Marmelator/pdf.js.mirror
1
0
Fork 0
mirror of https://github.com/mozilla/pdf.js.git synced 2026-08-03 04:47:21 +02:00
Code Issues Packages Projects Releases Wiki Activity

Don't throw on an invalid XML character reference

Browse Source 
`String.fromCodePoint` throws on anything which isn't a code point,
so e.g. "&#xZZ;" or "�" aborted the whole parsing. Such a
reference is now kept as-is, like an unknown named entity.
This commit is contained in:
calixteman 2026-08-01 16:24:03 +02:00
parent 7fc7072f9c
commit cec8d2eed6
No known key found for this signature in database
GPG Key ID: 0C5442631EE0691F
2 changed files with 27 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
src/core/xml_parser.js
View File

@ -53,12 +53,12 @@ class XMLParserBase {
} }
_resolveEntities(s) { _resolveEntities(s) {
return s.replaceAll(XMLParserBase._entityRegex, (_, hex, dec, entity) => { return s.replaceAll(XMLParserBase._entityRegex, (all, hex, dec, entity) => {
if (hex) { if (hex || dec) {
return String.fromCodePoint(parseInt(hex, 16)); const code = hex ? parseInt(hex, 16) : parseInt(dec, 10);
} // An out-of-range or unparsable code point is kept as-is, since
if (dec) { // `String.fromCodePoint` would throw on it.
return String.fromCodePoint(parseInt(dec, 10)); return code >= 0 && code <= 0x10ffff ? String.fromCodePoint(code) : all;
} }
switch (entity) { switch (entity) {
case "lt": case "lt":

21
test/unit/xml_spec.js
View File

@ -109,6 +109,27 @@ describe("XML", function () {
}); });
}); });
describe("character references", function () {
const parseText = xml =>
new SimpleXMLParser({}).parseFromString(xml).documentElement.textContent;
it("should resolve the valid ones", function () {
expect(parseText("<a>&#65;&#x42;&#x1F602;&#0;&#x10FFFF;</a>")).toEqual(
"AB\u{1F602}\0\u{10FFFF}"
);
});
it("should keep the invalid ones as-is", function () {
// These must not throw: `String.fromCodePoint` rejects anything which
// isn't a code point.
expect(parseText("<a>&#xZZ;</a>")).toEqual("&#xZZ;");
expect(parseText("<a>&#zz;</a>")).toEqual("&#zz;");
expect(parseText("<a>&#x110000;</a>")).toEqual("&#x110000;");
expect(parseText("<a>&#1114112;</a>")).toEqual("&#1114112;");
expect(parseText("<a>&#-1;</a>")).toEqual("&#-1;");
});
});
it("should parse processing instructions", function () { it("should parse processing instructions", function () {
const xml = ` const xml = `
<a> <a>