clang-format: [JS] handle single lines comments ending in `\\`.

Summary:
Previously, clang-format would consider the following code line to be part of
the comment and incorrectly format the rest of the file.

Reviewers: djasper

Subscribers: klimek, cfe-commits

Differential Revision: https://reviews.llvm.org/D36159

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@310365 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Format/FormatTokenLexer.cpp b/lib/Format/FormatTokenLexer.cpp
index 45c3ae1afe5fe8f9f52cf8718211be059368c8e8..5e5bfc8692378d020000d0c2d0da69a3598bd729 100644 (file)
--- a/lib/Format/FormatTokenLexer.cpp
+++ b/lib/Format/FormatTokenLexer.cpp
@@ -529,6 +529,34 @@ FormatToken *FormatTokenLexer::getNextToken() {
     readRawToken(*FormatTok);
   }
 
+  // JavaScript and Java do not allow to escape the end of the line with a
+  // backslash. Backslashes are syntax errors in plain source, but can occur in
+  // comments. When a single line comment ends with a \, it'll cause the next
+  // line of code to be lexed as a comment, breaking formatting. The code below
+  // finds comments that contain a backslash followed by a line break, truncates
+  // the comment token at the backslash, and resets the lexer to restart behind
+  // the backslash.
+  if ((Style.Language == FormatStyle::LK_JavaScript ||
+       Style.Language == FormatStyle::LK_Java) &&
+      FormatTok->is(tok::comment) && FormatTok->TokenText.startswith("//")) {
+    size_t BackslashPos = FormatTok->TokenText.find('\\');
+    while (BackslashPos != StringRef::npos) {
+      if (BackslashPos + 1 < FormatTok->TokenText.size() &&
+          FormatTok->TokenText[BackslashPos + 1] == '\n') {
+        const char *Offset = Lex->getBufferLocation();
+        Offset -= FormatTok->TokenText.size();
+        Offset += BackslashPos + 1;
+        resetLexer(SourceMgr.getFileOffset(Lex->getSourceLocation(Offset)));
+        FormatTok->TokenText = FormatTok->TokenText.substr(0, BackslashPos + 1);
+        FormatTok->ColumnWidth = encoding::columnWidthWithTabs(
+            FormatTok->TokenText, FormatTok->OriginalColumn, Style.TabWidth,
+            Encoding);
+        break;
+      }
+      BackslashPos = FormatTok->TokenText.find('\\', BackslashPos + 1);
+    }
+  }
+
   // In case the token starts with escaped newlines, we want to
   // take them into account as whitespace - this pattern is quite frequent
   // in macro definitions.

diff --git a/unittests/Format/FormatTestJS.cpp b/unittests/Format/FormatTestJS.cpp
index 67004f223fe7f33fb245d4f9e529d81b1f98f57c..12ff750a8f607c0fdd9b521d37ad77893c2bafd3 100644 (file)
--- a/unittests/Format/FormatTestJS.cpp
+++ b/unittests/Format/FormatTestJS.cpp
@@ -2074,5 +2074,27 @@ TEST_F(FormatTestJS, NestedLiterals) {
                "};", FourSpaces);
 }
 
+TEST_F(FormatTestJS, BackslashesInComments) {
+  verifyFormat("// hello \\\n"
+               "if (x) foo();\n",
+               "// hello \\\n"
+               "     if ( x) \n"
+               "   foo();\n");
+  verifyFormat("/* ignore \\\n"
+               " */\n"
+               "if (x) foo();\n",
+               "/* ignore \\\n"
+               " */\n"
+               " if (  x) foo();\n");
+  verifyFormat("// st \\ art\\\n"
+               "// comment"
+               "// continue \\\n"
+               "formatMe();\n",
+               "// st \\ art\\\n"
+               "// comment"
+               "// continue \\\n"
+               "formatMe( );\n");
+}
+
 } // end namespace tooling
 } // end namespace clang