[PATCH] D138861: [Clang] Implement CWG2640 Allow more characters in an n-char sequence

[Corentin Jabot via Phabricator via cfe-commits]

cor3ntin created this revision.
Herald added a project: All.
cor3ntin requested review of this revision.
Herald added a project: clang.
Herald added a subscriber: cfe-commits.

Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D138861

Files:
  clang/lib/Lex/Lexer.cpp
  clang/lib/Lex/LiteralSupport.cpp
  clang/test/CXX/drs/dr26xx.cpp
  clang/test/Lexer/char-escapes-delimited.c
  clang/test/Preprocessor/ucn-pp-identifier.c


Index: clang/test/Preprocessor/ucn-pp-identifier.c
===================================================================
--- clang/test/Preprocessor/ucn-pp-identifier.c
+++ clang/test/Preprocessor/ucn-pp-identifier.c
@@ -121,17 +121,20 @@
 #define \u{123456789}  // expected-error {{hex escape sequence out of range}} expected-error {{macro name must be an identifier}}
 #define \u{            // expected-warning {{incomplete delimited universal character name; treating as '\' 'u' '{' identifier}} expected-error {{macro name must be an identifier}}
 #define \u{fgh}        // expected-warning {{incomplete delimited universal character name; treating as '\' 'u' '{' identifier}} expected-error {{macro name must be an identifier}}
-#define \N{            // expected-warning {{incomplete delimited universal character name; treating as '\' 'N' '{' identifier}} expected-error {{macro name must be an identifier}}
+#define \N{
+// expected-warning at -1 {{incomplete delimited universal character name; treating as '\' 'N' '{' identifier}}
+// expected-error at -2 {{macro name must be an identifier}}
 #define \N{}           // expected-warning {{empty delimited universal character name; treating as '\' 'N' '{' '}'}} expected-error {{macro name must be an identifier}}
 #define \N{NOTATHING}  // expected-error {{'NOTATHING' is not a valid Unicode character name}} \
                        // expected-error {{macro name must be an identifier}}
 #define \NN            // expected-warning {{incomplete universal character name; treating as '\' followed by identifier}} expected-error {{macro name must be an identifier}}
 #define \N{GREEK_SMALL-LETTERALPHA}  // expected-error {{'GREEK_SMALL-LETTERALPHA' is not a valid Unicode character name}} \
                                      // expected-note {{characters names in Unicode escape sequences are sensitive to case and whitespaces}}
-
+#define \N{🤡}  // expected-error {{'🤡' is not a valid Unicode character name}} \
+                // expected-error {{macro name must be an identifier}}
 #define CONCAT(A, B) A##B
-int CONCAT(\N{GREEK, CAPITALLETTERALPHA}); // expected-error{{expected}} \
-                                           // expected-warning {{incomplete delimited universal character name}}
+int CONCAT(\N{GREEK, CAPITALLETTERALPHA}); // expected-error{{'GREEK, CAPITALLETTERALPHA' is not a valid Unicode character name}} \
+                                           // expected-error{{expected}}
 
 #ifdef TRIGRAPHS
 int \N??<GREEK CAPITAL LETTER ALPHA??> = 0; // expected-warning{{extension}} cxx2b-warning {{before C++2b}} \
Index: clang/test/Lexer/char-escapes-delimited.c
===================================================================
--- clang/test/Lexer/char-escapes-delimited.c
+++ clang/test/Lexer/char-escapes-delimited.c
@@ -96,6 +96,11 @@
   unsigned i = u'\N{GREEK CAPITAL LETTER DELTA}'; // ext-warning {{extension}} cxx2b-warning {{C++2b}}
   char j = '\NN';                                 // expected-error {{expected '{' after '\N' escape sequence}} expected-warning {{multi-character character constant}}
   unsigned k = u'\N{LOTUS';                       // expected-error {{incomplete universal character name}}
+
+  const char* emoji = "\N{🤡}"; // expected-error {{'🤡' is not a valid Unicode character name}} \
+                                // expected-note 5{{did you mean}}
+  const char* nested = "\N{\N{SPARKLE}}"; // expected-error {{'\N{SPARKLE' is not a valid Unicode character name}} \
+                                          // expected-note 5{{did you mean}}
 }
 
 void separators(void) {
Index: clang/test/CXX/drs/dr26xx.cpp
===================================================================
--- clang/test/CXX/drs/dr26xx.cpp
+++ clang/test/CXX/drs/dr26xx.cpp
@@ -28,3 +28,12 @@
 }
 
 }
+
+namespace dr2640 { // dr2640: yes
+
+int \N{Λ} = 0; //expected-error {{'Λ' is not a valid Unicode character name}} \
+               //expected-error 2{{expected unqualified-id}}
+const char* emoji = "\N{🤡}"; // expected-error {{'🤡' is not a valid Unicode character name}} \
+                              // expected-note 5{{did you mean}}
+
+}
Index: clang/lib/Lex/LiteralSupport.cpp
===================================================================
--- clang/lib/Lex/LiteralSupport.cpp
+++ clang/lib/Lex/LiteralSupport.cpp
@@ -548,11 +548,10 @@
     return false;
   }
   ThisTokBuf++;
-  const char *ClosingBrace =
-      std::find_if_not(ThisTokBuf, ThisTokEnd, [](char C) {
-        return llvm::isAlnum(C) || llvm::isSpace(C) || C == '_' || C == '-';
-      });
-  bool Incomplete = ClosingBrace == ThisTokEnd || *ClosingBrace != '}';
+  const char *ClosingBrace = std::find_if(ThisTokBuf, ThisTokEnd, [](char C) {
+    return C == '}' || C == '\n' || C == '\r';
+  });
+  bool Incomplete = ClosingBrace == ThisTokEnd;
   bool Empty = ClosingBrace == ThisTokBuf;
   if (Incomplete || Empty) {
     if (Diags) {
Index: clang/lib/Lex/Lexer.cpp
===================================================================
--- clang/lib/Lex/Lexer.cpp
+++ clang/lib/Lex/Lexer.cpp
@@ -3335,7 +3335,7 @@
       break;
     }
 
-    if (!isAlphanumeric(C) && C != '_' && C != '-' && C != ' ')
+    if (C == '\n' || C == '\r')
       break;
     Buffer.push_back(C);
   }


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D138861.478359.patch
Type: text/x-patch
Size: 5288 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/cfe-commits/attachments/20221128/438787b2/attachment-0001.bin>