mirrors/pdf.js
1
0
Fork 0
mirror of https://github.com/mozilla/pdf.js.git synced 2025-04-23 08:38:06 +02:00
Code Activity

Improve fingerprinting of documents

Browse source 
Fixes two issues:
- #4456 : The first 100 bytes are often not unique as they can be
filled with standard PDF headers - so we use the first 200 KB instead.
(This may be overkill)
- Some documents we encountered have invalid xref ids, which were
always coming out as ‘0000000000000000’ - so we detect that and use the
MD5 instead.
This commit is contained in:
Jordan Thoms 2014-08-03 01:19:55 +12:00
parent 20bf84ac54
commit aa53319c87
1 changed files with 14 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

17
src/core/core.js
View file

@ -280,6 +280,10 @@ var Page = (function PageClosure() {
* `PDFDocument` objects on the main thread created.
*/
var PDFDocument = (function PDFDocumentClosure() {
var FINGERPRINT_FIRST_BYTES = 1024;
var EMPTY_FINGERPRINT = '\x00\x00\x00\x00\x00\x00\x00' +
'\x00\x00\x00\x00\x00\x00\x00\x00\x00';
function PDFDocument(pdfManager, arg, password) {
if (isStream(arg)) {
init.call(this, pdfManager, arg, password);
@ -493,14 +497,21 @@ var PDFDocument = (function PDFDocumentClosure() {
get fingerprint() {
var xref = this.xref, hash, fileID = '';
if (xref.trailer.has('ID')) {
if (xref.trailer.has('ID') &&
xref.trailer.get('ID')[0] !== EMPTY_FINGERPRINT) {
hash = stringToBytes(xref.trailer.get('ID')[0]);
} else {
hash = calculateMD5(this.stream.bytes.subarray(0, 100), 0, 100);
if (this.stream.ensureRange) {
this.stream.ensureRange(0,
Math.min(FINGERPRINT_FIRST_BYTES, this.stream.end));
}
hash = calculateMD5(this.stream.bytes.subarray(0,
FINGERPRINT_FIRST_BYTES), 0, FINGERPRINT_FIRST_BYTES);
}
for (var i = 0, n = hash.length; i < n; i++) {
fileID += hash[i].toString(16);
var hex = hash[i].toString(16);
fileID += hex.length === 1 ? '0' + hex : hex;
}
return shadow(this, 'fingerprint', fileID);