fix date parsing w/ ICU 72 (FS#76773)

author: Evangelos Foutras 2022-12-08 01:21:42 +0000
committer: Evangelos Foutras 2022-12-08 01:21:42 +0000
commit: a90c5ad1c9c0b947d86223d6f9fb30f6cf897c19 (patch)
tree: 54aa1c73538cbdd5f24a3223e5fc8ee84e96d7d3
parent: 282fc828039433e0d1d41e1f749851cc2118fddd (diff)
download: aur-a90c5ad1c9c0b947d86223d6f9fb30f6cf897c19.tar.gz
3 files changed, 179 insertions, 1 deletions
diff --git a/PKGBUILD b/PKGBUILD
index 871a7d4ff2f5..8e06338beb18 100644
--- a/PKGBUILD
+++ b/PKGBUILD
@@ -5,7 +5,7 @@
 
 pkgname=chromium
 pkgver=108.0.5359.98
-pkgrel=1
+pkgrel=2
 _launcher_ver=8
 _gcc_patchset=2
 pkgdesc="A web browser built for speed, simplicity, and security"
@@ -26,6 +26,8 @@ source=(https://commondatastorage.googleapis.com/chromium-browser-official/chrom
         https://github.com/foutrelis/chromium-launcher/archive/v$_launcher_ver/chromium-launcher-$_launcher_ver.tar.gz
         https://github.com/stha09/chromium-patches/releases/download/chromium-${pkgver%%.*}-patchset-$_gcc_patchset/chromium-${pkgver%%.*}-patchset-$_gcc_patchset.tar.xz
         re-fix-TFLite-build-error-on-linux-with-system-zlib.patch
+        chromium-icu72.patch
+        v8-enhance-Date-parser-to-take-Unicode-SPACE.patch
         REVERT-roll-src-third_party-ffmpeg-m102.patch
         REVERT-roll-src-third_party-ffmpeg-m106.patch
         disable-GlobalMediaControlsCastStartStop.patch
@@ -35,6 +37,8 @@ sha256sums=('60b6137971e3cb2947477f654491ed4f517ab88ea2807fa3b89fcce34b83561e'
             '213e50f48b67feb4441078d50b0fd431df34323be15be97c55302d3fdac4483a'
             '40ef8af65e78901bb8554eddbbb5ebc55c0b8e7927f6ca51b2a353d1c7c50652'
             '9015b9d6d5b4c1e7248d6477a4b4b6bd6a3ebdc57225d2d8efcd79fc61790716'
+            'dabb5ab204b63be73d3c5c8b7c1fa74053105a285852ba3bbc4fb77646608572'
+            'b83406a881d66627757d9cbc05e345cbb2bd395a48b6d4c970e5e1cb3f6ed454'
             '30df59a9e2d95dcb720357ec4a83d9be51e59cc5551365da4c0073e68ccdec44'
             '4c12d31d020799d31355faa7d1fe2a5a807f7458e7f0c374adf55edb37032152'
             '7f3b1b22d6a271431c1f9fc92b6eb49c6d80b8b3f868bdee07a6a1a16630a302'
@@ -102,6 +106,8 @@ prepare() {
 
   # Upstream fixes
   patch -Np1 -i ../re-fix-TFLite-build-error-on-linux-with-system-zlib.patch
+  patch -Np1 -i ../chromium-icu72.patch
+  patch -Np1 -d v8 <../v8-enhance-Date-parser-to-take-Unicode-SPACE.patch
 
   # Revert ffmpeg roll requiring new channel layout API support
   # https://crbug.com/1325301
diff --git a/chromium-icu72.patch b/chromium-icu72.patch
new file mode 100644
index 000000000000..b8ebcd3b7d59
--- /dev/null
+++ b/chromium-icu72.patch
@@ -0,0 +1,114 @@
+From 2c4d3c61aa33f3169e7923ea3433c71e3df0952f Mon Sep 17 00:00:00 2001
+From: Frank Tang <ftang@chromium.org>
+Date: Mon, 7 Nov 2022 22:08:05 +0000
+Subject: [PATCH 1/2] Prepare for ICU72 landing
+
+The date format may output U+202F Narrow SPACE between time
+and AM/PM. So switch to use UTF8 and not restrict to ASCII which
+will break when the output is not only ASCII.
+
+Bug: 1371208
+Change-Id: I05f9daadfba5c45d618f15ae23340da373f2f36a
+Reviewed-on: https://chromium-review.googlesource.com/c/chromium/src/+/4007076
+Reviewed-by: Daniel Rubery <drubery@chromium.org>
+Commit-Queue: Frank Tang <ftang@chromium.org>
+Cr-Commit-Position: refs/heads/main@{#1068343}
+
+(cherry picked from commit ce2ffed84b95e2b7c068d6f066d86cd034212425)
+---
+ .../safe_browsing/content/browser/web_ui/safe_browsing_ui.cc    | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+diff --git a/components/safe_browsing/content/browser/web_ui/safe_browsing_ui.cc b/components/safe_browsing/content/browser/web_ui/safe_browsing_ui.cc
+index 92597a9d3a4..e6e7514a082 100644
+--- a/components/safe_browsing/content/browser/web_ui/safe_browsing_ui.cc
++++ b/components/safe_browsing/content/browser/web_ui/safe_browsing_ui.cc
+@@ -457,7 +457,7 @@ namespace {
+ std::string UserReadableTimeFromMillisSinceEpoch(int64_t time_in_milliseconds) {
+   base::Time time =
+       base::Time::UnixEpoch() + base::Milliseconds(time_in_milliseconds);
+-  return base::UTF16ToASCII(base::TimeFormatShortDateAndTime(time));
++  return base::UTF16ToUTF8(base::TimeFormatShortDateAndTime(time));
+ }
+ 
+ void AddStoreInfo(const DatabaseManagerInfo::DatabaseInfo::StoreInfo store_info,
+
+From 8ba9d96da703978655cddf07d58b0a15f0a43a10 Mon Sep 17 00:00:00 2001
+From: Frank Tang <ftang@chromium.org>
+Date: Tue, 8 Nov 2022 00:13:16 +0000
+Subject: [PATCH 2/2] Prepare the landing of ICU72/Unicode 15
+
+See
+https://www.unicode.org/emoji/charts-15.0/emoji-released.html
+https://www.unicode.org/charts/PDF/U1F680.pdf
+https://www.unicode.org/charts/PDF/U1FA70.pdf
+for the newly added emoji to
+Transport and Map Symbols
+Symbols and Pictographs Extended-A blocks.
+
+Update the kIsCJKIdeographOrSymbolRanges to Unicode 15
+Needed to avoid test breakage of
+CharacterTest.HammerEmojiVsCJKIdeographOrSymbol
+
+Bug: 1371208
+Change-Id: Ic7b319ba18f3aded46b252d8b484e3b1bc43eff4
+Reviewed-on: https://chromium-review.googlesource.com/c/chromium/src/+/4007098
+Reviewed-by: Stephen Chenney <schenney@chromium.org>
+Commit-Queue: Frank Tang <ftang@chromium.org>
+Cr-Commit-Position: refs/heads/main@{#1068422}
+
+(cherry picked from commit d93a774bf6fac8ddaaa1041ea6ad2dd8e5ff4539)
+---
+ .../platform/text/character_property_data.h   | 24 +++++++++----------
+ 1 file changed, 12 insertions(+), 12 deletions(-)
+
+diff --git a/third_party/blink/renderer/platform/text/character_property_data.h b/third_party/blink/renderer/platform/text/character_property_data.h
+index 9005c20a379..ee690563c28 100644
+--- a/third_party/blink/renderer/platform/text/character_property_data.h
++++ b/third_party/blink/renderer/platform/text/character_property_data.h
+@@ -107,7 +107,7 @@ static const UChar32 kIsCJKIdeographOrSymbolRanges[] = {
+     0x1F3FB, 0x1F3FF,
+ 
+     // Transport
+-    0x1F6DD, 0x1F6DF,
++    0x1F6DC, 0x1F6DF,
+ 
+     // Colored circles and squares for use with emoji.
+     0x1F7E0, 0x1F7EB,
+@@ -118,25 +118,25 @@ static const UChar32 kIsCJKIdeographOrSymbolRanges[] = {
+     0x1F900, 0x1F90F,
+     // ZIPPER-MOUTH FACE...SIGN OF THE HORNS
+     0x1F910, 0x1F918, 0x1F919, 0x1F97F, 0x1F980, 0x1F9BF, 0x1F9C0, 0x1F9FF,
+-    // Clothing
+-    0x1FA70, 0x1FA74,
+-    // Medical symbols
+-    0x1FA78, 0x1FA7C,
++    // Clothing, heart and Medical symbols
++    0x1FA70, 0x1FA7C,
+     // Toys and sport symbols
+-    0x1FA80, 0x1FA86,
++    0x1FA80, 0x1FA88,
+     // Miscellaneous objects
+-    0x1FA90, 0x1FAAC,
+     // Animals and nature
+-    0x1FAB0, 0x1FABA,
++    0x1FA90, 0x1FABD,
++    // Animal
+     // Body parts
+     // People
+-    0x1FAC0, 0x1FAC5,
++    0x1FABF, 0x1FAC5,
++    // animal-mammal
++    0x1FACE, 0x1FACF,
+     // Food and drink
+-    0x1FAD0, 0x1FAD9,
++    0x1FAD0, 0x1FADB,
+     // Face
+-    0x1FAE0, 0x1FAE7,
++    0x1FAE0, 0x1FAE8,
+     // Hand
+-    0x1FAF0, 0x1FAF6,
++    0x1FAF0, 0x1FAF8,
+     };
+ 
+ // https://html.spec.whatwg.org/C/#prod-potentialcustomelementname
diff --git a/v8-enhance-Date-parser-to-take-Unicode-SPACE.patch b/v8-enhance-Date-parser-to-take-Unicode-SPACE.patch
new file mode 100644
index 000000000000..7458834083df
--- /dev/null
+++ b/v8-enhance-Date-parser-to-take-Unicode-SPACE.patch
@@ -0,0 +1,58 @@
+From 81dd64c3705f89653859a5d0001dd0ca983a92e2 Mon Sep 17 00:00:00 2001
+From: Frank Tang <ftang@chromium.org>
+Date: Wed, 16 Nov 2022 09:18:45 -0800
+Subject: [PATCH] [intl] Enhance Date parser to take Unicode SPACE
+
+This is needed to prepare for the landing of ICU72.
+Allow U+202F in the Date String, which the toLocaleString("en-US")
+will generate w/ ICU72.
+
+Bug: v8:13494
+Change-Id: I41b83c4094ce3d0737a72dcd6310b52c68fdcdca
+Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/4027341
+Reviewed-by: Yang Guo <yangguo@chromium.org>
+Reviewed-by: Jungshik Shin <jshin@chromium.org>
+Commit-Queue: Frank Tang <ftang@chromium.org>
+Cr-Commit-Position: refs/heads/main@{#84308}
+
+(cherry picked from commit 2ada52cffbff11074abfaac18938bf02d85454f5)
+---
+ src/date/dateparser-inl.h | 2 +-
+ src/date/dateparser.h     | 4 +++-
+ 2 files changed, 4 insertions(+), 2 deletions(-)
+
+diff --git a/src/date/dateparser-inl.h b/src/date/dateparser-inl.h
+index 623986d2b1..b45479dc51 100644
+--- a/src/date/dateparser-inl.h
++++ b/src/date/dateparser-inl.h
+@@ -192,7 +192,7 @@ DateParser::DateToken DateParser::DateStringTokenizer<CharType>::Scan() {
+   if (in_->Skip('+')) return DateToken::Symbol('+');
+   if (in_->Skip('.')) return DateToken::Symbol('.');
+   if (in_->Skip(')')) return DateToken::Symbol(')');
+-  if (in_->IsAsciiAlphaOrAbove()) {
++  if (in_->IsAsciiAlphaOrAbove() && !in_->IsWhiteSpaceChar()) {
+     DCHECK_EQ(KeywordTable::kPrefixLength, 3);
+     uint32_t buffer[3] = {0, 0, 0};
+     int length = in_->ReadWord(buffer, 3);
+diff --git a/src/date/dateparser.h b/src/date/dateparser.h
+index 1a0a0b15ab..59b2f3c9fd 100644
+--- a/src/date/dateparser.h
++++ b/src/date/dateparser.h
+@@ -91,7 +91,8 @@ class DateParser : public AllStatic {
+     // Return word length.
+     int ReadWord(uint32_t* prefix, int prefix_size) {
+       int len;
+-      for (len = 0; IsAsciiAlphaOrAbove(); Next(), len++) {
++      for (len = 0; IsAsciiAlphaOrAbove() && !IsWhiteSpaceChar();
++           Next(), len++) {
+         if (len < prefix_size) prefix[len] = AsciiAlphaToLower(ch_);
+       }
+       for (int i = len; i < prefix_size; i++) prefix[i] = 0;
+@@ -115,6 +116,7 @@ class DateParser : public AllStatic {
+     bool IsEnd() const { return ch_ == 0; }
+     bool IsAsciiDigit() const { return IsDecimalDigit(ch_); }
+     bool IsAsciiAlphaOrAbove() const { return ch_ >= 'A'; }
++    bool IsWhiteSpaceChar() const { return IsWhiteSpace(ch_); }
+     bool IsAsciiSign() const { return ch_ == '+' || ch_ == '-'; }
+ 
+     // Return 1 for '+' and -1 for '-'.
author	Evangelos Foutras	2022-12-08 01:21:42 +0000
committer	Evangelos Foutras	2022-12-08 01:21:42 +0000
commit	a90c5ad1c9c0b947d86223d6f9fb30f6cf897c19 (patch)
tree	54aa1c73538cbdd5f24a3223e5fc8ee84e96d7d3
parent	282fc828039433e0d1d41e1f749851cc2118fddd (diff)
download	aur-a90c5ad1c9c0b947d86223d6f9fb30f6cf897c19.tar.gz