56 lines
2.5 KiB
Diff
56 lines
2.5 KiB
Diff
|
From 103e1ff08c00590be56c98aa5647e92c7fa78631 Mon Sep 17 00:00:00 2001
|
||
|
|
From: Mustafa Emre Acer <meacer@chromium.org>
|
||
|
|
Date: Fri, 18 Nov 2022 22:52:00 +0000
|
||
|
|
Subject: [PATCH] IDN Spoof Checks: Disallow ZWJ and ZWNJ in ICU versions below
|
||
|
|
72
|
||
|
|
|
||
|
|
ICU 72 updates to Unicode 15 which changes the zero width joiner (ZWJ)
|
||
|
|
and zero width non-joiner (ZWNJ) characters from
|
||
|
|
Identifier_Status=Allowed to Identifier_Status=Restricted. These
|
||
|
|
characters are therefore no longer allowed by default in ICU 72.
|
||
|
|
|
||
|
|
crbug/694157 recently implemented Non-Transitional IDNA 2008 behind a
|
||
|
|
flag. ZWJ and ZWNJ are disallowed in Transitional Mode but allowed in
|
||
|
|
Non-Transitional Mode, so the test cases with the Non-Transitional Mode
|
||
|
|
enabled fail in ICU 72.
|
||
|
|
|
||
|
|
This CL removes ZWJ and ZWNJ from the allowed identifiers set for
|
||
|
|
ICU versions below 72. This effectively disables these characters even
|
||
|
|
in Non-Transitional Mode.
|
||
|
|
|
||
|
|
This is a temporary fix. Once ICU 72 is rolled out, we should check if
|
||
|
|
we can use UIDNA_CHECK_CONTEXTJ and explicitly add ZWJ and ZWNJ to
|
||
|
|
the allowed sets again.
|
||
|
|
|
||
|
|
Bug: 1386204, 694157
|
||
|
|
Change-Id: I606c43b9d94fea0f2331e5aed530f633bb94517c
|
||
|
|
Reviewed-on: https://chromium-review.googlesource.com/c/chromium/src/+/4038542
|
||
|
|
Reviewed-by: Frank Tang <ftang@chromium.org>
|
||
|
|
Commit-Queue: Mustafa Emre Acer <meacer@chromium.org>
|
||
|
|
Cr-Commit-Position: refs/heads/main@{#1073605}
|
||
|
|
---
|
||
|
|
.../spoof_checks/idn_spoof_checker.cc | 9 ++++++
|
||
|
|
.../idn_spoof_checker_unittest.cc | 28 +++++++++++--------
|
||
|
|
2 files changed, 25 insertions(+), 12 deletions(-)
|
||
|
|
|
||
|
|
diff --git a/components/url_formatter/spoof_checks/idn_spoof_checker.cc b/components/url_formatter/spoof_checks/idn_spoof_checker.cc
|
||
|
|
index aaff7c60bb918..87f62e49f487f 100644
|
||
|
|
--- a/components/url_formatter/spoof_checks/idn_spoof_checker.cc
|
||
|
|
+++ b/components/url_formatter/spoof_checks/idn_spoof_checker.cc
|
||
|
|
@@ -713,6 +713,15 @@ void IDNSpoofChecker::SetAllowedUnicodeSet(UErrorCode* status) {
|
||
|
|
allowed_set.remove(0xA640u, 0xA69Fu); // Cyrillic Extended-B
|
||
|
|
allowed_set.remove(0xA720u, 0xA7FFu); // Latin Extended-D
|
||
|
|
|
||
|
|
+#if U_ICU_VERSION_MAJOR_NUM < 72
|
||
|
|
+ // Unicode 15 changes ZWJ and ZWNJ from allowed to restricted. Restrict them
|
||
|
|
+ // in lower versions too. This only relevant in Non-Transitional Mode as
|
||
|
|
+ // Transitional Mode maps these characters out.
|
||
|
|
+ // TODO(crbug.com/1386204): Remove these after ICU 72 is rolled out.
|
||
|
|
+ allowed_set.remove(0x200Cu); // Zero Width Non-Joiner
|
||
|
|
+ allowed_set.remove(0x200Du); // Zero Width Joiner
|
||
|
|
+#endif
|
||
|
|
+
|
||
|
|
uspoof_setAllowedUnicodeSet(checker_, &allowed_set, status);
|
||
|
|
}
|
||
|
|
|