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 '-'.