Get pdf-attachments from Gmail as text - pdf

I searched around the web & Stack Overflow but didn't find a solution. What I try to do is the following: I get certain attachments via mail that I would like to have as (Plain) text for further processing. My script looks like this:
function MyFunction() {
var threads = GmailApp.search ('label:templabel');
var messages = GmailApp.getMessagesForThreads(threads);
for (i = 0; i < messages.length; ++i)
{
j = messages[i].length;
var messageBody = messages[i][0].getBody();
var messageSubject = messages [i][0].getSubject();
var attach = messages [i][0].getAttachments();
var attachcontent = attach.getContentAsString();
GmailApp.sendEmail("mail", messageSubject, "", {htmlBody: attachcontent});
}
}
Unfortunately this doesn't work. Does anybody here have an idea how I can do this? Is it even possible?
Thank you very much in advance.
Best, Phil

Edit: Updated for DriveApp, as DocsList deprecated.
I suggest breaking this down into two problems. The first is how to get a pdf attachment from an email, the second is how to convert that pdf to text.
As you've found out, getContentAsString() does not magically change a pdf attachment to plain text or html. We need to do something a little more complicated.
First, we'll get the attachment as a Blob, a utility class used by several Services to exchange data.
var blob = attachments[0].getAs(MimeType.PDF);
So with the second problem separated out, and maintaining the assumption that we're interested in only the first attachment of the first message of each thread labeled templabel, here is how myFunction() looks:
/**
* Get messages labeled 'templabel', and send myself the text contents of
* pdf attachments in new emails.
*/
function myFunction() {
var threads = GmailApp.search('label:templabel');
var threadsMessages = GmailApp.getMessagesForThreads(threads);
for (var thread = 0; thread < threadsMessages.length; ++thread) {
var message = threadsMessages[thread][0];
var messageBody = message.getBody();
var messageSubject = message.getSubject();
var attachments = message.getAttachments();
var blob = attachments[0].getAs(MimeType.PDF);
var filetext = pdfToText( blob, {keepTextfile: false} );
GmailApp.sendEmail(Session.getActiveUser().getEmail(), messageSubject, filetext);
}
}
We're relying on a helper function, pdfToText(), to convert our pdf blob into text, which we'll then send to ourselves as a plain text email. This helper function has a variety of options; by setting keepTextfile: false, we've elected to just have it return the text content of the PDF file to us, and leave no residual files in our Drive.
pdfToText()
This utility is available as a gist. Several examples are provided there.
A previous answer indicated that it was possible to use the Drive API's insert method to perform OCR, but it didn't provide code details. With the introduction of Advanced Google Services, the Drive API is easily accessible from Google Apps Script. You do need to switch on and enable the Drive API from the editor, under Resources > Advanced Google Services.
pdfToText() uses the Drive service to generate a Google Doc from the content of the PDF file. Unfortunately, this contains the "pictures" of each page in the document - not much we can do about that. It then uses the regular DocumentService to extract the document body as plain text.
/**
* See gist: https://gist.github.com/mogsdad/e6795e438615d252584f
*
* Convert pdf file (blob) to a text file on Drive, using built-in OCR.
* By default, the text file will be placed in the root folder, with the same
* name as source pdf (but extension 'txt'). Options:
* keepPdf (boolean, default false) Keep a copy of the original PDF file.
* keepGdoc (boolean, default false) Keep a copy of the OCR Google Doc file.
* keepTextfile (boolean, default true) Keep a copy of the text file.
* path (string, default blank) Folder path to store file(s) in.
* ocrLanguage (ISO 639-1 code) Default 'en'.
* textResult (boolean, default false) If true and keepTextfile true, return
* string of text content. If keepTextfile
* is false, text content is returned without
* regard to this option. Otherwise, return
* id of textfile.
*
* #param {blob} pdfFile Blob containing pdf file
* #param {object} options (Optional) Object specifying handling details
*
* #returns {string} id of text file (default) or text content
*/
function pdfToText ( pdfFile, options ) {
// Ensure Advanced Drive Service is enabled
try {
Drive.Files.list();
}
catch (e) {
throw new Error( "To use pdfToText(), first enable 'Drive API' in Resources > Advanced Google Services." );
}
// Set default options
options = options || {};
options.keepTextfile = options.hasOwnProperty("keepTextfile") ? options.keepTextfile : true;
// Prepare resource object for file creation
var parents = [];
if (options.path) {
parents.push( getDriveFolderFromPath (options.path) );
}
var pdfName = pdfFile.getName();
var resource = {
title: pdfName,
mimeType: pdfFile.getContentType(),
parents: parents
};
// Save PDF to Drive, if requested
if (options.keepPdf) {
var file = Drive.Files.insert(resource, pdfFile);
}
// Save PDF as GDOC
resource.title = pdfName.replace(/pdf$/, 'gdoc');
var insertOpts = {
ocr: true,
ocrLanguage: options.ocrLanguage || 'en'
}
var gdocFile = Drive.Files.insert(resource, pdfFile, insertOpts);
// Get text from GDOC
var gdocDoc = DocumentApp.openById(gdocFile.id);
var text = gdocDoc.getBody().getText();
// We're done using the Gdoc. Unless requested to keepGdoc, delete it.
if (!options.keepGdoc) {
Drive.Files.remove(gdocFile.id);
}
// Save text file, if requested
if (options.keepTextfile) {
resource.title = pdfName.replace(/pdf$/, 'txt');
resource.mimeType = MimeType.PLAIN_TEXT;
var textBlob = Utilities.newBlob(text, MimeType.PLAIN_TEXT, resource.title);
var textFile = Drive.Files.insert(resource, textBlob);
}
// Return result of conversion
if (!options.keepTextfile || options.textResult) {
return text;
}
else {
return textFile.id
}
}
The conversion to DriveApp is helped with this utility from Bruce McPherson:
// From: http://ramblings.mcpher.com/Home/excelquirks/gooscript/driveapppathfolder
function getDriveFolderFromPath (path) {
return (path || "/").split("/").reduce ( function(prev,current) {
if (prev && current) {
var fldrs = prev.getFoldersByName(current);
return fldrs.hasNext() ? fldrs.next() : null;
}
else {
return current ? null : prev;
}
},DriveApp.getRootFolder());
}

Related

Printing to pdf from Google Apps Script HtmlOutput

For years, I have been using Google Cloud Print to print labels in our laboratories on campus (to standardize) using a Google Apps Script custom HtmlService form.
Now that GCP is becoming depreciated, I am in on a search for a solution. I have found a few options but am struggling to get the file to convert to a pdf as would be needed with these other vendors.
Currently, when you submit a text/html blob to the GCP servers in GAS, the backend converts the blob to application/pdf (as evidenced by looking at the job details in the GCP panel on Chrome under 'content type').
That said, because these other cloud print services require pdf printing, I have tried for some time now to have GAS change the file to pdf format before sending to GCP and I always get a strange result. Below, I'll show some of the strategies that I have used and include pictures of one of our simple labels generated with the different functions.
The following is the base code for the ticket and payload that has worked for years with GCP
//BUILD PRINT JOB FOR NARROW TAPES
var ticket = {
version: "1.0",
print: {
color: {
type: "STANDARD_COLOR",
vendor_id: "Color"
},
duplex: {
type: "NO_DUPLEX"
},
copies: {copies: parseFloat(quantity)},
media_size: {
width_microns: 27940,
height_microns:40960
},
page_orientation: {
type: "LANDSCAPE"
},
margins: {
top_microns:0,
bottom_microns:0,
left_microns:0,
right_microns:0
},
page_range: {
interval:
[{start:1,
end:1}]
},
}
};
var payload = {
"printerid" : QL710,
"title" : "Blank Template Label",
"content" : HtmlService.createHtmlOutput(html).getBlob(),
"contentType": 'text/html',
"ticket" : JSON.stringify(ticket)
};
This generates the expected following printout:
When trying to convert to pdf using the following code:
The following is the code used to transform to pdf:
var blob = HtmlService.createTemplate(html).evaluate().getContent();
var newBlob = Utilities.newBlob(html, "text/html", "text.html");
var pdf = newBlob.getAs("application/pdf").setName('tempfile');
var file = DriveApp.getFolderById("FOLDER ID").createFile(pdf);
var payload = {
"printerid" : QL710,
"title" : "Blank Template Label",
"content" : pdf,//HtmlService.createHtmlOutput(html).getBlob(),
"contentType": 'text/html',
"ticket" : JSON.stringify(ticket)
};
an unexpected result occurs:
This comes out the same way for direct coding in the 'content' field with and without .getBlob():
"content" : HtmlService.createHtmlOutput(html).getAs('application/pdf'),
note the createFile line in the code above used to test the pdf. This file is created as expected, of course with the wrong dimensions for label printing (not sure how to convert to pdf with the appropriate margins and page size?): see below
I have now tried to adopt Yuri's ideas; however, the conversion from html to document loses formatting.
var blob = HtmlService.createHtmlOutput(html).getBlob();
var docID = Drive.Files.insert({title: 'temp-label'}, blob, {convert: true}).id
var file = DocumentApp.openById(docID);
file.getBody().setMarginBottom(0).setMarginLeft(0).setMarginRight(0).setMarginTop(0).setPageHeight(79.2).setPageWidth(172.8);
This produces a document looks like this (picture also showing expected output in my hand).
Does anyone have insights into:
How to format the converted pdf to contain appropriate height, width
and margins.
How to convert to pdf in a way that would print correctly.
Here is a minimal code to get a better sense of context https://script.google.com/d/1yP3Jyr_r_FIlt6_aGj_zIf7HnVGEOPBKI0MpjEGHRFAWztGzcWKCJrD0/edit?usp=sharing
I've made the template (80 x 40 mm -- sorry, I don't know your size):
https://docs.google.com/document/d/1vA93FxGXcWLIEZBuQwec0n23cWGddyLoey-h0WR9weY/edit?usp=sharing
And there is the script:
function myFunction() {
// input data
var matName = '<b>testing this to <u>see</u></b> if it <i>actually</i> works <i>e.coli</i>'
var disposeWeek = 'end of semester'
var prepper = 'John Ruppert';
var className = 'Cell and <b>Molecular</b> Biology <u>Fall 2020</u> a few exercises a few exercises a few exercises a few exercises';
var hazards = 'Lots of hazards';
// make a temporary Doc from the template
var copyFile = DriveApp.getFileById('1vA93FxGXcWLIEZBuQwec0n23cWGddyLoey-h0WR9weY').makeCopy();
var doc = DocumentApp.openById(copyFile.getId());
var body = doc.getBody();
// replace placeholders with data
body.replaceText('{matName}', matName);
body.replaceText('{disposeWeek}', disposeWeek);
body.replaceText('{prepper}', prepper);
body.replaceText('{className}', className);
body.replaceText('{hazards}', hazards);
// make Italics, Bold and Underline
handle_tags(['<i>', '</i>'], body);
handle_tags(['<b>', '</b>'], body);
handle_tags(['<u>', '</u>'], body);
// save the temporary Doc
doc.saveAndClose();
// make a PDF
var docblob = doc.getBlob().setName('Label.pdf');
DriveApp.createFile(docblob);
// delete the temporary Doc
copyFile.setTrashed(true);
}
// this function applies formatting to text inside the tags
function handle_tags(tags, body) {
var start_tag = tags[0].toLowerCase();
var end_tag = tags[1].toLowerCase();
var found = body.findText(start_tag);
while (found) {
var elem = found.getElement();
var start = found.getEndOffsetInclusive();
var end = body.findText(end_tag, found).getStartOffset()-1;
switch (start_tag) {
case '<b>': elem.setBold(start, end, true); break;
case '<i>': elem.setItalic(start, end, true); break;
case '<u>': elem.setUnderline(start, end, true); break;
}
found = body.findText(start_tag, found);
}
body.replaceText(start_tag, ''); // remove tags
body.replaceText(end_tag, '');
}
The script just changes the {placeholders} with the data and saves the result as a PDF file (Label.pdf). The PDF looks like this:
There is one thing, I'm not sure if it's possible -- to change a size of the texts dynamically to fit them into the cells, like it's done in your 'autosize.html'. Roughly, you can take a length of the text in the cell and, in case it is bigger than some number, to make the font size a bit smaller. Probably you can use the jquery texfill function from the 'autosize.html' to get an optimal size and apply the size in the document.
I'm not sure if I got you right. Do you need make PDF and save it on Google Drive? You can do in Google Docs.
As example:
Make a new document with your table and text. Something like this
Add this script into your doc:
function myFunction() {
var copyFile = DriveApp.getFileById(ID).makeCopy();
var newFile = DriveApp.createFile(copyFile.getAs('application/pdf'));
newFile.setName('label');
copyFile.setTrashed(true);
}
Every time you run this script it makes the file 'label.pdf' on your Google Drive.
The size of this pdf will be the same as the page size of your Doc. You can make any size of page with add-on: Page Sizer https://webapps.stackexchange.com/questions/129617/how-to-change-the-size-of-paper-in-google-docs-to-custom-size
If you need to change the text in your label before generate pdf or/and you need change the name of generated file, you can do it via script as well.
Here is a variant of the script that changes a font size in one of the cells if the label doesn't fit into one page.
function main() {
// input texts
var text = {};
text.matName = '<b>testing this to <u>see</u></b> if it <i>actually</i> works <i>e.coli</i>';
text.disposeWeek = 'end of semester';
text.prepper = 'John Ruppert';
text.className = 'Cell and <b>Molecular</b> Biology <u>Fall 2020</u> a few exercises a few exercises a few exercises a few exercises';
text.hazards = 'Lots of hazards';
// initial max font size for the 'matName'
var size = 10;
var doc_blob = set_text(text, size);
// if we got more than 1 page, reduce the font size and repeat
while ((size > 4) && (getNumPages(doc_blob) > 1)) {
size = size-0.5;
doc_blob = set_text(text, size);
}
// save pdf
DriveApp.createFile(doc_blob);
}
// this function takes texts and a size and put the texts into fields
function set_text(text, size) {
// make a copy
var copyFile = DriveApp.getFileById('1vA93FxGXcWLIEZBuQwec0n23cWGddyLoey-h0WR9weY').makeCopy();
var doc = DocumentApp.openById(copyFile.getId());
var body = doc.getBody();
// replace placeholders with data
body.replaceText('{matName}', text.matName);
body.replaceText('{disposeWeek}', text.disposeWeek);
body.replaceText('{prepper}', text.prepper);
body.replaceText('{className}', text.className);
body.replaceText('{hazards}', text.hazards);
// set font size for 'matName'
body.findText(text.matName).getElement().asText().setFontSize(size);
// make Italics, Bold and Underline
handle_tags(['<i>', '</i>'], body);
handle_tags(['<b>', '</b>'], body);
handle_tags(['<u>', '</u>'], body);
// save the doc
doc.saveAndClose();
// delete the copy
copyFile.setTrashed(true);
// return blob
return docblob = doc.getBlob().setName('Label.pdf');
}
// this function formats the text beween html tags
function handle_tags(tags, body) {
var start_tag = tags[0].toLowerCase();
var end_tag = tags[1].toLowerCase();
var found = body.findText(start_tag);
while (found) {
var elem = found.getElement();
var start = found.getEndOffsetInclusive();
var end = body.findText(end_tag, found).getStartOffset()-1;
switch (start_tag) {
case '<b>': elem.setBold(start, end, true); break;
case '<i>': elem.setItalic(start, end, true); break;
case '<u>': elem.setUnderline(start, end, true); break;
}
found = body.findText(start_tag, found);
}
body.replaceText(start_tag, '');
body.replaceText(end_tag, '');
}
// this funcion takes saved doc and returns the number of its pages
function getNumPages(doc) {
var blob = doc.getAs('application/pdf');
var data = blob.getDataAsString();
var pages = parseInt(data.match(/ \/N (\d+) /)[1], 10);
Logger.log("pages = " + pages);
return pages;
}
It looks rather awful and hopeless. It turned out that Google Docs has no page number counter. You need to convert your document into a PDF and to count pages of the PDF file. Gross!
Next problem, even if you managed somehow to count the pages, you have no clue which of the cells was overflowed. This script takes just one cell, changes its font size, counts pages, changes the font size again, etc. But it doesn't granted a success, because there can be another cell with long text inside. You can reduce font size of all the texts, but it doesn't look like a great idea as well.

Acumatica: How do I get an attachment file from SO Screen using Web API?

I'd folow the example From I200 pdf for a stock item, but I dont' know how to download the file from an Sales Order. Does anybody has a clue?
IN202500Content stockItemSchema = context.IN202500GetSchema();
var commands = new Command[]
{
new Value
{
Value = "AAMACHINE1",
LinkedCommand = stockItemSchema.StockItemSummary.InventoryID
},
new Value
{
FieldName = "T2MCRO.jpg",
LinkedCommand =
stockItemSchema.StockItemSummary.ServiceCommands.Attachment
}
};
var stockItemAttachment =
context.IN202500Export(commands, null, 1, false, true);
You were almost there, in the "stockItemAttachment" variable you should have the content of the file "T2MCRO.jpg" in byte format.
The only thing you have left to do is to write it to your file system.
You can use the following command :
File.WriteAllBytes(Path, Convert.FromBase64String(stockItemAttachment[0][0]));

Detecting file size with MultipartFormDataStreamProvider before file is saved?

We are using the MultipartFormDataStreamProviderto save file upload by clients. I have a hard requirement that file size must be greater than 1KB. The easiest thing to do would of course be the save the file to disk and then look at the file unfortunately i can't do it like this. After i save the file to disk i don't have the ability to access it so i need to look at the file before its saved to disk. I've been looking at the properties of the stream provider to try to figure out what the size of the file is but unfortunately i've been unsuccessful.
The test file i'm using is 1025 bytes.
MultipartFormDataStreamProvider.BufferSize is 4096
Headers.ContentDisposition.Size is null
ContentLength is null
Is there a way to determine file size before it's saved to the file system?
Thanks to Guanxi i was able to formulate a solution. I used his code in the link as the basis i just added a little more async/await goodness :). I wanted to add the solution just in case it helps anyone else:
private async Task SaveMultipartStreamToDisk(Guid guid, string fullPath)
{
var user = HttpContext.Current.User.Identity.Name;
var multipartMemoryStreamProvider = await Request.Content.ReadAsMultipartAsync();
foreach (var content in multipartMemoryStreamProvider.Contents)
{
using (content)
{
if (content.Headers.ContentDisposition.FileName != null)
{
var existingFileName = content.Headers.ContentDisposition.FileName.Replace("\"", string.Empty);
Log.Information("Original File name was {OriginalFileName}: {guid} {user}", existingFileName, guid,user);
using (var st = await content.ReadAsStreamAsync())
{
var ext = Path.GetExtension(existingFileName.Replace("\"", string.Empty));
List<string> validExtensions = new List<string>() { ".pdf", ".jpg", ".jpeg", ".png" };
//1024 = 1KB
if (st.Length > 1024 && validExtensions.Contains(ext, StringComparer.OrdinalIgnoreCase))
{
var newFileName = guid + ext;
using (var fs = new FileStream(Path.Combine(fullPath, newFileName), FileMode.Create))
{
await st.CopyToAsync(fs);
Log.Information("Completed writing {file}: {guid} {user}", Path.Combine(fullPath, newFileName), guid, HttpContext.Current.User.Identity.Name);
}
}
else
{
if (st.Length < 1025)
{
Log.Warning("File of length {FileLength} bytes was attempted to be uploaded: {guid} {user}",st.Length,guid,user);
}
else
{
Log.Warning("A file of type {FileType} was attempted to be uploaded: {guid} {user}", ext, guid,user);
}
var responseMessage = new HttpResponseMessage(HttpStatusCode.BadRequest)
{
Content =
st.Length < 1025
? new StringContent(
$"file of length {st.Length} does not meet our minumim file size requirements")
: new StringContent($"a file extension of {ext} is not an acceptable type")
};
throw new HttpResponseException(responseMessage);
}
}
}
}
}
You can also read the request contents without using MultipartFormDataStreamProvider. In that case all of the request contents (including files) would be in memory. I have given an example of how to do that at this link.
In this case you can read header for file size or read stream and check the file size. If it satisfy your criteria then only write it to desire location.

Fiddler: Programmatically add word to Query string

Please be kind, I'm new to Fiddler
My purpose:I want to use Fiddler as a Google search filter
Summary:
I'm tired of manually adding "dog" every time I use Google.I do not want the "dog" appearing in my search results.
For example:
//www.google.com/search?q=cat+-dog
//www.google.com/search?q=baseball+-dog
CODE:
dog replaced with -torrent-watch-download
// ==UserScript==
// #name Tamper with Google Results
// #namespace http://superuser.com/users/145045/krowe
// #version 0.1
// #description This just modifies google results to exclude certain things.
// #match http://*.google.com
// #match https://*.google.com
// #copyright 2014+, KRowe
// ==/UserScript==
function GM_main () {
window.onload = function () {
var targ = window.location;
if(targ && targ.href && targ.href.match('https?:\/\/www.google.com/.+#q=.+') && targ.href.search("/+-torrent/+-watch/+-download")==-1) {
targ.href = targ.href +"+-torrent+-watch+-download";
}
};
}
//-- This is a standard-ish utility function:
function addJS_Node(text, s_URL, funcToRun, runOnLoad) {
var D=document, scriptNode = D.createElement('script');
if(runOnLoad) scriptNode.addEventListener("load", runOnLoad, false);
scriptNode.type = "text/javascript";
if(text) scriptNode.textContent = text;
if(s_URL) scriptNode.src = s_URL;
if(funcToRun) scriptNode.textContent = '(' + funcToRun.toString() + ')()';
var targ = D.getElementsByTagName('head')[0] || D.body || D.documentElement;
targ.appendChild(scriptNode);
}
addJS_Node (null, null, GM_main);
At first I was going to go with Tampermonkey userscripts,Because I did not know about Fiddler
==================================================================================
Now,lets focus on Fiddler
Before Request:
I want Fiddler to add text at the end of Google Query string.
Someone suggested me to use
static function OnBeforeRequest(oSession: Session) {
if (oSession.uriContains("targetString")) {
var sText = "Enter a string to append to a URL";
oSession.fullUrl = oSession.fullUrl + sText;
}
}
Before Response:
This is where my problem lies
I totally love the HTML response,Now I just want to scrape/hide the word in the search box without changing the search results.How can it be done? Any Ideas?
http://i.stack.imgur.com/4mUSt.jpg
Can you guys please take the above information and fix the problem for me
Thank you
Basing on goal definition above, I believe you can achieve better results with your own free Google custom search engine service. In particular, because you have control over GCSE fine-tuning results, returned by regular Google search.
Links:
https://www.google.com/cse/all
https://developers.google.com/custom-search/docs/structured_search

ColdFusion CFDOCUMENT with links to other PDFs

I am creating a PDF using the cfdocument tag at the moment. The PDF is not much more than a bunch of links to other PDFs.
So I create this PDF index and the links are all HREFs
Another PDF
if I set the localURL attribute to "no" my URLs have the whole web path in them:
Another PDF
if I set the localURL attribute to "yes" then I get:
Another PDF
So this index PDF is going to go onto a CD and all of the linked PDFs are going to sit right next to it so I need a relative link ... more like:
Another PDF
cfdocument does not seem to do this. I can modify the file name of the document and make it "File:///Another_PDF.pdf" but this does not work either because I don't know the driveletter of the CD drive ... or if the files are going to end up inside a directory on the CD.
Is there a way (possibly using iText or something) of opening up the PDF once it is created and converting the URL links to actual PDF GoTo tags?
I know this is kind of a stretch but I am at my wits end with this.
So I've managed to get into the Objects but I'm still struggling with.
Converting from:
5 0 obj<</C[0 0 1]/Border[0 0 0]/A<</URI(File:///75110_002.PDF)/S/URI>>/Subtype/Link/Rect[145 502 184 513]>>endobj
To this:
19 0 obj<</SGoToR/D[0/XYZ null null 0]/F(75110_002.PDF)>>endobj
20 0 obj<</Subtype/Link/Rect[145 502 184 513]/Border[0 0 0]/A 19 0 R>>endobj
Wow this is really kicking my ass! :)
So I've managed to get the document open, loop through the Link Annotations, capture the Rect co-ordinates and the linked to document name (saved into an array of Structures) and then successfully deleted the Annotation which was a URI Link.
So now I thought I could now loop over that array of structures and put the Annotations back into the document using the createLink method or the setAction method. But all the examples I've seen of these methods are attached to a Chunk (of text). But my document already has the Text in place so I don't need to remake the text links I just need to put the Links back in in the same spot.
So I figured I could reopen the document and look for the actual text that was the link and then attache the setAction to th ealready existing chunk of text .... I can't find the text!!
I suck! :)
This thread has an example of updating the link actions, by modifying the pdf annotations. It is written in iTextSharp 5.x, but the java code is not much different.
The thread provides a solid explanation of how annotations work. But to summarize, you need to read in your source pdf and loop through the individual pages for annotations. Extract the links and use something like getFileFromPath() to replace them with a file name only.
I was curious, so I did a quick and ugly conversion of the iTextSharp code above. Disclaimer, it is not highly tested:
/**
Usage:
util = createObject("component", "path.to.ThisComponent");
util.fixLinks( "c:/path/to/sourceFile.pdf", "c:/path/to/newFile.pdf");
*/
component {
/**
Convert all absolute links, in the given pdf, to relative links (file name only)
#source - absolute path to the source pdf file
#destination - absolute path to save copy
*/
public function fixLinks( string source, string destination) {
// initialize objects
Local.reader = createObject("java", "com.lowagie.text.pdf.PdfReader").init( arguments.source );
Local.pdfName = createObject("java", "com.lowagie.text.pdf.PdfName");
// check each page for hyperlinks
for ( Local.i = 1; Local.i <= Local.reader.getNumberOfPages(); Local.i++) {
//Get all of the annotations for the current page
Local.page = Local.reader.getPageN( Local.i );
Local.annotations = Local.page.getAsArray( Local.PdfName.ANNOTS ).getArrayList();
// search annotations for links
for (Local.x = 1; !isNull( Local.annotations) && Local.x < arrayLen(Local.annotations); Local.x++) {
// get current properties
Local.current = Local.annotations[ Local.x ];
Local.dictionary = Local.reader.getPdfObject( Local.current );
Local.subType = Local.dictionary.get( Local.PdfName.SUBTYPE );
Local.action = Local.dictionary.get( Local.PdfName.A );
Local.hasLink = true;
//Skip this item if it does not have a link AND action
if (Local.subType != Local.PdfName.LINK || isNull(Local.action)) {
Local.hasLink = false;
}
//Skip this item if it does not have a URI
if ( Local.hasLink && Local.action.get( Local.PdfName.S ) != Local.PdfName.URI ) {
Local.hasLink = false;
}
//If it is a valid URI, update link
if (Local.hasLink) {
// extract file name from URL
Local.oldLink = Local.action.get( Local.pdfName.URI );
Local.newLink = getFileFromPath( Local.oldLink );
// replace link
// WriteDump("Changed link from ["& Local.oldLink &"] ==> ["& Local.newLink &"]");
Local.pdfString = createObject("java", "com.lowagie.text.pdf.PdfString");
Local.action.put( Local.pdfName.URI, Local.pdfString.init( Local.newLink ) );
}
}
}
// save all pages to new file
copyPDF( Local.reader , arguments.destination );
}
/**
Copy all pages in pdfReader to the given destination file
#pdfReader - pdf to copy
#destination - absolute path to save copy
*/
public function copyPDF( any pdfReader, string destination) {
try {
Local.doc = createObject("java", "com.lowagie.text.Document").init();
Local.out = createObject("java", "java.io.FileOutputStream").init( arguments.destination );
Local.writer = createObject("java", "com.lowagie.text.pdf.PdfCopy").init(Local.doc, Local.out);
// open document and save individual pages
Local.doc.open();
for (Local.i = 1; i <= arguments.pdfReader.getNumberOfPages(); Local.i++) {
Local.writer.addPage( Local.writer.getImportedPage( arguments.pdfReader, Local.i) );
}
Local.doc.close();
}
finally
{
// cleanup
if (structKeyExists(Local, "doc")) { Local.doc.close(); }
if (structKeyExists(Local, "writer")) { Local.writer.close(); }
if (structKeyExists(Local, "out")) { Local.out.close(); }
}
}
}
I finally got it:
public function resetLinks( string source, string destination) {
try {
// initialize objects
Local.reader = createObject("java", "com.lowagie.text.pdf.PdfReader").init( arguments.source );
Local.pdfName = createObject("java", "com.lowagie.text.pdf.PdfName");
Local.annot = createObject("java", "com.lowagie.text.pdf.PdfAnnotation");
Local.out = createObject("java", "java.io.FileOutputStream").init( arguments.destination );
Local.stamper = createObject("java", "com.lowagie.text.pdf.PdfStamper").init(Local.reader, Local.out);
Local.PdfAction = createObject("java", "com.lowagie.text.pdf.PdfAction");
Local.PdfRect = createObject("java", "com.lowagie.text.Rectangle");
Local.PdfBorderArray = createObject("java", "com.lowagie.text.pdf.PdfBorderArray").init(javacast("float", "0"), javacast("float", "0"), javacast("float", "0"));
Local.newAnnots = [];
// check each page for hyperlinks
// Save the data to a structure then write it to an array
// then delete the hyperlink Annotation
for ( Local.i = 1; Local.i <= Local.reader.getNumberOfPages(); Local.i = Local.i + 1) {
//Get all of the annotations for the current page
Local.page = Local.reader.getPageN( Local.i );
Local.annotations = Local.page.getAsArray( Local.PdfName.ANNOTS ).getArrayList();
// search annotations for links
for (Local.x = arrayLen(Local.annotations); !isNull( Local.annotations) && Local.x > 0; Local.x--) {
// get current properties
Local.current = Local.annotations[ Local.x ];
Local.dictionary = Local.reader.getPdfObject( Local.current );
Local.subType = Local.dictionary.get( Local.PdfName.SUBTYPE );
Local.action = Local.dictionary.get( Local.PdfName.A );
Local.hasLink = true;
//Skip this item if it does not have a link AND action
if (Local.subType != Local.PdfName.LINK || isNull(Local.action)) {
Local.hasLink = false;
}
//Skip this item if it does not have a URI
if ( Local.hasLink && Local.action.get( Local.PdfName.S ) != Local.PdfName.URI ) {
Local.hasLink = false;
}
//If it is a valid URI, update link
if (Local.hasLink) {
// extract file name from URL
Local.oldLink = Local.action.get( Local.pdfName.URI );
Local.newLink = getFileFromPath( Local.oldLink );
Local.Rect = Local.dictionary.Get(PdfName.Rect);
arrayStruct = StructNew();
arrayStruct.rectSTR = Local.Rect.toString();
arrayStruct.link = Local.newLink;
arrayStruct.page = Local.i;
ArrayAppend(Local.newAnnots, arrayStruct);
// Delete
Local.annotations.remove(Local.current);
}
}
}
// Now really remove them!
Local.reader.RemoveUnusedObjects();
// Now loop over the saved annotations and put them back!!
for ( Local.z = 1; Local.z <= ArrayLen(Local.newAnnots); Local.z++) {
// Parse the rect we got save into an Array
theRectArray = ListToArray(ReplaceNoCase(ReplaceNoCase(Local.newAnnots[z].rectSTR, "[", ""), "]", ""));
// Create the GoToR action
theAction = Local.PdfAction.gotoRemotePage(javacast("string", '#Local.newAnnots[z].link#'), javacast("string", '#Local.newAnnots[z].link#'), javacast("boolean", "false"), javacast("boolean", "false"));
// Create the Link Annotation with the above Action and the Rect
theAnnot = Local.annot.createLink(Local.stamper.getWriter(), Local.PdfRect.init(javacast("int", theRectArray[1]), javacast("int", theRectArray[2]), javacast("int", theRectArray[3]), javacast("int", theRectArray[4])), Local.annot.HIGHLIGHT_INVERT, theAction);
// Remove the border the underlying underlined text will flag item as a link
theAnnot.setBorder(Local.PdfBorderArray);
// Add the Annotation to the Page
Local.stamper.addAnnotation(theAnnot, Local.newAnnots[z].page);
}
}
finally {
// cleanup
if (structKeyExists(Local, "reader")) { Local.reader.close(); }
if (structKeyExists(Local, "stamper")) { Local.stamper.close(); }
if (structKeyExists(Local, "out")) { Local.out.close(); }
}
}
I couldn't have done this without the help of Leigh!!