mirror of
https://github.com/mozilla/pdf.js.git
synced 2025-04-20 15:18:08 +02:00
Fallback gracefully when encountering corrupt PDF files with empty /MediaBox and /CropBox entries
This is based on a real-world PDF file I encountered very recently[1], although I'm currently unable to recall where I saw it. Note that different PDF viewers handle these sort of errors differently, with Adobe Reader outright failing to render the attached PDF file whereas PDFium mostly handles it "correctly". The patch makes the following notable changes: - Refactor the `cropBox` and `mediaBox` getters, on the `Page`, to reduce unnecessary duplication. (This will also help in the future, if support for extracting additional page bounding boxes are added to the API.) - Ensure that the page bounding boxes, i.e. `cropBox` and `mediaBox`, are never empty to prevent issues/weirdness in the viewer. - Ensure that the `view` getter on the `Page` will never return an empty intersection of the `cropBox` and `mediaBox`. - Add an *optional* parameter to `Util.intersect`, to allow checking that the computed intersection isn't actually empty. - Change `Util.intersect` to have consistent return types, since Arrays are of type `Object` and falling back to returning a `Boolean` thus seem strange. --- [1] In that case I believe that only the `cropBox` was empty, but it seemed like a good idea to attempt to fix a bunch of related cases all at once.
This commit is contained in:
parent
aaef00ce5d
commit
d637b25e36
6 changed files with 199 additions and 21 deletions
1
test/pdfs/.gitignore
vendored
1
test/pdfs/.gitignore
vendored
|
@ -1,6 +1,7 @@
|
|||
*.pdf
|
||||
*.error
|
||||
|
||||
!boundingBox_invalid.pdf
|
||||
!tracemonkey.pdf
|
||||
!TrueType_without_cmap.pdf
|
||||
!franz.pdf
|
||||
|
|
130
test/pdfs/boundingBox_invalid.pdf
Normal file
130
test/pdfs/boundingBox_invalid.pdf
Normal file
|
@ -0,0 +1,130 @@
|
|||
%PDF-1.7
|
||||
%âãÏÓ
|
||||
1 0 obj
|
||||
<<
|
||||
/Pages 2 0 R
|
||||
/Type /Catalog
|
||||
>>
|
||||
endobj
|
||||
2 0 obj
|
||||
<<
|
||||
/Kids [3 0 R 4 0 R 5 0 R]
|
||||
/Type /Pages
|
||||
/Count 3
|
||||
>>
|
||||
endobj
|
||||
3 0 obj
|
||||
<<
|
||||
/Parent 2 0 R
|
||||
/Resources
|
||||
<<
|
||||
/Font
|
||||
<<
|
||||
/F1 6 0 R
|
||||
>>
|
||||
>>
|
||||
/MediaBox [0 0 0 0]
|
||||
/Type /Page
|
||||
/Contents 7 0 R
|
||||
>>
|
||||
endobj
|
||||
4 0 obj
|
||||
<<
|
||||
/CropBox [0 0 0 0]
|
||||
/Parent 2 0 R
|
||||
/Resources
|
||||
<<
|
||||
/Font
|
||||
<<
|
||||
/F1 6 0 R
|
||||
>>
|
||||
>>
|
||||
/MediaBox [0 0 800 600]
|
||||
/Type /Page
|
||||
/Contents 8 0 R
|
||||
>>
|
||||
endobj
|
||||
5 0 obj
|
||||
<<
|
||||
/CropBox [600 800 1000 1000]
|
||||
/Parent 2 0 R
|
||||
/Resources
|
||||
<<
|
||||
/Font
|
||||
<<
|
||||
/F1 6 0 R
|
||||
>>
|
||||
>>
|
||||
/MediaBox [0 0 600 800]
|
||||
/Type /Page
|
||||
/Contents 9 0 R
|
||||
>>
|
||||
endobj
|
||||
6 0 obj
|
||||
<<
|
||||
/BaseFont /Times-Roman
|
||||
/Subtype /Type1
|
||||
/Type /Font
|
||||
/Encoding /WinAnsiEncoding
|
||||
>>
|
||||
endobj
|
||||
7 0 obj
|
||||
<<
|
||||
/Length 48
|
||||
>>
|
||||
stream
|
||||
BT
|
||||
25 700 TD
|
||||
/F1 30 Tf
|
||||
(Empty /MediaBox) Tj
|
||||
ET
|
||||
|
||||
|
||||
endstream
|
||||
endobj
|
||||
8 0 obj
|
||||
<<
|
||||
/Length 46
|
||||
>>
|
||||
stream
|
||||
BT
|
||||
25 500 TD
|
||||
/F1 30 Tf
|
||||
(Empty /CropBox) Tj
|
||||
ET
|
||||
|
||||
endstream
|
||||
endobj
|
||||
9 0 obj
|
||||
<<
|
||||
/Length 73
|
||||
>>
|
||||
stream
|
||||
BT
|
||||
25 700 TD
|
||||
/F1 30 Tf
|
||||
(Empty /CropBox and /MediaBox intersection) Tj
|
||||
ET
|
||||
|
||||
endstream
|
||||
endobj xref
|
||||
0 10
|
||||
0000000000 65535 f
|
||||
0000000015 00000 n
|
||||
0000000066 00000 n
|
||||
0000000137 00000 n
|
||||
0000000263 00000 n
|
||||
0000000412 00000 n
|
||||
0000000571 00000 n
|
||||
0000000672 00000 n
|
||||
0000000773 00000 n
|
||||
0000000872 00000 n
|
||||
trailer
|
||||
|
||||
<<
|
||||
/Root 1 0 R
|
||||
/Size 10
|
||||
>>
|
||||
startxref
|
||||
997
|
||||
%%EOF
|
|
@ -39,6 +39,13 @@
|
|||
"lastPage": 1,
|
||||
"type": "text"
|
||||
},
|
||||
{ "id": "boundingBox_invalid",
|
||||
"file": "pdfs/boundingBox_invalid.pdf",
|
||||
"md5": "f6dfc471bf43abac00cdcf05d81cb070",
|
||||
"rounds": 1,
|
||||
"link": false,
|
||||
"type": "eq"
|
||||
},
|
||||
{ "id": "issue11016",
|
||||
"file": "pdfs/issue11016_reduced.pdf",
|
||||
"md5": "b75578bd052d2e6acdcc85b615eab6b1",
|
||||
|
|
|
@ -1065,9 +1065,35 @@ describe('api', function() {
|
|||
it('gets userUnit', function () {
|
||||
expect(page.userUnit).toEqual(1.0);
|
||||
});
|
||||
it('gets view', function () {
|
||||
|
||||
it('gets view', function() {
|
||||
expect(page.view).toEqual([0, 0, 595.28, 841.89]);
|
||||
});
|
||||
it('gets view, with empty/invalid bounding boxes', function(done) {
|
||||
const viewLoadingTask = getDocument(buildGetDocumentParams(
|
||||
'boundingBox_invalid.pdf'));
|
||||
|
||||
viewLoadingTask.promise.then((pdfDoc) => {
|
||||
const numPages = pdfDoc.numPages;
|
||||
expect(numPages).toEqual(3);
|
||||
|
||||
const viewPromises = [];
|
||||
for (let i = 0; i < numPages; i++) {
|
||||
viewPromises[i] = pdfDoc.getPage(i + 1).then((pdfPage) => {
|
||||
return pdfPage.view;
|
||||
});
|
||||
}
|
||||
|
||||
Promise.all(viewPromises).then(([page1, page2, page3]) => {
|
||||
expect(page1).toEqual([0, 0, 612, 792]);
|
||||
expect(page2).toEqual([0, 0, 800, 600]);
|
||||
expect(page3).toEqual([0, 0, 600, 800]);
|
||||
|
||||
viewLoadingTask.destroy().then(done);
|
||||
});
|
||||
}).catch(done.fail);
|
||||
});
|
||||
|
||||
it('gets viewport', function () {
|
||||
var viewport = page.getViewport({ scale: 1.5, rotation: 90, });
|
||||
expect(viewport.viewBox).toEqual(page.view);
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue