X-Git-Url: http://plrg.eecs.uci.edu/git/?p=oota-llvm.git;a=blobdiff_plain;f=include%2Fllvm%2FADT%2FStringRef.h;h=34caeee801a2f477975492907df7867c42ea0527;hp=56848fb61672dc16027827b30983231881ea2d79;hb=f41971f6e7f9e5ba0c590c7e35e2c1af0cd38c69;hpb=fb5b3eaacbc65603b436279300c32512176150fe diff --git a/include/llvm/ADT/StringRef.h b/include/llvm/ADT/StringRef.h index 56848fb6167..34caeee801a 100644 --- a/include/llvm/ADT/StringRef.h +++ b/include/llvm/ADT/StringRef.h @@ -10,7 +10,6 @@ #ifndef LLVM_ADT_STRINGREF_H #define LLVM_ADT_STRINGREF_H -#include "llvm/Support/type_traits.h" #include #include #include @@ -19,7 +18,7 @@ #include namespace llvm { - template + template class SmallVectorImpl; class APInt; class hash_code; @@ -52,12 +51,6 @@ namespace llvm { /// The length of the string. size_t Length; - // Workaround PR5482: nearly all gcc 4.x miscompile StringRef and std::min() - // Changing the arg of min to be an integer, instead of a reference to an - // integer works around this bug. - static size_t min(size_t a, size_t b) { return a < b ? a : b; } - static size_t max(size_t a, size_t b) { return a > b ? a : b; } - // Workaround memcmp issue with null pointers (undefined behavior) // by providing a specialized version static int compareMemory(const char *Lhs, const char *Rhs, size_t Length) { @@ -70,7 +63,7 @@ namespace llvm { /// @{ /// Construct an empty string ref. - /*implicit*/ StringRef() : Data(0), Length(0) {} + /*implicit*/ StringRef() : Data(nullptr), Length(0) {} /// Construct a string ref from a cstring. /*implicit*/ StringRef(const char *Str) @@ -90,10 +83,6 @@ namespace llvm { /*implicit*/ StringRef(const std::string &Str) : Data(Str.data()), Length(Str.length()) {} - /// Construct a string ref from a boolean. - explicit StringRef(bool B) - : Data(B ? "true" : "false"), Length(::strlen(Data)) {} - /// @} /// @name Iterators /// @{ @@ -102,6 +91,13 @@ namespace llvm { iterator end() const { return Data + Length; } + const unsigned char *bytes_begin() const { + return reinterpret_cast(begin()); + } + const unsigned char *bytes_end() const { + return reinterpret_cast(end()); + } + /// @} /// @name String Operations /// @{ @@ -128,6 +124,13 @@ namespace llvm { return Data[Length-1]; } + // copy - Allocate copy in Allocator and return StringRef to it. + template StringRef copy(Allocator &A) const { + char *S = A.template Allocate(Length); + std::copy(begin(), end(), S); + return StringRef(S, Length); + } + /// equals - Check for string equality, this is more efficient than /// compare() when the relative ordering of inequal strings isn't needed. bool equals(StringRef RHS) const { @@ -144,7 +147,7 @@ namespace llvm { /// is lexicographically less than, equal to, or greater than the \p RHS. int compare(StringRef RHS) const { // Check the prefix for a mismatch. - if (int Res = compareMemory(Data, RHS.Data, min(Length, RHS.Length))) + if (int Res = compareMemory(Data, RHS.Data, std::min(Length, RHS.Length))) return Res < 0 ? -1 : 1; // Otherwise the prefixes match, so we only need to check the lengths. @@ -179,11 +182,11 @@ namespace llvm { /// transform one of the given strings into the other. If zero, /// the strings are identical. unsigned edit_distance(StringRef Other, bool AllowReplacements = true, - unsigned MaxEditDistance = 0); + unsigned MaxEditDistance = 0) const; /// str - Get the contents as an std::string. std::string str() const { - if (Data == 0) return std::string(); + if (!Data) return std::string(); return std::string(Data, Length); } @@ -214,12 +217,18 @@ namespace llvm { compareMemory(Data, Prefix.Data, Prefix.Length) == 0; } + /// Check if this string starts with the given \p Prefix, ignoring case. + bool startswith_lower(StringRef Prefix) const; + /// Check if this string ends with the given \p Suffix. bool endswith(StringRef Suffix) const { return Length >= Suffix.Length && compareMemory(end() - Suffix.Length, Suffix.Data, Suffix.Length) == 0; } + /// Check if this string ends with the given \p Suffix, ignoring case. + bool endswith_lower(StringRef Suffix) const; + /// @} /// @name String Searching /// @{ @@ -229,9 +238,12 @@ namespace llvm { /// \returns The index of the first occurrence of \p C, or npos if not /// found. size_t find(char C, size_t From = 0) const { - for (size_t i = min(From, Length), e = Length; i != e; ++i) - if (Data[i] == C) - return i; + size_t FindBegin = std::min(From, Length); + if (FindBegin < Length) { // Avoid calling memchr with nullptr. + // Just forward to memchr, which is faster than a hand-rolled loop. + if (const void *P = ::memchr(Data + FindBegin, C, Length - FindBegin)) + return static_cast(P) - Data; + } return npos; } @@ -246,7 +258,7 @@ namespace llvm { /// \returns The index of the last occurrence of \p C, or npos if not /// found. size_t rfind(char C, size_t From = npos) const { - From = min(From, Length); + From = std::min(From, Length); size_t i = From; while (i != 0) { --i; @@ -331,7 +343,7 @@ namespace llvm { /// this returns true to signify the error. The string is considered /// erroneous if empty or if it overflows T. template - typename enable_if_c::is_signed, bool>::type + typename std::enable_if::is_signed, bool>::type getAsInteger(unsigned Radix, T &Result) const { long long LLVal; if (getAsSignedInteger(*this, Radix, LLVal) || @@ -342,11 +354,14 @@ namespace llvm { } template - typename enable_if_c::is_signed, bool>::type + typename std::enable_if::is_signed, bool>::type getAsInteger(unsigned Radix, T &Result) const { unsigned long long ULLVal; + // The additional cast to unsigned long long is required to avoid the + // Visual C++ warning C4805: '!=' : unsafe mix of type 'bool' and type + // 'unsigned __int64' when instantiating getAsInteger with T = bool. if (getAsUnsignedInteger(*this, Radix, ULLVal) || - static_cast(ULLVal) != ULLVal) + static_cast(static_cast(ULLVal)) != ULLVal) return true; Result = ULLVal; return false; @@ -388,8 +403,8 @@ namespace llvm { /// exceeds the number of characters remaining in the string, the string /// suffix (starting with \p Start) will be returned. StringRef substr(size_t Start, size_t N = npos) const { - Start = min(Start, Length); - return StringRef(Data + Start, min(N, Length - Start)); + Start = std::min(Start, Length); + return StringRef(Data + Start, std::min(N, Length - Start)); } /// Return a StringRef equal to 'this' but with the first \p N elements @@ -417,8 +432,8 @@ namespace llvm { /// number of characters remaining in the string, the string suffix /// (starting with \p Start) will be returned. StringRef slice(size_t Start, size_t End) const { - Start = min(Start, Length); - End = min(max(Start, End), Length); + Start = std::min(Start, Length); + End = std::min(std::max(Start, End), Length); return StringRef(Data + Start, End - Start); } @@ -459,7 +474,7 @@ namespace llvm { /// Split into substrings around the occurrences of a separator string. /// /// Each substring is stored in \p A. If \p MaxSplit is >= 0, at most - /// \p MaxSplit splits are done and consequently <= \p MaxSplit + /// \p MaxSplit splits are done and consequently <= \p MaxSplit + 1 /// elements are added to A. /// If \p KeepEmpty is false, empty strings are not added to \p A. They /// still count when considering \p MaxSplit @@ -474,6 +489,23 @@ namespace llvm { StringRef Separator, int MaxSplit = -1, bool KeepEmpty = true) const; + /// Split into substrings around the occurrences of a separator character. + /// + /// Each substring is stored in \p A. If \p MaxSplit is >= 0, at most + /// \p MaxSplit splits are done and consequently <= \p MaxSplit + 1 + /// elements are added to A. + /// If \p KeepEmpty is false, empty strings are not added to \p A. They + /// still count when considering \p MaxSplit + /// An useful invariant is that + /// Separator.join(A) == *this if MaxSplit == -1 and KeepEmpty == true + /// + /// \param A - Where to put the substrings. + /// \param Separator - The string to split on. + /// \param MaxSplit - The maximum number of times the string is split. + /// \param KeepEmpty - True if empty substring should be added. + void split(SmallVectorImpl &A, char Separator, int MaxSplit = -1, + bool KeepEmpty = true) const; + /// Split into two substrings around the last occurrence of a separator /// character. /// @@ -551,7 +583,6 @@ namespace llvm { // StringRefs can be treated like a POD type. template struct isPodLike; template <> struct isPodLike { static const bool value = true; }; - } #endif