Marmelator/pdf.js.mirror
1
0
Fork 0
mirror of https://github.com/mozilla/pdf.js.git synced 2026-08-04 05:17:24 +02:00
Code Issues Packages Projects Releases Wiki Activity

Bound the email parts in the autolinker regex

Browse Source 
The local part and the domain labels were unbounded, making the
search quadratic in the length of a run of characters preceding
an "@": scanning the text of a single page could take seconds.
This commit is contained in:
calixteman 2026-08-01 15:46:46 +02:00
parent 7fc7072f9c
commit b1f51818ae
No known key found for this signature in database
GPG Key ID: 0C5442631EE0691F
2 changed files with 25 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
test/unit/autolinker_spec.js
View File

@ -220,4 +220,24 @@ describe("autolinker", function () {
["john.doe@uni-cityname.tld", "mailto:john.doe@uni-cityname.tld"],
]);
});
it("should find emails with the longest parts allowed by the RFCs", function () {
const local = "a".repeat(64);
const label = "b".repeat(63);
testLinks([[`${local}@${label}.com`, `mailto:${local}@${label}.com`]]);
});
it("shouldn't find emails with parts longer than allowed by the RFCs", function () {
expect(
Autolinker.findLinks(`${"a".repeat(107)}@${"a".repeat(80)}.com`)
).toEqual([]);
});
it("should handle a long run of characters before an @ efficiently", function () {
const text = `${"a".repeat(50000)}@`;
const startTime = performance.now();
expect(Autolinker.findLinks(text)).toEqual([]);
expect(performance.now() - startTime).toBeLessThan(1000);
});
});

7
web/autolinker.js
View File

@ -136,10 +136,13 @@ class Autolinker {
static #numericTLDRegex;
static findLinks(text) {
// Regex can be tested and verified at https://regex101.com/r/rXoLiT/2.
// Regex can be tested and verified at https://regex101.com/r/riHjvK/1.
// The email parts are bounded to keep the scan linear: a local part can't
// exceed 64 characters (RFC 5321, section 4.5.3.1.1) and a domain label
// can't exceed 63 (RFC 1035, section 2.3.4).
this.#regex ??=
// eslint-disable-next-line regexp/no-super-linear-backtracking
/\b(?:https?:\/\/|mailto:|www\.)(?:[\S--[\p{P}<>]]|\/|[\S--[\[\]]]+[\S--[\p{P}<>]])+|(?=\p{L})[\S--[@\p{Ps}\p{Pe}<>]]+@([\S--[[\p{P}--\-]<>]]+(?:\.[\S--[[\p{P}--\-]<>]]+)+)/gv;
/\b(?:https?:\/\/|mailto:|www\.)(?:[\S--[\p{P}<>]]|\/|[\S--[\[\]]]+[\S--[\p{P}<>]])+|(?=\p{L})[\S--[@\p{Ps}\p{Pe}<>]]{1,64}@([\S--[[\p{P}--\-]<>]]{1,63}(?:\.[\S--[[\p{P}--\-]<>]]{1,63})+)/gv;
const [normalizedText, diffs] = normalize(text, { ignoreDashEOL: true });
const matches = normalizedText.matchAll(this.#regex);