[clang] 27f5479 - [clang-format] Break after string literals with trailing line breaks (#76795)

[via cfe-commits]

Author: kadir çetinkaya
Date: 2024-01-08T11:11:02+01:00
New Revision: 27f547968cce89d4706ae2b27a0c15254d1670ee

URL: https://github.com/llvm/llvm-project/commit/27f547968cce89d4706ae2b27a0c15254d1670ee
DIFF: https://github.com/llvm/llvm-project/commit/27f547968cce89d4706ae2b27a0c15254d1670ee.diff

LOG: [clang-format] Break after string literals with trailing line breaks (#76795)

This restores a subset of functionality that was forego in
d68826dfbd987377ef6771d40c1d984f09ee3b9e.

Streaming multiple string literals is rare enough in practice, hence
that change makes sense in general. But it seems people were
incidentally relying on this for having line breaks after string
literals that ended with `\n`.

This patch tries to restore that behavior to prevent regressions in the
upcoming LLVM release, until we can implement some configuration based
approach as proposed in https://github.com/llvm/llvm-project/pull/69859.

Added: 
    

Modified: 
    clang/lib/Format/TokenAnnotator.cpp
    clang/unittests/Format/FormatTest.cpp
    clang/unittests/Format/TokenAnnotatorTest.cpp

Removed: 
    


################################################################################
diff  --git a/clang/lib/Format/TokenAnnotator.cpp b/clang/lib/Format/TokenAnnotator.cpp
index 3ac3aa3c5e3a22..8b43438c72dfe1 100644
--- a/clang/lib/Format/TokenAnnotator.cpp
+++ b/clang/lib/Format/TokenAnnotator.cpp
@@ -5151,6 +5151,14 @@ bool TokenAnnotator::mustBreakBefore(const AnnotatedLine &Line,
     return true;
   if (Left.IsUnterminatedLiteral)
     return true;
+  // FIXME: Breaking after newlines seems useful in general. Turn this into an
+  // option and recognize more cases like endl etc, and break independent of
+  // what comes after operator lessless.
+  if (Right.is(tok::lessless) && Right.Next &&
+      Right.Next->is(tok::string_literal) && Left.is(tok::string_literal) &&
+      Left.TokenText.ends_with("\\n\"")) {
+    return true;
+  }
   if (Right.is(TT_RequiresClause)) {
     switch (Style.RequiresClausePosition) {
     case FormatStyle::RCPS_OwnLine:

diff  --git a/clang/unittests/Format/FormatTest.cpp b/clang/unittests/Format/FormatTest.cpp
index 881993ede17c3d..25ef5c680af862 100644
--- a/clang/unittests/Format/FormatTest.cpp
+++ b/clang/unittests/Format/FormatTest.cpp
@@ -26708,6 +26708,8 @@ TEST_F(FormatTest, PPBranchesInBracedInit) {
 
 TEST_F(FormatTest, StreamOutputOperator) {
   verifyFormat("std::cout << \"foo\" << \"bar\" << baz;");
+  verifyFormat("std::cout << \"foo\\n\"\n"
+               "          << \"bar\";");
 }
 
 TEST_F(FormatTest, BreakAdjacentStringLiterals) {

diff  --git a/clang/unittests/Format/TokenAnnotatorTest.cpp b/clang/unittests/Format/TokenAnnotatorTest.cpp
index 2cafc0438ffb46..decc0785c5cde7 100644
--- a/clang/unittests/Format/TokenAnnotatorTest.cpp
+++ b/clang/unittests/Format/TokenAnnotatorTest.cpp
@@ -2499,6 +2499,15 @@ TEST_F(TokenAnnotatorTest, BraceKind) {
   EXPECT_BRACE_KIND(Tokens[6], BK_Block);
 }
 
+TEST_F(TokenAnnotatorTest, StreamOperator) {
+  auto Tokens = annotate("\"foo\\n\" << aux << \"foo\\n\" << \"foo\";");
+  ASSERT_EQ(Tokens.size(), 9u) << Tokens;
+  EXPECT_FALSE(Tokens[1]->MustBreakBefore);
+  EXPECT_FALSE(Tokens[3]->MustBreakBefore);
+  // Only break between string literals if the former ends with \n.
+  EXPECT_TRUE(Tokens[5]->MustBreakBefore);
+}
+
 } // namespace
 } // namespace format
 } // namespace clang