) noIDs.push(p);
}
if (theIDs.length) {
	theIDs.sort(function(a, b){return a[0]-b[0]});
	var newDoc=app.newDoc();
	for (var i=0; i<theIDs.length; i++) {
		console.clear();
		console.println("Process starting: "+starting);
		console.println("Adding page #"+(theIDs[i][1]+1)+" to the new file.");
		newDoc.insertPages ({
			nPage: newDoc.numPages-1,
			cPath: this.path,
			nStart: theIDs[i][1]
		});
	}
	newDoc.deletePages(0);
	if (noIDs.length) {
		for (var i=0; i<noIDs.length; i++) {
			console.clear();
			console.println("Process starting: "+starting);
			console.println("Adding page #"+(noIDs[i]+1)+" to the new file.");
			newDoc.insertPages ({
				nPage: newDoc.numPages-1,
				cPath: this.path,
				nStart: noIDs[i]
			});
		}
	}
	newDoc.saveAs(this.path.replace(/.pdf$/i," \(Sorted\).pdf"));
	df=new Date();
	ending=util.printd("mm/dd/yy – HH:MM:ss",df);
	temps=(df.valueOf()-d0.valueOf())/1000/60;
	var theMinutes=parseInt(temps);
	var theSeconds=(temps-theMinutes)*60;
	var theSeconds=parseInt(theSeconds*10)/10;
	var theTime="";
	if (theMinutes>0) {
		if (theMinutes==1) var theTime="1 minute";
		else var theTime=theMinutes+" minutes";
	}
	if (theSeconds>0) {
		if (theSeconds<2) var theTime=theTime+" "+theSeconds+" second";
		else var theTime=theTime+" "+theSeconds+" seconds";
	}
	var theTime=theTime.replace(/^\s+|\s+$/gm,"");
	var plurial=theIDs.length>1?"s":"";
	var txt="Process starting: "+starting+"\rProcess ending: "+ending+"\rProcess duration: "+theTime+"\r\r"+theIDs.length+" reference"+plurial+" sorted.";
	if (noIDs.length) {
		var plurial=noIDs.length>1?"s":"";
		txt+="\r"+noIDs.length+" page"+plurial+" without any ID found.";
	}
	console.clear();
	console.println(txt);
	app.alert(txt,3);
}

Let me know if that suits to you and how long did that take for your entire file.

@+

Wow. This is great java wizardry. I will apply this any let you know. Thank you for sharing your skill set 😃

Bernd Alheit

Community Expert

May be possible with a script.

O

OCD BObAuthor

Participating Frequently

Thank you for the response. Can you point me in the direction of a pre made scrip?

Sign up

To post, reply, or follow discussions, please sign in with your Adobe ID.

Sign in to Adobe Community

To post, reply, or follow discussions, please sign in with your Adobe ID.

Scanning file for viruses.

This file cannot be downloaded