Sakurai/pdf.js
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Use stringToPDFString to sanitizing bad "Prefix" entries in Page Label dictionaries

Browse Source 
It seems that certain bad PDF generators can create badly encoded "Prefix" entries for Page Labels, one example being http://ukjewishfilm.org/wp-content/uploads/2015/09/Jewish-Film-Festival-Programme-ONLINE.pdf.

Unfortunately I didn't come across such a PDF file while adding the API support for Page Labels, but with them now being used in the viewer I just found this issue. With this patch, we now display the Page Labels in the same way as Adobe Reader.
This commit is contained in:
Jonas Jenwald 2016-11-03 19:48:08 +01:00
parent 9f8d67475e
commit 2d8d8b5e53
4 changed files with 15 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
src/core/obj.js
View File

@ -302,8 +302,9 @@ var Catalog = (function CatalogClosure() {
assert(!s || isName(s), 'Invalid style in PageLabel dictionary.');
style = (s ? s.name : null);
prefix = labelDict.get('P') || '';
assert(isString(prefix), 'Invalid prefix in PageLabel dictionary.');
var p = labelDict.get('P') || '';
assert(isString(p), 'Invalid prefix in PageLabel dictionary.');
prefix = stringToPDFString(p);
start = labelDict.get('St') || 1;
assert(isInt(start), 'Invalid start in PageLabel dictionary.');

1
test/pdfs/.gitignore vendored
View File

@ -40,6 +40,7 @@
!issue7544.pdf
!issue7598.pdf
!issue7665.pdf
!bad-PageLabels.pdf
!filled-background.pdf
!ArabicCIDTrueType.pdf
!ThuluthFeatures.pdf

BIN
test/pdfs/bad-PageLabels.pdf Normal file
View File

Binary file not shown.

12
test/unit/api_spec.js
View File

@ -503,14 +503,24 @@ describe('api', function() {
return pdfDoc.getPageLabels();
});
Promise.all([promise0, promise1, promise2]).then(function (pageLabels) {
// PageLabels with bad "Prefix" entries.
var url3 = new URL('../pdfs/bad-PageLabels.pdf', window.location).href;
var loadingTask3 = new PDFJS.getDocument(url3);
var promise3 = loadingTask3.promise.then(function (pdfDoc) {
return pdfDoc.getPageLabels();
});
Promise.all([promise0, promise1, promise2, promise3]).then(
function (pageLabels) {
expect(pageLabels[0]).toEqual(['i', 'ii', 'iii', '1']);
expect(pageLabels[1]).toEqual(['Front Page1']);
expect(pageLabels[2]).toEqual(['1', '2']);
expect(pageLabels[3]).toEqual(['X1']);
loadingTask0.destroy();
loadingTask1.destroy();
loadingTask2.destroy();
loadingTask3.destroy();
done();
}).catch(function (reason) {
done.fail(reason);