[clang-format] Handle Trailing Whitespace After Line Continuation (P2223R2)

clang/docs/ReleaseNotes.rst

@@ -1025,6 +1025,9 @@ clang-format
   ``enum`` enumerator lists.
 - Add ``OneLineFormatOffRegex`` option for turning formatting off for one line.
 - Add ``SpaceAfterOperatorKeyword`` option.
+- Support trailing whitespace in line splicing.
+  (P2223R2 <https://www.open-std.org/jtc1/sc22/wg21/docs/papers/2021/p2223r2.pdf>_, #GH145226)
+
 
 clang-refactor
 --------------

clang/lib/Format/FormatTokenLexer.cpp

@@ -14,6 +14,7 @@
 
 #include "FormatTokenLexer.h"
 #include "FormatToken.h"
+#include "clang/Basic/CharInfo.h"
 #include "clang/Basic/SourceLocation.h"
 #include "clang/Basic/SourceManager.h"
 #include "clang/Format/Format.h"
@@ -1205,14 +1206,23 @@ static size_t countLeadingWhitespace(StringRef Text) {
   while (Cur < End) {
     if (isspace(Cur[0])) {
       ++Cur;
-    } else if (Cur[0] == '\\' && (Cur[1] == '\n' || Cur[1] == '\r')) {
-      // A '\' followed by a newline always escapes the newline, regardless
-      // of whether there is another '\' before it.
+    } else if (Cur[0] == '\\') {
+      // A '\' followed by a optional horizontal whitespace (P22232R2) and then
+      // newline  always escapes the newline, regardless  of whether there is
+      // another '\' before it.
       // The source has a null byte at the end. So the end of the entire input
       // isn't reached yet. Also the lexer doesn't break apart an escaped
       // newline.
-      assert(End - Cur >= 2);
-      Cur += 2;
+      const unsigned char *Lookahead = Cur + 1;
+      while (isHorizontalWhitespace(*Lookahead))
+        ++Lookahead;
+      if (*Lookahead == '\n' || *Lookahead == '\r') {
+        // Splice found, consume it.
+        Cur = Lookahead + 1;
+        continue;
+      }
+      // No line splice found; the '\' is a token.
+      break;
     } else if (Cur[0] == '?' && Cur[1] == '?' && Cur[2] == '/' &&
                (Cur[3] == '\n' || Cur[3] == '\r')) {
       // Newlines can also be escaped by a '?' '?' '/' trigraph. By the way, the
@@ -1295,13 +1305,18 @@ FormatToken *FormatTokenLexer::getNextToken() {
       case '/':
         // The text was entirely whitespace when this loop was entered. Thus
         // this has to be an escape sequence.
-        assert(Text.substr(i, 2) == "\\\r" || Text.substr(i, 2) == "\\\n" ||
-               Text.substr(i, 4) == "\?\?/\r" ||
+        assert(Text.substr(i, 4) == "\?\?/\r" ||
                Text.substr(i, 4) == "\?\?/\n" ||
                (i >= 1 && (Text.substr(i - 1, 4) == "\?\?/\r" ||
                            Text.substr(i - 1, 4) == "\?\?/\n")) ||
                (i >= 2 && (Text.substr(i - 2, 4) == "\?\?/\r" ||
-                           Text.substr(i - 2, 4) == "\?\?/\n")));
+                           Text.substr(i - 2, 4) == "\?\?/\n")) ||
+               (Text[i] == '\\' && [&]() -> bool {
+                 size_t j = i + 1;
+                 while (j < Text.size() && isHorizontalWhitespace(Text[j]))
+                   ++j;
+                 return j < Text.size() && (Text[j] == '\n' || Text[j] == '\r');
+               }()));
         InEscape = true;
         break;
       default:

clang/test/Format/splice-trailing-whitespace-p2223r2.cpp

@@ -0,0 +1,14 @@
+// RUN: grep -Ev "// *[A-Z-]+:" %s \
+// RUN:   | clang-format -style='{BasedOnStyle: LLVM, AlignEscapedNewlines: DontAlign}' \
+// RUN:   | FileCheck -strict-whitespace %s
+
+// CHECK: {{^#define TAG\(\.\.\.\) \\}}
+// CHECK: {{^  struct a \{\};}}
+// There is whitespace following  v  this backslash!
+#define TAG(...)  struct a {     \     
+  };
+
+// CHECK: {{^int   i;}}
+// The comment below eats its following line because of the line splice.
+// I also have trailing whitespace. Nom nom nom \     
+int   i;