69 lines
3.1 KiB
Diff
69 lines
3.1 KiB
Diff
|
From e58fa0ba66272c5f28828b15d06c7e42a9882b3b Mon Sep 17 00:00:00 2001
|
|||
|
|
From: Jungshik Shin <jshin@chromium.org>
|
|||
|
|
Date: Sat, 16 Dec 2017 04:19:27 +0000
|
|||
|
|
Subject: [PATCH] Use fromUTF8() for UnicodeString construction from UTF-8
|
|||
|
|
|
|||
|
|
Chrome's copy of ICU is built with U_CHARSET_IS_UTF8=1 so that |char *|
|
|||
|
|
buffer is treated as UTF-8 when constructing UnicodeString() regardless
|
|||
|
|
of the default encoding of the current locale on Linux or non-Unicode code
|
|||
|
|
page on Windows.
|
|||
|
|
|
|||
|
|
However, some Linux distros do not set U_CHARSET_IS_UTF=1 when building
|
|||
|
|
ICU and Chromium build with system_icu crashes when Chromium is run in
|
|||
|
|
non-UTF-8 locale (e.g. 'C').
|
|||
|
|
|
|||
|
|
To make Chromium work in a non-UTF-8 locale (which is pretty rare these
|
|||
|
|
days), use 'icu::UnicodeString::fromUTF8(StringPiece)' instead of
|
|||
|
|
'icu::UnicodeString(const char*)'.
|
|||
|
|
|
|||
|
|
Bug: 772655
|
|||
|
|
Test: components_unittests --gtest_filter=*IDN*
|
|||
|
|
Test: Chromium built with system_icu does not crash in C locale.
|
|||
|
|
Change-Id: I0daa284ec06b8e83814fc70eb8e9e5c96444ebfa
|
|||
|
|
Reviewed-on: https://chromium-review.googlesource.com/831247
|
|||
|
|
Reviewed-by: Peter Kasting <pkasting@chromium.org>
|
|||
|
|
Commit-Queue: Jungshik Shin <jshin@chromium.org>
|
|||
|
|
Cr-Commit-Position: refs/heads/master@{#524586}
|
|||
|
|
---
|
|||
|
|
components/url_formatter/idn_spoof_checker.cc | 10 +++++-----
|
|||
|
|
1 file changed, 5 insertions(+), 5 deletions(-)
|
|||
|
|
|
|||
|
|
diff --git a/components/url_formatter/idn_spoof_checker.cc b/components/url_formatter/idn_spoof_checker.cc
|
|||
|
|
index a88c5e8f8331..aee748d8a4d5 100644
|
|||
|
|
--- a/components/url_formatter/idn_spoof_checker.cc
|
|||
|
|
+++ b/components/url_formatter/idn_spoof_checker.cc
|
|||
|
|
@@ -110,8 +110,8 @@ IDNSpoofChecker::IDNSpoofChecker() {
|
|||
|
|
|
|||
|
|
// These Cyrillic letters look like Latin. A domain label entirely made of
|
|||
|
|
// these letters is blocked as a simplified whole-script-spoofable.
|
|||
|
|
- cyrillic_letters_latin_alike_ =
|
|||
|
|
- icu::UnicodeSet(icu::UnicodeString("[асԁеһіјӏорԛѕԝхуъЬҽпгѵѡ]"), status);
|
|||
|
|
+ cyrillic_letters_latin_alike_ = icu::UnicodeSet(
|
|||
|
|
+ icu::UnicodeString::fromUTF8("[асԁеһіјӏорԛѕԝхуъЬҽпгѵѡ]"), status);
|
|||
|
|
cyrillic_letters_latin_alike_.freeze();
|
|||
|
|
|
|||
|
|
cyrillic_letters_ =
|
|||
|
|
@@ -141,8 +141,8 @@ IDNSpoofChecker::IDNSpoofChecker() {
|
|||
|
|
UParseError parse_error;
|
|||
|
|
diacritic_remover_.reset(icu::Transliterator::createFromRules(
|
|||
|
|
UNICODE_STRING_SIMPLE("DropAcc"),
|
|||
|
|
- icu::UnicodeString("::NFD; ::[:Nonspacing Mark:] Remove; ::NFC;"
|
|||
|
|
- " ł > l; ø > o; đ > d;"),
|
|||
|
|
+ icu::UnicodeString::fromUTF8("::NFD; ::[:Nonspacing Mark:] Remove; ::NFC;"
|
|||
|
|
+ " ł > l; ø > o; đ > d;"),
|
|||
|
|
UTRANS_FORWARD, parse_error, status));
|
|||
|
|
|
|||
|
|
// Supplement the Unicode confusable list by the following mapping.
|
|||
|
|
@@ -158,7 +158,7 @@ IDNSpoofChecker::IDNSpoofChecker() {
|
|||
|
|
// - U+0D1F (ട) => s
|
|||
|
|
extra_confusable_mapper_.reset(icu::Transliterator::createFromRules(
|
|||
|
|
UNICODE_STRING_SIMPLE("ExtraConf"),
|
|||
|
|
- icu::UnicodeString(
|
|||
|
|
+ icu::UnicodeString::fromUTF8(
|
|||
|
|
"ӏ > l; [кĸκ] > k; п > n; [ƅь] > b; в > b; м > m; н > h; "
|
|||
|
|
"т > t; [шщ] > w; ട > s;"),
|
|||
|
|
UTRANS_FORWARD, parse_error, status));
|
|||
|
|
--
|
|||
|
|
2.15.1
|
|||
|
|
|