diff options
| -rw-r--r-- | clang/lib/Lex/LiteralSupport.cpp | 21 | ||||
| -rw-r--r-- | clang/test/CXX/lex/lex.literal/lex.string/p4.cpp | 17 |
2 files changed, 34 insertions, 4 deletions
diff --git a/clang/lib/Lex/LiteralSupport.cpp b/clang/lib/Lex/LiteralSupport.cpp index beacbc9df15..1a1b281bd91 100644 --- a/clang/lib/Lex/LiteralSupport.cpp +++ b/clang/lib/Lex/LiteralSupport.cpp @@ -1417,10 +1417,23 @@ void StringLiteralParser::init(ArrayRef<Token> StringToks){ ThisTokEnd -= ThisTokBuf - Prefix; assert(ThisTokEnd >= ThisTokBuf && "malformed raw string literal"); - // Copy the string over - if (CopyStringFragment(StringToks[i], ThisTokBegin, - StringRef(ThisTokBuf, ThisTokEnd - ThisTokBuf))) - hadError = true; + // C++14 [lex.string]p4: A source-file new-line in a raw string literal + // results in a new-line in the resulting execution string-literal. + StringRef RemainingTokenSpan(ThisTokBuf, ThisTokEnd - ThisTokBuf); + while (!RemainingTokenSpan.empty()) { + // Split the string literal on \r\n boundaries. + size_t CRLFPos = RemainingTokenSpan.find("\r\n"); + StringRef BeforeCRLF = RemainingTokenSpan.substr(0, CRLFPos); + StringRef AfterCRLF = RemainingTokenSpan.substr(CRLFPos); + + // Copy everything before the \r\n sequence into the string literal. + if (CopyStringFragment(StringToks[i], ThisTokBegin, BeforeCRLF)) + hadError = true; + + // Point into the \n inside the \r\n sequence and operate on the + // remaining portion of the literal. + RemainingTokenSpan = AfterCRLF.substr(1); + } } else { if (ThisTokBuf[0] != '"') { // The file may have come from PCH and then changed after loading the diff --git a/clang/test/CXX/lex/lex.literal/lex.string/p4.cpp b/clang/test/CXX/lex/lex.literal/lex.string/p4.cpp new file mode 100644 index 00000000000..f8561ba17bc --- /dev/null +++ b/clang/test/CXX/lex/lex.literal/lex.string/p4.cpp @@ -0,0 +1,17 @@ +// RUN: %clang_cc1 -fsyntax-only -std=c++11 -verify %s
+// expected-no-diagnostics
+
+// NOTE: This file intentionally uses DOS-style line endings to test
+// that we don't propagate them into string literals as per [lex.string]p4.
+
+constexpr const char* p = R"(a\
+b
+c)";
+
+static_assert(p[0] == 'a', "");
+static_assert(p[1] == '\\', "");
+static_assert(p[2] == '\n', "");
+static_assert(p[3] == 'b', "");
+static_assert(p[4] == '\n', "");
+static_assert(p[5] == 'c', "");
+static_assert(p[6] == '\0', "");
|

