mirrors/pdf.js
1
0
Fork 0
mirror of https://github.com/mozilla/pdf.js.git synced 2025-04-26 10:08:06 +02:00
Code Activity

Decode XML metadata as UTF-8

Browse source 
XML uses UTF-8 by default, which needs to be decoded to a Javascript
String prior to feeding it to the DOMParser.
In an ideal world, the XML would actually be analyzed and the specified
charset would be used, however that does not seem feasible unless JS
engines get iconv bindings.

Fixes GH-1692
This commit is contained in:
Nils Maier 2012-05-27 22:49:28 +02:00
parent e9632120c4
commit 40b9be137f
2 changed files with 10 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

7
src/obj.js
View file

@ -140,7 +140,12 @@ var Catalog = (function CatalogClosure() {
if (isName(type) && isName(subtype) &&
type.name === 'Metadata' && subtype.name === 'XML') {
metadata = stringToPDFString(bytesToString(stream.getBytes()));
// XXX: This should examine the charset the XML document defines,
// however since there are currently no real means to decode
// arbitrary charsets, let's just hope that the author of the PDF
// was reasonable enough to stick with the XML default charset,
// which is UTF-8.
metadata = stringToUTF8String(bytesToString(stream.getBytes()));
}
}