1 files changed, 23 insertions, 24 deletions

diff --git a/llvm/lib/Support/UnicodeNameToCodepoint.cpp b/llvm/lib/Support/UnicodeNameToCodepoint.cpp
index 1e8aebf1b8eb..accebf1098ab 100644
--- a/llvm/lib/Support/UnicodeNameToCodepoint.cpp
+++ b/llvm/lib/Support/UnicodeNameToCodepoint.cpp
@@ -46,7 +46,7 @@ struct Node {
     std::string S;
     // Reserve enough space for most unicode code points.
     // The chosen value represent the 99th percentile of name size as of
-    // Unicode 14.
+    // Unicode 15.0.
     S.reserve(46);
     const Node *N = this;
     while (N) {
@@ -105,7 +105,7 @@ static Node readNode(uint32_t Offset, const Node *Parent = nullptr) {
     uint8_t H = UnicodeNameToCodepointIndex[Offset++];
     N.HasSibling = H & 0x80;
     bool HasChildren = H & 0x40;
-    H &= ~0xC0;
+    H &= uint8_t(~0xC0);
     if (HasChildren) {
       N.ChildrenOffset = (H << 16);
       N.ChildrenOffset |=
@@ -251,7 +251,7 @@ constexpr const char *const HangulSyllables[][3] = {
     };
 // clang-format on
 
-// Unicode 14.0
+// Unicode 15.0
 // 3.12 Conjoining Jamo Behavior Common constants
 constexpr const char32_t SBase = 0xAC00;
 constexpr const uint32_t LCount = 19;
@@ -285,7 +285,7 @@ static std::size_t findSyllable(StringRef Name, bool Strict,
   return size_t(Len);
 }
 
-static llvm::Optional<char32_t>
+static std::optional<char32_t>
 nameToHangulCodePoint(StringRef Name, bool Strict, BufferType &Buffer) {
   Buffer.clear();
   // Hangul Syllable Decomposition
@@ -294,7 +294,7 @@ nameToHangulCodePoint(StringRef Name, bool Strict, BufferType &Buffer) {
   bool DoesStartWith = startsWith(Name, "HANGUL SYLLABLE ", Strict, Consummed,
                                   NameStart, NeedleStart);
   if (!DoesStartWith)
-    return None;
+    return std::nullopt;
   Name = Name.substr(Consummed);
   int L = -1, V = -1, T = -1;
   Name = Name.substr(findSyllable(Name, Strict, NameStart, L, 0));
@@ -314,7 +314,7 @@ nameToHangulCodePoint(StringRef Name, bool Strict, BufferType &Buffer) {
            std::uint32_t(T);
   }
   // Otherwise, it's an illegal syllable name.
-  return None;
+  return std::nullopt;
 }
 
 struct GeneratedNamesData {
@@ -323,18 +323,17 @@ struct GeneratedNamesData {
   uint32_t End;
 };
 
-// Unicode 14.0 Table 4-8. Name Derivation Rule Prefix Strings
-// This needs to be kept in sync with
-// llvm/utils/UnicodeData/UnicodeNameMappingGenerator.cpp
+// Unicode 15.0 Table 4-8. Name Derivation Rule Prefix Strings
 static const GeneratedNamesData GeneratedNamesDataTable[] = {
     {"CJK UNIFIED IDEOGRAPH-", 0x3400, 0x4DBF},
-    {"CJK UNIFIED IDEOGRAPH-", 0x4E00, 0x9FFC},
-    {"CJK UNIFIED IDEOGRAPH-", 0x20000, 0x2A6DD},
-    {"CJK UNIFIED IDEOGRAPH-", 0x2A700, 0x2B734},
+    {"CJK UNIFIED IDEOGRAPH-", 0x4E00, 0x9FFF},
+    {"CJK UNIFIED IDEOGRAPH-", 0x20000, 0x2A6DF},
+    {"CJK UNIFIED IDEOGRAPH-", 0x2A700, 0x2B739},
     {"CJK UNIFIED IDEOGRAPH-", 0x2B740, 0x2B81D},
     {"CJK UNIFIED IDEOGRAPH-", 0x2B820, 0x2CEA1},
     {"CJK UNIFIED IDEOGRAPH-", 0x2CEB0, 0x2EBE0},
     {"CJK UNIFIED IDEOGRAPH-", 0x30000, 0x3134A},
+    {"CJK UNIFIED IDEOGRAPH-", 0x31350, 0x323AF},
     {"TANGUT IDEOGRAPH-", 0x17000, 0x187F7},
     {"TANGUT IDEOGRAPH-", 0x18D00, 0x18D08},
     {"KHITAN SMALL SCRIPT CHARACTER-", 0x18B00, 0x18CD5},
@@ -344,7 +343,7 @@ static const GeneratedNamesData GeneratedNamesDataTable[] = {
     {"CJK COMPATIBILITY IDEOGRAPH-", 0x2F800, 0x2FA1D},
 };
 
-static llvm::Optional<char32_t>
+static std::optional<char32_t>
 nameToGeneratedCodePoint(StringRef Name, bool Strict, BufferType &Buffer) {
   for (auto &&Item : GeneratedNamesDataTable) {
     Buffer.clear();
@@ -368,15 +367,15 @@ nameToGeneratedCodePoint(StringRef Name, bool Strict, BufferType &Buffer) {
     }
     return V;
   }
-  return None;
+  return std::nullopt;
 }
 
-static llvm::Optional<char32_t> nameToCodepoint(StringRef Name, bool Strict,
-                                                BufferType &Buffer) {
+static std::optional<char32_t> nameToCodepoint(StringRef Name, bool Strict,
+                                               BufferType &Buffer) {
   if (Name.empty())
-    return None;
+    return std::nullopt;
 
-  llvm::Optional<char32_t> Res = nameToHangulCodePoint(Name, Strict, Buffer);
+  std::optional<char32_t> Res = nameToHangulCodePoint(Name, Strict, Buffer);
   if (!Res)
     Res = nameToGeneratedCodePoint(Name, Strict, Buffer);
   if (Res)
@@ -398,22 +397,22 @@ static llvm::Optional<char32_t> nameToCodepoint(StringRef Name, bool Strict,
     }
     return Value;
   }
-  return None;
+  return std::nullopt;
 }
 
-llvm::Optional<char32_t> nameToCodepointStrict(StringRef Name) {
+std::optional<char32_t> nameToCodepointStrict(StringRef Name) {
 
   BufferType Buffer;
   auto Opt = nameToCodepoint(Name, true, Buffer);
   return Opt;
 }
 
-llvm::Optional<LooseMatchingResult>
+std::optional<LooseMatchingResult>
 nameToCodepointLooseMatching(StringRef Name) {
   BufferType Buffer;
   auto Opt = nameToCodepoint(Name, false, Buffer);
   if (!Opt)
-    return None;
+    return std::nullopt;
   return LooseMatchingResult{*Opt, Buffer};
 }
 
@@ -445,8 +444,8 @@ nearestMatchesForCodepointName(StringRef Pattern, std::size_t MaxMatchesCount) {
       return Name;
     };
 
-    auto It = std::lower_bound(
-        Matches.begin(), Matches.end(), Distance,
+    auto It = llvm::lower_bound(
+        Matches, Distance,
         [&](const MatchForCodepointName &a, std::size_t Distance) {
           if (Distance == a.Distance)
             return a.Name < GetName();