This revision was automatically updated to reflect the committed changes.
Closed by commit rG36a8f7f6d8f5: [clang-format] Handle escaped " in C# 
string-literals (authored by krasimir).
Herald added a project: clang.
Herald added a subscriber: cfe-commits.

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D73353/new/

https://reviews.llvm.org/D73353

Files:
  clang/lib/Format/FormatTokenLexer.cpp
  clang/unittests/Format/FormatTestCSharp.cpp


Index: clang/unittests/Format/FormatTestCSharp.cpp
===================================================================
--- clang/unittests/Format/FormatTestCSharp.cpp
+++ clang/unittests/Format/FormatTestCSharp.cpp
@@ -409,5 +409,13 @@
   verifyFormat("(int) x / y;", Style);
 }
 
+TEST_F(FormatTestCSharp, CSharpEscapedQuotesInVerbatimStrings) {
+  FormatStyle Style = getGoogleStyle(FormatStyle::LK_CSharp);
+
+  verifyFormat(R"(string str = @"""")", Style);
+  verifyFormat(R"(string str = @"""Hello world""")", Style);
+  verifyFormat(R"(string str = $@"""Hello {friend}""")", Style);
+}
+
 } // namespace format
 } // end namespace clang
Index: clang/lib/Format/FormatTokenLexer.cpp
===================================================================
--- clang/lib/Format/FormatTokenLexer.cpp
+++ clang/lib/Format/FormatTokenLexer.cpp
@@ -184,15 +184,33 @@
 bool FormatTokenLexer::tryMergeCSharpVerbatimStringLiteral() {
   if (Tokens.size() < 2)
     return false;
-  auto &At = *(Tokens.end() - 2);
+
   auto &String = *(Tokens.end() - 1);
+  if (!String->is(tok::string_literal))
+    return false;
+
+  // verbatim strings could contain "" which C# sees as an escaped ".
+  // @"""Hello""" will have been tokenized as @"" "Hello" "" and needs
+  // merging into a single string literal.
+  auto &CSharpStringLiteral = *(Tokens.end() - 2);
+  if (CSharpStringLiteral->Type == TT_CSharpStringLiteral &&
+      (CSharpStringLiteral->TokenText.startswith(R"(@")") ||
+       CSharpStringLiteral->TokenText.startswith(R"($@")"))) {
+    CSharpStringLiteral->TokenText = StringRef(
+        CSharpStringLiteral->TokenText.begin(),
+        String->TokenText.end() - CSharpStringLiteral->TokenText.begin());
+    CSharpStringLiteral->ColumnWidth += String->ColumnWidth;
+    Tokens.erase(Tokens.end() - 1);
+    return true;
+  }
+
+  auto &At = *(Tokens.end() - 2);
 
-  // Look for $"aaaaaa" @"aaaaaa".
-  if (!(At->is(tok::at) || At->TokenText == "$") ||
-      !String->is(tok::string_literal))
+  // Look for @"aaaaaa" or $"aaaaaa".
+  if (!(At->is(tok::at) || At->TokenText == "$"))
     return false;
 
-  if (Tokens.size() >= 2 && At->is(tok::at)) {
+  if (Tokens.size() > 2 && At->is(tok::at)) {
     auto &Dollar = *(Tokens.end() - 3);
     if (Dollar->TokenText == "$") {
       // This looks like $@"aaaaa" so we need to combine all 3 tokens.


Index: clang/unittests/Format/FormatTestCSharp.cpp
===================================================================
--- clang/unittests/Format/FormatTestCSharp.cpp
+++ clang/unittests/Format/FormatTestCSharp.cpp
@@ -409,5 +409,13 @@
   verifyFormat("(int) x / y;", Style);
 }
 
+TEST_F(FormatTestCSharp, CSharpEscapedQuotesInVerbatimStrings) {
+  FormatStyle Style = getGoogleStyle(FormatStyle::LK_CSharp);
+
+  verifyFormat(R"(string str = @"""")", Style);
+  verifyFormat(R"(string str = @"""Hello world""")", Style);
+  verifyFormat(R"(string str = $@"""Hello {friend}""")", Style);
+}
+
 } // namespace format
 } // end namespace clang
Index: clang/lib/Format/FormatTokenLexer.cpp
===================================================================
--- clang/lib/Format/FormatTokenLexer.cpp
+++ clang/lib/Format/FormatTokenLexer.cpp
@@ -184,15 +184,33 @@
 bool FormatTokenLexer::tryMergeCSharpVerbatimStringLiteral() {
   if (Tokens.size() < 2)
     return false;
-  auto &At = *(Tokens.end() - 2);
+
   auto &String = *(Tokens.end() - 1);
+  if (!String->is(tok::string_literal))
+    return false;
+
+  // verbatim strings could contain "" which C# sees as an escaped ".
+  // @"""Hello""" will have been tokenized as @"" "Hello" "" and needs
+  // merging into a single string literal.
+  auto &CSharpStringLiteral = *(Tokens.end() - 2);
+  if (CSharpStringLiteral->Type == TT_CSharpStringLiteral &&
+      (CSharpStringLiteral->TokenText.startswith(R"(@")") ||
+       CSharpStringLiteral->TokenText.startswith(R"($@")"))) {
+    CSharpStringLiteral->TokenText = StringRef(
+        CSharpStringLiteral->TokenText.begin(),
+        String->TokenText.end() - CSharpStringLiteral->TokenText.begin());
+    CSharpStringLiteral->ColumnWidth += String->ColumnWidth;
+    Tokens.erase(Tokens.end() - 1);
+    return true;
+  }
+
+  auto &At = *(Tokens.end() - 2);
 
-  // Look for $"aaaaaa" @"aaaaaa".
-  if (!(At->is(tok::at) || At->TokenText == "$") ||
-      !String->is(tok::string_literal))
+  // Look for @"aaaaaa" or $"aaaaaa".
+  if (!(At->is(tok::at) || At->TokenText == "$"))
     return false;
 
-  if (Tokens.size() >= 2 && At->is(tok::at)) {
+  if (Tokens.size() > 2 && At->is(tok::at)) {
     auto &Dollar = *(Tokens.end() - 3);
     if (Dollar->TokenText == "$") {
       // This looks like $@"aaaaa" so we need to combine all 3 tokens.
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

Reply via email to