[clang-format] TableGen multi line string support.

Author: hnakamura5

clang/lib/Format/ContinuationIndenter.cpp

@@ -1591,6 +1591,9 @@ unsigned ContinuationIndenter::moveStateToNextToken(LineState &State,
     State.StartOfStringLiteral = State.Column + 1;
   if (Current.is(TT_CSharpStringLiteral) && State.StartOfStringLiteral == 0) {
     State.StartOfStringLiteral = State.Column + 1;
+  } else if (Current.is(TT_TableGenMultiLineString) &&
+             State.StartOfStringLiteral == 0) {
+    State.StartOfStringLiteral = State.Column + 1;
   } else if (Current.isStringLiteral() && State.StartOfStringLiteral == 0) {
     State.StartOfStringLiteral = State.Column;
   } else if (!Current.isOneOf(tok::comment, tok::identifier, tok::hash) &&

clang/lib/Format/FormatToken.h

@@ -148,6 +148,7 @@ namespace format {
   TYPE(StructLBrace)                                                           \
   TYPE(StructRBrace)                                                           \
   TYPE(StructuredBindingLSquare)                                               \
+  TYPE(TableGenMultiLineString)                                                \
   TYPE(TemplateCloser)                                                         \
   TYPE(TemplateOpener)                                                         \
   TYPE(TemplateString)                                                         \

clang/lib/Format/FormatTokenLexer.cpp

@@ -93,6 +93,8 @@ ArrayRef<FormatToken *> FormatTokenLexer::lex() {
       // string literals are correctly identified.
       handleCSharpVerbatimAndInterpolatedStrings();
     }
+    if (Style.isTableGen())
+      handleTableGenMultilineString();
     if (Tokens.back()->NewlinesBefore > 0 || Tokens.back()->IsMultiline)
       FirstInLineIndex = Tokens.size() - 1;
   } while (Tokens.back()->isNot(tok::eof));
@@ -272,6 +274,14 @@ void FormatTokenLexer::tryMergePreviousTokens() {
       return;
     }
   }
+  if (Style.isTableGen()) {
+    if (tryMergeTokens({tok::l_square, tok::l_brace},
+                       TT_TableGenMultiLineString)) {
+      // Multi line string starts with [{
+      Tokens.back()->Tok.setKind(tok::string_literal);
+      return;
+    }
+  }
 }
 
 bool FormatTokenLexer::tryMergeNSStringLiteral() {
@@ -763,6 +773,53 @@ void FormatTokenLexer::handleCSharpVerbatimAndInterpolatedStrings() {
   resetLexer(SourceMgr.getFileOffset(Lex->getSourceLocation(Offset + 1)));
 }
 
+void FormatTokenLexer::handleTableGenMultilineString() {
+  FormatToken *MultiLineString = Tokens.back();
+  if (MultiLineString->isNot(TT_TableGenMultiLineString))
+    return;
+
+  bool PrevIsRBrace = false;
+  const char *FirstBreak = nullptr;
+  const char *LastBreak = nullptr;
+  const char *Begin = MultiLineString->TokenText.begin();
+  // Skip until }], the closer of multi line string found.
+  for (const char *Current = Begin, *End = Lex->getBuffer().end();
+       Current != End; ++Current) {
+    if (PrevIsRBrace && *Current == ']') {
+      // }] is the end of multi line string.
+      if (!FirstBreak)
+        FirstBreak = Current;
+      MultiLineString->TokenText = StringRef(Begin, Current - Begin + 1);
+      // ColumnWidth is only the width of the first line.
+      MultiLineString->ColumnWidth = encoding::columnWidthWithTabs(
+          StringRef(Begin, FirstBreak - Begin + 1),
+          MultiLineString->OriginalColumn, Style.TabWidth, Encoding);
+      if (LastBreak) {
+        // Set LastLineColumnWidth if multi line string has multiple lines.
+        MultiLineString->LastLineColumnWidth = encoding::columnWidthWithTabs(
+            StringRef(LastBreak + 1, Current - LastBreak),
+            MultiLineString->OriginalColumn, Style.TabWidth, Encoding);
+      }
+      resetLexer(SourceMgr.getFileOffset(Lex->getSourceLocation(Current + 1)));
+      return;
+    }
+    PrevIsRBrace = false;
+    if (*Current == '\n') {
+      MultiLineString->IsMultiline = true;
+      // Assure LastBreak is not equal to FirstBreak.
+      if (!FirstBreak)
+        FirstBreak = Current;
+      LastBreak = Current;
+      continue;
+    }
+    if (*Current == '}') {
+      // Memorize '}'. If next character is ']', they are the closer.
+      PrevIsRBrace = true;
+      continue;
+    }
+  }
+}
+
 void FormatTokenLexer::handleTemplateStrings() {
   FormatToken *BacktickToken = Tokens.back();
 

clang/lib/Format/FormatTokenLexer.h

@@ -95,6 +95,9 @@ class FormatTokenLexer {
 
   void handleCSharpVerbatimAndInterpolatedStrings();
 
+  // Handles TableGen multiline strings. It has the form [{ ... }].
+  void handleTableGenMultilineString();
+
   void tryParsePythonComment();
 
   bool tryMerge_TMacro();

clang/lib/Format/TokenAnnotator.cpp

@@ -1710,7 +1710,7 @@ class AnnotatingParser {
             TT_UnionLBrace, TT_RequiresClause,
             TT_RequiresClauseInARequiresExpression, TT_RequiresExpression,
             TT_RequiresExpressionLParen, TT_RequiresExpressionLBrace,
-            TT_BracedListLBrace)) {
+            TT_BracedListLBrace, TT_TableGenMultiLineString)) {
       CurrentToken->setType(TT_Unknown);
     }
     CurrentToken->Role.reset();

clang/unittests/Format/TokenAnnotatorTest.cpp

@@ -2193,6 +2193,11 @@ TEST_F(TokenAnnotatorTest, UnderstandTableGenTokens) {
   ASSERT_TRUE(Keywords.isTableGenDefinition(*Tokens[0]));
   ASSERT_TRUE(Tokens[0]->is(Keywords.kw_def));
   ASSERT_TRUE(Tokens[1]->is(TT_StartOfName));
+
+  // Code, the multiline string token.
+  Tokens = Annotate("[{ code is multiline string }]");
+  ASSERT_EQ(Tokens.size(), 2u) << Tokens;
+  EXPECT_TOKEN(Tokens[0], tok::string_literal, TT_TableGenMultiLineString);
 }
 
 TEST_F(TokenAnnotatorTest, UnderstandConstructors) {