1 files changed, 48 insertions, 11 deletions

diff --git a/contrib/llvm-project/clang/lib/Format/FormatTokenLexer.cpp b/contrib/llvm-project/clang/lib/Format/FormatTokenLexer.cpp
index 52a55ea23b5f..63949b2e26bd 100644
--- a/contrib/llvm-project/clang/lib/Format/FormatTokenLexer.cpp
+++ b/contrib/llvm-project/clang/lib/Format/FormatTokenLexer.cpp
@@ -100,6 +100,13 @@ ArrayRef<FormatToken *> FormatTokenLexer::lex() {
     if (Tokens.back()->NewlinesBefore > 0 || Tokens.back()->IsMultiline)
       FirstInLineIndex = Tokens.size() - 1;
   } while (Tokens.back()->isNot(tok::eof));
+  if (Style.InsertNewlineAtEOF) {
+    auto &TokEOF = *Tokens.back();
+    if (TokEOF.NewlinesBefore == 0) {
+      TokEOF.NewlinesBefore = 1;
+      TokEOF.OriginalColumn = 0;
+    }
+  }
   return Tokens;
 }
 
@@ -276,13 +283,44 @@ void FormatTokenLexer::tryMergePreviousTokens() {
       return;
     }
   }
-  // TableGen's Multi line string starts with [{
-  if (Style.isTableGen() && tryMergeTokens({tok::l_square, tok::l_brace},
-                                           TT_TableGenMultiLineString)) {
-    // Set again with finalizing. This must never be annotated as other types.
-    Tokens.back()->setFinalizedType(TT_TableGenMultiLineString);
-    Tokens.back()->Tok.setKind(tok::string_literal);
-    return;
+  if (Style.isTableGen()) {
+    // TableGen's Multi line string starts with [{
+    if (tryMergeTokens({tok::l_square, tok::l_brace},
+                       TT_TableGenMultiLineString)) {
+      // Set again with finalizing. This must never be annotated as other types.
+      Tokens.back()->setFinalizedType(TT_TableGenMultiLineString);
+      Tokens.back()->Tok.setKind(tok::string_literal);
+      return;
+    }
+    // TableGen's bang operator is the form !<name>.
+    // !cond is a special case with specific syntax.
+    if (tryMergeTokens({tok::exclaim, tok::identifier},
+                       TT_TableGenBangOperator)) {
+      Tokens.back()->Tok.setKind(tok::identifier);
+      Tokens.back()->Tok.setIdentifierInfo(nullptr);
+      if (Tokens.back()->TokenText == "!cond")
+        Tokens.back()->setFinalizedType(TT_TableGenCondOperator);
+      else
+        Tokens.back()->setFinalizedType(TT_TableGenBangOperator);
+      return;
+    }
+    if (tryMergeTokens({tok::exclaim, tok::kw_if}, TT_TableGenBangOperator)) {
+      // Here, "! if" becomes "!if".  That is, ! captures if even when the space
+      // exists. That is only one possibility in TableGen's syntax.
+      Tokens.back()->Tok.setKind(tok::identifier);
+      Tokens.back()->Tok.setIdentifierInfo(nullptr);
+      Tokens.back()->setFinalizedType(TT_TableGenBangOperator);
+      return;
+    }
+    // +, - with numbers are literals. Not unary operators.
+    if (tryMergeTokens({tok::plus, tok::numeric_constant}, TT_Unknown)) {
+      Tokens.back()->Tok.setKind(tok::numeric_constant);
+      return;
+    }
+    if (tryMergeTokens({tok::minus, tok::numeric_constant}, TT_Unknown)) {
+      Tokens.back()->Tok.setKind(tok::numeric_constant);
+      return;
+    }
   }
 }
 
@@ -373,7 +411,7 @@ bool FormatTokenLexer::tryMergeNullishCoalescingEqual() {
     return false;
   auto &NullishCoalescing = *(Tokens.end() - 2);
   auto &Equal = *(Tokens.end() - 1);
-  if (NullishCoalescing->getType() != TT_NullCoalescingOperator ||
+  if (NullishCoalescing->isNot(TT_NullCoalescingOperator) ||
       Equal->isNot(tok::equal)) {
     return false;
   }
@@ -785,7 +823,7 @@ void FormatTokenLexer::handleTableGenMultilineString() {
   auto CloseOffset = Lex->getBuffer().find("}]", OpenOffset);
   if (CloseOffset == StringRef::npos)
     return;
-  auto Text = Lex->getBuffer().substr(OpenOffset, CloseOffset + 2);
+  auto Text = Lex->getBuffer().substr(OpenOffset, CloseOffset - OpenOffset + 2);
   MultiLineString->TokenText = Text;
   resetLexer(SourceMgr.getFileOffset(
       Lex->getSourceLocation(Lex->getBufferLocation() - 2 + Text.size())));
@@ -1389,7 +1427,7 @@ void FormatTokenLexer::readRawToken(FormatToken &Tok) {
   // For formatting, treat unterminated string literals like normal string
   // literals.
   if (Tok.is(tok::unknown)) {
-    if (!Tok.TokenText.empty() && Tok.TokenText[0] == '"') {
+    if (Tok.TokenText.starts_with("\"")) {
       Tok.Tok.setKind(tok::string_literal);
       Tok.IsUnterminatedLiteral = true;
     } else if (Style.isJavaScript() && Tok.TokenText == "''") {
@@ -1411,7 +1449,6 @@ void FormatTokenLexer::readRawToken(FormatToken &Tok) {
 
 void FormatTokenLexer::resetLexer(unsigned Offset) {
   StringRef Buffer = SourceMgr.getBufferData(ID);
-  LangOpts = getFormattingLangOpts(Style);
   Lex.reset(new Lexer(SourceMgr.getLocForStartOfFile(ID), LangOpts,
                       Buffer.begin(), Buffer.begin() + Offset, Buffer.end()));
   Lex->SetKeepWhitespaceMode(true);