mirror of
https://github.com/mozilla/pdf.js.git
synced 2025-04-22 16:18:08 +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
|
@ -95,24 +95,28 @@ class Page {
|
|||
this._getInheritableProperty('Resources') || Dict.empty);
|
||||
}
|
||||
|
||||
get mediaBox() {
|
||||
const mediaBox = this._getInheritableProperty('MediaBox',
|
||||
/* getArray = */ true);
|
||||
// Reset invalid media box to letter size.
|
||||
if (!Array.isArray(mediaBox) || mediaBox.length !== 4) {
|
||||
return shadow(this, 'mediaBox', LETTER_SIZE_MEDIABOX);
|
||||
_getBoundingBox(name) {
|
||||
const box = this._getInheritableProperty(name, /* getArray = */ true);
|
||||
|
||||
if (Array.isArray(box) && box.length === 4) {
|
||||
if ((box[2] - box[0]) !== 0 && (box[3] - box[1]) !== 0) {
|
||||
return box;
|
||||
}
|
||||
warn(`Empty /${name} entry.`);
|
||||
}
|
||||
return shadow(this, 'mediaBox', mediaBox);
|
||||
return null;
|
||||
}
|
||||
|
||||
get mediaBox() {
|
||||
// Reset invalid media box to letter size.
|
||||
return shadow(this, 'mediaBox',
|
||||
this._getBoundingBox('MediaBox') || LETTER_SIZE_MEDIABOX);
|
||||
}
|
||||
|
||||
get cropBox() {
|
||||
const cropBox = this._getInheritableProperty('CropBox',
|
||||
/* getArray = */ true);
|
||||
// Reset invalid crop box to media box.
|
||||
if (!Array.isArray(cropBox) || cropBox.length !== 4) {
|
||||
return shadow(this, 'cropBox', this.mediaBox);
|
||||
}
|
||||
return shadow(this, 'cropBox', cropBox);
|
||||
return shadow(this, 'cropBox',
|
||||
this._getBoundingBox('CropBox') || this.mediaBox);
|
||||
}
|
||||
|
||||
get userUnit() {
|
||||
|
@ -129,12 +133,18 @@ class Page {
|
|||
// extend beyond the boundaries of the media box. If they do, they are
|
||||
// effectively reduced to their intersection with the media box."
|
||||
const { cropBox, mediaBox, } = this;
|
||||
let view;
|
||||
if (cropBox === mediaBox || isArrayEqual(cropBox, mediaBox)) {
|
||||
return shadow(this, 'view', mediaBox);
|
||||
view = mediaBox;
|
||||
} else {
|
||||
const box = Util.intersect(cropBox, mediaBox, /* skipEmpty = */ true);
|
||||
if (box) {
|
||||
view = box;
|
||||
} else {
|
||||
warn('Empty /CropBox and /MediaBox intersection.');
|
||||
}
|
||||
}
|
||||
|
||||
const intersection = Util.intersect(cropBox, mediaBox);
|
||||
return shadow(this, 'view', intersection || mediaBox);
|
||||
return shadow(this, 'view', view || mediaBox);
|
||||
}
|
||||
|
||||
get rotate() {
|
||||
|
|
|
@ -748,7 +748,7 @@ var Util = (function UtilClosure() {
|
|||
// Returns a rectangle [x1, y1, x2, y2] corresponding to the
|
||||
// intersection of rect1 and rect2. If no intersection, returns 'false'
|
||||
// The rectangle coordinates of rect1, rect2 should be [x1, y1, x2, y2]
|
||||
Util.intersect = function Util_intersect(rect1, rect2) {
|
||||
Util.intersect = function Util_intersect(rect1, rect2, skipEmpty = false) {
|
||||
function compare(a, b) {
|
||||
return a - b;
|
||||
}
|
||||
|
@ -768,7 +768,7 @@ var Util = (function UtilClosure() {
|
|||
result[0] = orderedX[1];
|
||||
result[2] = orderedX[2];
|
||||
} else {
|
||||
return false;
|
||||
return null;
|
||||
}
|
||||
|
||||
// Y: first and second points belong to different rectangles?
|
||||
|
@ -778,9 +778,13 @@ var Util = (function UtilClosure() {
|
|||
result[1] = orderedY[1];
|
||||
result[3] = orderedY[2];
|
||||
} else {
|
||||
return false;
|
||||
return null;
|
||||
}
|
||||
|
||||
if (skipEmpty &&
|
||||
((result[2] - result[0]) === 0 || (result[3] - result[1]) === 0)) {
|
||||
return null;
|
||||
}
|
||||
return result;
|
||||
};
|
||||
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue