cor3ntin created this revision.
cor3ntin requested review of this revision.
Herald added a project: clang.
Herald added a subscriber: cfe-commits.
This is a proposed C++ paper (P2290R1) that has not been accepted yet
\x{XXXX} \u{XXXX} and \o{OOOO} are accepted in all languages mode
in characters and string literals.
Repository:
rG LLVM Github Monorepo
https://reviews.llvm.org/D105737
Files:
clang/include/clang/Basic/DiagnosticLexKinds.td
clang/lib/Lex/LiteralSupport.cpp
clang/test/Lexer/char-escapes-delimited.cpp
Index: clang/test/Lexer/char-escapes-delimited.cpp
===================================================================
--- /dev/null
+++ clang/test/Lexer/char-escapes-delimited.cpp
@@ -0,0 +1,37 @@
+// RUN: %clang_cc1 -fsyntax-only -pedantic -verify %s
+
+const char* errors =
+"\u{}" //expected-error {{empty escape sequence}}
+"\u{" //expected-error {{incomplete escape sequence}}
+"\u{h}" //expected-error {{invalid digit in escape sequence}}
+"\x{}" //expected-error {{empty escape sequence}}
+"\x{" //expected-error {{incomplete escape sequence}}
+"\x{h}" //expected-error {{invalid digit in escape sequence}}
+"\o{}" //expected-error {{empty escape sequence}}
+"\o{" //expected-error {{incomplete escape sequence}}
+"\o{8}" //expected-error {{invalid digit in escape sequence}}
+;
+
+void ucn () {
+ char a = '\u{1234}'; //expected-error {{character too large for enclosing character literal type}}
+ char32_t b = U'\u{1234}';
+ char32_t b2 = U'\u{1}';
+ char32_t c = U'\u{000000000001234}';
+ char32_t d = U'\u{111111111}'; //expected-error {{hex escape sequence out of range}}
+}
+
+void hex () {
+ char a = '\x{1}';
+ char b = '\x{g}'; // expected-error {{invalid digit in escape sequence}}
+ char c = '\x{ff1}'; // expected-error {{hex escape sequence out of range}}
+ char32_t d = U'\x{FFFFFFFF}';
+ char32_t e = U'\x{FFFFFFFF1}'; // expected-error {{hex escape sequence out of range}}
+}
+
+void octal () {
+ char a = '\o{1}';
+ char b = '\o{8}'; // expected-error {{invalid digit in escape sequence}}
+ char c = '\o{777}'; // //expected-error {{octal escape sequence out of range}}
+ char32_t d = U'\o{37777777777}';
+ char32_t e = U'\o{47777777777}'; // expected-error {{octal escape sequence out of range}}
+}
Index: clang/lib/Lex/LiteralSupport.cpp
===================================================================
--- clang/lib/Lex/LiteralSupport.cpp
+++ clang/lib/Lex/LiteralSupport.cpp
@@ -95,6 +95,7 @@
DiagnosticsEngine *Diags,
const LangOptions &Features) {
const char *EscapeBegin = ThisTokBuf;
+ bool Delimited = false;
// Skip the '\' char.
++ThisTokBuf;
@@ -143,26 +144,45 @@
break;
case 'x': { // Hex escape.
ResultChar = 0;
- if (ThisTokBuf == ThisTokEnd || !isHexDigit(*ThisTokBuf)) {
+ if (ThisTokBuf != ThisTokEnd && *ThisTokBuf == '{') {
+ Delimited = true;
+ ThisTokBuf++;
+ if (*ThisTokBuf == '}') {
+ Diag(Diags, Features, Loc, ThisTokBegin, EscapeBegin, ThisTokBuf,
+ diag::err_delimited_escape_empty)
+ << "x";
+ return ResultChar;
+ }
+ } else if (ThisTokBuf == ThisTokEnd || !isHexDigit(*ThisTokBuf)) {
if (Diags)
Diag(Diags, Features, Loc, ThisTokBegin, EscapeBegin, ThisTokBuf,
- diag::err_hex_escape_no_digits) << "x";
- HadError = true;
- break;
+ diag::err_delimited_escape_invalid)
+ << "x";
+ return ResultChar;
}
// Hex escapes are a maximal series of hex digits.
bool Overflow = false;
for (; ThisTokBuf != ThisTokEnd; ++ThisTokBuf) {
+ if (Delimited && *ThisTokBuf == '}') {
+ ThisTokBuf++;
+ Delimited = false;
+ break;
+ }
int CharVal = llvm::hexDigitValue(ThisTokBuf[0]);
- if (CharVal == -1) break;
+ if (CharVal == -1) {
+ if (Diags)
+ Diag(Diags, Features, Loc, ThisTokBegin, EscapeBegin, ThisTokBuf,
+ diag::err_delimited_escape_invalid)
+ << "x";
+ continue;
+ }
// About to shift out a digit?
if (ResultChar & 0xF0000000)
Overflow = true;
ResultChar <<= 4;
ResultChar |= CharVal;
}
-
// See if any bits will be truncated when evaluated as a character.
if (CharWidth != 32 && (ResultChar >> CharWidth) != 0) {
Overflow = true;
@@ -200,7 +220,57 @@
}
break;
}
+ case 'o': {
+ bool Overflow = false;
+ if (ThisTokBuf == ThisTokEnd || *ThisTokBuf != '{') {
+ HadError = true;
+ if (Diags)
+ Diag(Diags, Features, Loc, ThisTokBegin, EscapeBegin, ThisTokBuf,
+ diag::err_delimited_escape_missing_brace)
+ << 'o';
+ break;
+ }
+ ResultChar = 0;
+ Delimited = true;
+ ++ThisTokBuf;
+ if (*ThisTokBuf == '}') {
+ Diag(Diags, Features, Loc, ThisTokBegin, EscapeBegin, ThisTokBuf,
+ diag::err_delimited_escape_empty)
+ << "x";
+ return ResultChar;
+ }
+
+ while (ThisTokBuf != ThisTokEnd) {
+ if (*ThisTokBuf == '}') {
+ Delimited = false;
+ ThisTokBuf++;
+ break;
+ }
+ if (*ThisTokBuf < '0' || *ThisTokBuf > '7') {
+ if (Diags)
+ Diag(Diags, Features, Loc, ThisTokBegin, EscapeBegin, ThisTokBuf,
+ diag::err_delimited_escape_invalid)
+ << 1;
+ ThisTokBuf++;
+ continue;
+ }
+ if (ResultChar & 0x020000000)
+ Overflow = true;
+
+ ResultChar <<= 3;
+ ResultChar |= *ThisTokBuf++ - '0';
+ }
+ // Check for overflow. Reject '\777', but not L'\777'.
+ if (Overflow || (CharWidth != 32 && (ResultChar >> CharWidth) != 0)) {
+ if (Diags)
+ Diag(Diags, Features, Loc, ThisTokBegin, EscapeBegin, ThisTokBuf,
+ diag::err_escape_too_large)
+ << 1;
+ ResultChar &= ~0U >> (32 - CharWidth);
+ }
+ break;
+ }
// Otherwise, these are not valid escapes.
case '(': case '{': case '[': case '%':
// GCC accepts these as extensions. We warn about them as such though.
@@ -224,6 +294,12 @@
break;
}
+ if (Delimited) {
+ Diag(Diags, Features, Loc, ThisTokBegin, EscapeBegin, ThisTokBuf,
+ diag::err_delimited_escape_incomplete)
+ << 0;
+ }
+
return ResultChar;
}
@@ -282,25 +358,72 @@
// Skip the '\u' char's.
ThisTokBuf += 2;
- if (ThisTokBuf == ThisTokEnd || !isHexDigit(*ThisTokBuf)) {
+ bool Delimited = false;
+ bool EndDelimiterFound = false;
+
+ if (UcnBegin[1] == 'u' && in_char_string_literal &&
+ ThisTokBuf != ThisTokEnd && *ThisTokBuf == '{') {
+ Delimited = true;
+ ThisTokBuf++;
+ } else if (ThisTokBuf == ThisTokEnd || !isHexDigit(*ThisTokBuf)) {
if (Diags)
Diag(Diags, Features, Loc, ThisTokBegin, UcnBegin, ThisTokBuf,
diag::err_hex_escape_no_digits) << StringRef(&ThisTokBuf[-1], 1);
return false;
}
UcnLen = (ThisTokBuf[-1] == 'u' ? 4 : 8);
- unsigned short UcnLenSave = UcnLen;
- for (; ThisTokBuf != ThisTokEnd && UcnLenSave; ++ThisTokBuf, UcnLenSave--) {
+
+ bool Overflow = false;
+ unsigned short Count = 0;
+ for (; ThisTokBuf != ThisTokEnd && (Delimited || Count != UcnLen);
+ ++ThisTokBuf) {
+ if (Delimited && *ThisTokBuf == '}') {
+ ++ThisTokBuf;
+ EndDelimiterFound = true;
+ break;
+ }
int CharVal = llvm::hexDigitValue(ThisTokBuf[0]);
- if (CharVal == -1) break;
+ if (CharVal == -1) {
+ if (Diags) {
+ Diag(Diags, Features, Loc, ThisTokBegin, UcnBegin, ThisTokBuf,
+ diag::err_delimited_escape_invalid)
+ << 'u';
+ }
+ Count++;
+ continue;
+ }
+ if (UcnVal & 0xF0000000) {
+ Overflow = true;
+ continue;
+ }
UcnVal <<= 4;
UcnVal |= CharVal;
+ Count++;
+ }
+
+ if (Overflow) {
+ if (Diags)
+ Diag(Diags, Features, Loc, ThisTokBegin, UcnBegin, ThisTokBuf,
+ diag::err_escape_too_large)
+ << 0;
+ return false;
}
+
+ if (Delimited && !EndDelimiterFound) {
+ if (Diags) {
+ Diag(Diags, Features, Loc, ThisTokBegin, UcnBegin, ThisTokBuf,
+ diag::err_delimited_escape_incomplete)
+ << 'u';
+ }
+ return false;
+ }
+
// If we didn't consume the proper number of digits, there is a problem.
- if (UcnLenSave) {
+ if (Count == 0 || (!Delimited && Count != UcnLen)) {
if (Diags)
Diag(Diags, Features, Loc, ThisTokBegin, UcnBegin, ThisTokBuf,
- diag::err_ucn_escape_incomplete);
+ Delimited ? diag::err_delimited_escape_empty
+ : diag::err_ucn_escape_incomplete);
return false;
}
Index: clang/include/clang/Basic/DiagnosticLexKinds.td
===================================================================
--- clang/include/clang/Basic/DiagnosticLexKinds.td
+++ clang/include/clang/Basic/DiagnosticLexKinds.td
@@ -125,6 +125,14 @@
"identifier contains Unicode character <U+%0> that is invisible in "
"some environments">, InGroup<DiagGroup<"unicode-zero-width">>;
+def err_delimited_escape_incomplete : Error<
+ "incomplete escape sequence">;
+def err_delimited_escape_empty : Error<
+ "empty escape sequence">;
+def err_delimited_escape_missing_brace: Error<
+ "expected { after \\%0 escape sequence">;
+def err_delimited_escape_invalid : Error<
+ "invalid digit in escape sequence">;
def err_hex_escape_no_digits : Error<
"\\%0 used with no following hex digits">;
def warn_ucn_escape_no_digits : Warning<
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
