[clang-format] Ignore UnbreakableTailLength sometimes during breaking

Summary:
This patch fixes an issue where the UnbreakableTailLength would be counted towards
the length of a token during breaking, even though we can break after the token.

For example, this proto text with column limit 20
```
# ColumnLimit: 20  V
foo: {
  bar: {
    bazoo: "aaaaaaa"
  }
}
```
was broken:
```
# ColumnLimit: 20  V
foo: {
  bar: {
    bazoo:
        "aaaaaaa"
  }
}
```
because the 2 closing `}` were counted towards the string literal's `UnbreakableTailLength`.

Reviewers: djasper

Reviewed By: djasper

Subscribers: klimek, cfe-commits

Differential Revision: https://reviews.llvm.org/D42376

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@323188 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Format/BreakableToken.cpp b/lib/Format/BreakableToken.cpp
index 4735ab3564f0ec91c3c50475eec1fe40023796c7..72d2078797e5ab474ecbb1654a85db0fd3f221e3 100644 (file)
--- a/lib/Format/BreakableToken.cpp
+++ b/lib/Format/BreakableToken.cpp
@@ -214,11 +214,11 @@ unsigned BreakableStringLiteral::getContentStartColumn(unsigned LineIndex,
 
 BreakableStringLiteral::BreakableStringLiteral(
     const FormatToken &Tok, unsigned StartColumn, StringRef Prefix,
-    StringRef Postfix, bool InPPDirective, encoding::Encoding Encoding,
-    const FormatStyle &Style)
+    StringRef Postfix, unsigned UnbreakableTailLength, bool InPPDirective,
+    encoding::Encoding Encoding, const FormatStyle &Style)
     : BreakableToken(Tok, InPPDirective, Encoding, Style),
       StartColumn(StartColumn), Prefix(Prefix), Postfix(Postfix),
-      UnbreakableTailLength(Tok.UnbreakableTailLength) {
+      UnbreakableTailLength(UnbreakableTailLength) {
   assert(Tok.TokenText.startswith(Prefix) && Tok.TokenText.endswith(Postfix));
   Line = Tok.TokenText.substr(
       Prefix.size(), Tok.TokenText.size() - Prefix.size() - Postfix.size());

diff --git a/lib/Format/BreakableToken.h b/lib/Format/BreakableToken.h
index 8ef26ef464da9ea8b085ec26994edac178ea8fcd..eba48f75e88fde9e65abbde3c878409a0791f624 100644 (file)
--- a/lib/Format/BreakableToken.h
+++ b/lib/Format/BreakableToken.h
@@ -238,8 +238,8 @@ public:
   /// after formatting.
   BreakableStringLiteral(const FormatToken &Tok, unsigned StartColumn,
                          StringRef Prefix, StringRef Postfix,
-                         bool InPPDirective, encoding::Encoding Encoding,
-                         const FormatStyle &Style);
+                         unsigned UnbreakableTailLength, bool InPPDirective,
+                         encoding::Encoding Encoding, const FormatStyle &Style);
 
   Split getSplit(unsigned LineIndex, unsigned TailOffset, unsigned ColumnLimit,
                  unsigned ReflowColumn,

diff --git a/lib/Format/ContinuationIndenter.cpp b/lib/Format/ContinuationIndenter.cpp
index f7472bcd083fc3c0bc89c18173700f1ec8bae1b2..3711ee01c4829ec109befdc704b97ec47088d1e4 100644 (file)
--- a/lib/Format/ContinuationIndenter.cpp
+++ b/lib/Format/ContinuationIndenter.cpp
@@ -1576,9 +1576,16 @@ std::unique_ptr<BreakableToken> ContinuationIndenter::createBreakableToken(
           Text.startswith(Prefix = "u8\"") ||
           Text.startswith(Prefix = "L\""))) ||
         (Text.startswith(Prefix = "_T(\"") && Text.endswith(Postfix = "\")"))) {
+      // We need this to address the case where there is an unbreakable tail
+      // only if certain other formatting decisions have been taken. The
+      // UnbreakableTailLength of Current is an overapproximation is that case
+      // and we need to be correct here.
+      unsigned UnbreakableTailLength = (State.NextToken && canBreak(State))
+                                           ? 0
+                                           : Current.UnbreakableTailLength;
       return llvm::make_unique<BreakableStringLiteral>(
-          Current, StartColumn, Prefix, Postfix, State.Line->InPPDirective,
-          Encoding, Style);
+          Current, StartColumn, Prefix, Postfix, UnbreakableTailLength,
+          State.Line->InPPDirective, Encoding, Style);
     }
   } else if (Current.is(TT_BlockComment)) {
     if (!Style.ReflowComments ||

diff --git a/unittests/Format/FormatTestTextProto.cpp b/unittests/Format/FormatTestTextProto.cpp
index 0a7bcdd82362311387fca8b0a8413b23e716de72..82da8737a377f60c07a8a986ed2f05e8bf6fd74b 100644 (file)
--- a/unittests/Format/FormatTestTextProto.cpp
+++ b/unittests/Format/FormatTestTextProto.cpp
@@ -290,5 +290,17 @@ TEST_F(FormatTestTextProto, SupportsAngleBracketMessageFields) {
                "  product_data <product {1}>\n"
                ">");
 }
+
+TEST_F(FormatTestTextProto, DiscardsUnbreakableTailIfCanBreakAfter) {
+  // The two closing braces count towards the string UnbreakableTailLength, but
+  // since we have broken after the corresponding opening braces, we don't
+  // consider that length for string breaking.
+  verifyFormat(
+      "foo: {\n"
+      "  bar: {\n"
+      "    text: \"aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa\"\n"
+      "  }\n"
+      "}");
+}
 } // end namespace tooling
 } // end namespace clang