Import of Word Documents to ServiceNow Knowledge base

welterp · ‎02-10-2014

I am trying to import Word Documents to ServiceNow Knowledge Articles with out losing any images. I have tried using the Word Cleaner and SED installs without any success. Is there any fix that works?

conmic · ‎09-09-2014

IMPORTANT UPDATE - 03/03/2016:

I updated the entire script as I ran into some errors. And now it can also be used with journal fields!

See my reply: Re: Import of Word Documents to ServiceNow Knowledge base

You can also read more about it here: Create Knowledge Base Article (HTML field) or Comments (Journal field) from Email

you corrected the thrown exception errors on 4 of the lines in the script.

example on your line 18 with the part:

while(match == regex.exec(searchBody)){

the actual script is

while(match = regex.exec(searchBody)){

I know it throws an errors, but that's somehow required for the script to work. Because later you're going to use the value in the variable 'match' that has been set in line 18... If somebody has any idea how to formulate this correctly, you're welcome to help out.

Here is the full script that I use:

var gdt = new GlideDate();

gdt.addDays(2);

//current.valid_to = gdt;

var desc = email.subject;

desc = desc.replace("Knowledge:","");

current.short_description = desc.trim();

current.workflow_state = "draft";

current.topic = "General";

//current.category = "";

current.roles = "knowledge";



//Find and replace the image tags with the proper source.

//Get the number of attachments so the loop can be exited

//so it will stop no mater what.

var currentCount = 0;

var newBody = email.body_html;

var searchBody = email.body_html.replace(/\n/g, " ");



var regex = /<img(.*?)>/ig;

var match;

var match2;

while(match = regex.exec(searchBody)){

   //Add a style float tag next to the align tag.

   var alignText = match[0].replace(/align=['"]?left['"]?/gi, 'align="left" style="FLOAT: left"');

   alignText = alignText.replace(/align=['"]?right['"]?/gi, 'align="right" style="FLOAT: right"');

   searchBody = searchBody.replace(match[0], alignText);

   var regex2 = /src=("(.)*?"|'(.)*?'|(.)*?\s+$)?/ig;

   while(match2 = regex2.exec(alignText)){

   findAndReplaceImage(match2[1].replace(/\s+$/,"").replace(/"+/g,"").replace(/'+/g,""));

   }

   currentCount += 1;

   if(currentCount >= 100)

   break;

}

searchBody = searchBody.replace(/<o:p>(.*?)<\/o:p>/ig, "");

currentCount = 0;

var regex2 = /<!--\[if(.*?)<!\[endif\]-->/ig;

while(match = regex2.exec(searchBody)){

   searchBody = searchBody.replace(match[0], "");

   currentCount += 1;

   if(currentCount >= 100)

   break;

}

currentCount = 0;

var regex2 = /<!\[if !vml\]>(.*?)<!\[endif\]>/ig;

while(match = regex2.exec(searchBody)){

   searchBody = searchBody.replace(match[0], match[1]);

   currentCount += 1;

   if(currentCount >= 100)

   break;

}



//gs.log("Create Morning Post: " + searchBody);



current.text = searchBody;



current.insert();



event.state="stop_processing";



function getEmailSYSID(emailuid) {

   var em = new GlideRecord('sys_email');

   em.addQuery('uid', emailuid);

   em.query();

   while(em.next()) {

   //we execute the return only within a certain time difference between the creation of the attachment and now (in seconds)

   var dif = gs.dateDiff(em.sys_created_on, gs.nowNoTZ(), true);

   //gs.log("difference: " + dif + "eid: " + em.sys_id + " uid: " + em.uid); //debug

   if(dif < 300 && dif > -300){

   //gs.log('passed dif if: ' + em.sys_id + " uid: " + em.uid); //debug

   return em.sys_id;

   }

   }

   return "";

}




function findAndReplaceImage(imageText){

   var img = imageText;

   var imgName = img.substring(4, img.search(/@/i));

   var imgCode = "sys_attachment.do?sys_id=";

   //Get the sys_id of the attachment

   var gr = new GlideRecord("sys_attachment");

   gr.addQuery("file_name", imgName);

   gr.addQuery("table_sys_id", getEmailSYSID(email.uid));

   gr.query();

   if (gr.next()) {

   imgCode += gr.sys_id;

   }

   searchBody = searchBody.replace(img, imgCode);

}

View solution in original post

Goran WitchDoc · ‎11-05-2015

Thats strange..

since in our eureka the script looks like:

var match;

var match2;

while(match == regex.exec(searchBody)){

And it works here...

samwallace881 · ‎11-05-2015

Can you paste your full working code so I can see?

Mine still isn't working.

Goran WitchDoc · ‎11-05-2015

Condition on inbound action: email.subject.startsWith("ny knowledge:")

Dont forget to replace current.kb_knowledge_base = 'a7e8a78bff0221009b20ffffffffff17'; with your own sys_id

My script is like this:

var gdt = new GlideDate();

gdt.addDays(2);

//current.valid_to = gdt;

var desc = email.subject;

desc = desc.replace("Knowledge:","");

current.kb_knowledge_base = 'a7e8a78bff0221009b20ffffffffff17';

current.short_description = desc.trim();

current.workflow_state = "draft";

current.topic = "General";

current.roles = "knowledge";

//Find and replace the image tags with the proper source.

//Get the number of attachments so the loop can be exited

//so it will stop no mater what.

var currentCount = 0;

var newBody = email.body_html;

var emailuid = email.uid;

var searchBody = email.body_html.replace(/\n/g, " ");

var regex = /<img(.*?)>/ig;

var match = [];

var match2 = [];

while(match == regex.exec(searchBody)){

//Add a style float tag next to the align tag.

var alignText = match[0].replace(/align=['"]?left['"]?/gi, 'align="left" style="FLOAT: left"');

alignText = alignText.replace(/align=['"]?right['"]?/gi, 'align="right" style="FLOAT: right"');

searchBody = searchBody.replace(match[0], alignText);

var regex2 = /src=("(.)*?"|'(.)*?'|(.)*?\s+$)?/ig;

currentCount += 1;

if(currentCount >= 100)

break;

}

searchBody = searchBody.replace(/<o:p>(.*?)<\/o:p>/ig, "");

currentCount = 0;

var regex2 = //ig;

while(match == regex2.exec(searchBody)){

searchBody = searchBody.replace(match[0], "");

currentCount += 1;

if(currentCount >= 100)

break;

}

currentCount = 0;

var regex3 = /<!\[if !vml\]>(.*?)<!\[endif\]>/ig;

while(match == regex3.exec(searchBody)){

searchBody = searchBody.replace(match[0], match[1]);

currentCount += 1;

if(currentCount >= 100)

break;

}

searchBody = searchBody.replace(/<!\[if !supportLists\]>/ig, "");

searchBody = searchBody.replace(/<!\[endif\]>/ig, "");

current.text = searchBody;

current.insert();

event.state="stop_processing";

DrewW · ‎11-05-2015

I think you need to look at the HTML that is in the knowledge article because I believe changing the condition on the while loop like you have will cause it to never be true and there for never run. Which may or may not matter.

conmic · ‎03-03-2016

Hello there,

I have cleaned up the script as the current logic is causing errors in some cases. I wrote about it here:Create Knowledge Base Article (HTML field) or Comments (Journal field) from Email

My inbound action looks now like below and I am using the function "formatEmailBodyHtmlForJournal()" as described in my article above.

Condition: email.subject.indexOf("Knowledge:") == 0

Script:

/*load includes*/

var sismc = new global.SystemMailbox_Custom();


/*fields with no special logic*/

current.kb_knowledge_base = "dfc19531bf2021003f07e2c1ac0739ab"; //Legacy Knowledge Base

current.roles = "knowledge";

current.workflow_state = "draft";

current.topic = "";

//current.category = "";


/*fields that require a special logic*/

//Short Description - remove the "Knowledge:" prefix required to trigger this inbound action

var newSubject = email.subject;

newSubject = newSubject.replace("Knowledge:","");

current.short_description = newSubject.trim();


//Text - extract the HTML of the email body, format it to be usable with the HTML field in SN

var newText = sismc.formatEmailBodyHtmlForJournal(email.body_html);

current.text = newText;


//create the KB article

current.insert();


//stop processing any further inbound actions

event.state="stop_process";