//===--- StringRef.h - Constant String Reference Wrapper --------*- C++ -*-===// // // The LLVM Compiler Infrastructure // // This file is distributed under the University of Illinois Open Source // License. See LICENSE.TXT for details. // //===----------------------------------------------------------------------===// #ifndef LLVM_ADT_STRINGREF_H #define LLVM_ADT_STRINGREF_H #include #include #include #include namespace llvm { /// StringRef - Represent a constant reference to a string, i.e. a character /// array and a length, which need not be null terminated. /// /// This class does not own the string data, it is expected to be used in /// situations where the character data resides in some other buffer, whose /// lifetime extends past that of the StringRef. For this reason, it is not in /// general safe to store a StringRef. class StringRef { public: typedef const char *iterator; static const size_t npos = ~size_t(0); typedef size_t size_type; private: /// The start of the string, in an external buffer. const char *Data; /// The length of the string. size_t Length; public: /// @name Constructors /// @{ /// Construct an empty string ref. /*implicit*/ StringRef() : Data(0), Length(0) {} /// Construct a string ref from a cstring. /*implicit*/ StringRef(const char *Str) : Data(Str) { if (Str) Length = ::strlen(Str); else Length = 0; } /// Construct a string ref from a pointer and length. /*implicit*/ StringRef(const char *data, size_t length) : Data(data), Length(length) {} /// Construct a string ref from an std::string. /*implicit*/ StringRef(const std::string &Str) : Data(Str.c_str()), Length(Str.length()) {} /// @} /// @name Iterators /// @{ iterator begin() const { return Data; } iterator end() const { return Data + Length; } /// @} /// @name String Operations /// @{ /// data - Get a pointer to the start of the string (which may not be null /// terminated). const char *data() const { return Data; } /// empty - Check if the string is empty. bool empty() const { return Length == 0; } /// size - Get the string size. size_t size() const { return Length; } /// front - Get the first character in the string. char front() const { assert(!empty()); return Data[0]; } /// back - Get the last character in the string. char back() const { assert(!empty()); return Data[Length-1]; } /// equals - Check for string equality, this is more efficient than /// compare() when the relative ordering of inequal strings isn't needed. bool equals(const StringRef &RHS) const { return (Length == RHS.Length && memcmp(Data, RHS.Data, RHS.Length) == 0); } /// compare - Compare two strings; the result is -1, 0, or 1 if this string /// is lexicographically less than, equal to, or greater than the \arg RHS. int compare(const StringRef &RHS) const { // Check the prefix for a mismatch. if (int Res = memcmp(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. if (Length == RHS.Length) return 0; return Length < RHS.Length ? -1 : 1; } /// str - Get the contents as an std::string. std::string str() const { return std::string(Data, Length); } /// @} /// @name Operator Overloads /// @{ char operator[](size_t Index) const { assert(Index < Length && "Invalid index!"); return Data[Index]; } /// @} /// @name Type Conversions /// @{ operator std::string() const { return str(); } /// @} /// @name String Predicates /// @{ /// startswith - Check if this string starts with the given \arg Prefix. bool startswith(const StringRef &Prefix) const { return substr(0, Prefix.Length).equals(Prefix); } /// endswith - Check if this string ends with the given \arg Suffix. bool endswith(const StringRef &Suffix) const { return slice(size() - Suffix.Length, size()).equals(Suffix); } /// @} /// @name String Searching /// @{ /// find - Search for the first character \arg C in the string. /// /// \return - The index of the first occurence of \arg C, or npos if not /// found. size_t find(char C) const { for (size_t i = 0, e = Length; i != e; ++i) if (Data[i] == C) return i; return npos; } /// find - Search for the first string \arg Str in the string. /// /// \return - The index of the first occurence of \arg Str, or npos if not /// found. size_t find(const StringRef &Str) const; /// rfind - Search for the last character \arg C in the string. /// /// \return - The index of the last occurence of \arg C, or npos if not /// found. size_t rfind(char C, size_t From = npos) const { From = std::min(From, Length); size_t i = From; while (i != 0) { --i; if (Data[i] == C) return i; } return npos; } /// rfind - Search for the last string \arg Str in the string. /// /// \return - The index of the last occurence of \arg Str, or npos if not /// found. size_t rfind(const StringRef &Str) const; /// find_first_of - Find the first instance of the specified character or /// return npos if not in string. Same as find. size_type find_first_of(char C) const { return find(C); } /// find_first_of - Find the first character from the string 'Chars' in the /// current string or return npos if not in string. size_type find_first_of(StringRef Chars) const; /// find_first_not_of - Find the first character in the string that is not /// in the string 'Chars' or return npos if all are in string. Same as find. size_type find_first_not_of(StringRef Chars) const; /// @} /// @name Helpful Algorithms /// @{ /// count - Return the number of occurrences of \arg C in the string. size_t count(char C) const { size_t Count = 0; for (size_t i = 0, e = Length; i != e; ++i) if (Data[i] == C) ++Count; return Count; } /// count - Return the number of non-overlapped occurrences of \arg Str in /// the string. size_t count(const StringRef &Str) const; /// getAsInteger - Parse the current string as an integer of the specified /// radix. If Radix is specified as zero, this does radix autosensing using /// extended C rules: 0 is octal, 0x is hex, 0b is binary. /// /// If the string is invalid or if only a subset of the string is valid, /// this returns true to signify the error. The string is considered /// erroneous if empty. /// bool getAsInteger(unsigned Radix, long long &Result) const; bool getAsInteger(unsigned Radix, unsigned long long &Result) const; bool getAsInteger(unsigned Radix, int &Result) const; bool getAsInteger(unsigned Radix, unsigned &Result) const; // TODO: Provide overloads for int/unsigned that check for overflow. /// @} /// @name Substring Operations /// @{ /// substr - Return a reference to the substring from [Start, Start + N). /// /// \param Start - The index of the starting character in the substring; if /// the index is npos or greater than the length of the string then the /// empty substring will be returned. /// /// \param N - The number of characters to included in the substring. If N /// exceeds the number of characters remaining in the string, the string /// suffix (starting with \arg Start) will be returned. StringRef substr(size_t Start, size_t N = npos) const { Start = std::min(Start, Length); return StringRef(Data + Start, std::min(N, Length - Start)); } /// slice - Return a reference to the substring from [Start, End). /// /// \param Start - The index of the starting character in the substring; if /// the index is npos or greater than the length of the string then the /// empty substring will be returned. /// /// \param End - The index following the last character to include in the /// substring. If this is npos, or less than \arg Start, or exceeds the /// number of characters remaining in the string, the string suffix /// (starting with \arg Start) will be returned. StringRef slice(size_t Start, size_t End) const { Start = std::min(Start, Length); End = std::min(std::max(Start, End), Length); return StringRef(Data + Start, End - Start); } /// split - Split into two substrings around the first occurence of a /// separator character. /// /// If \arg Separator is in the string, then the result is a pair (LHS, RHS) /// such that (*this == LHS + Separator + RHS) is true and RHS is /// maximal. If \arg Separator is not in the string, then the result is a /// pair (LHS, RHS) where (*this == LHS) and (RHS == ""). /// /// \param Separator - The character to split on. /// \return - The split substrings. std::pair split(char Separator) const { size_t Idx = find(Separator); if (Idx == npos) return std::make_pair(*this, StringRef()); return std::make_pair(slice(0, Idx), slice(Idx+1, npos)); } /// rsplit - Split into two substrings around the last occurence of a /// separator character. /// /// If \arg Separator is in the string, then the result is a pair (LHS, RHS) /// such that (*this == LHS + Separator + RHS) is true and RHS is /// minimal. If \arg Separator is not in the string, then the result is a /// pair (LHS, RHS) where (*this == LHS) and (RHS == ""). /// /// \param Separator - The character to split on. /// \return - The split substrings. std::pair rsplit(char Separator) const { size_t Idx = rfind(Separator); if (Idx == npos) return std::make_pair(*this, StringRef()); return std::make_pair(slice(0, Idx), slice(Idx+1, npos)); } /// @} }; /// @name StringRef Comparison Operators /// @{ inline bool operator==(const StringRef &LHS, const StringRef &RHS) { return LHS.equals(RHS); } inline bool operator!=(const StringRef &LHS, const StringRef &RHS) { return !(LHS == RHS); } inline bool operator<(const StringRef &LHS, const StringRef &RHS) { return LHS.compare(RHS) == -1; } inline bool operator<=(const StringRef &LHS, const StringRef &RHS) { return LHS.compare(RHS) != 1; } inline bool operator>(const StringRef &LHS, const StringRef &RHS) { return LHS.compare(RHS) == 1; } inline bool operator>=(const StringRef &LHS, const StringRef &RHS) { return LHS.compare(RHS) != -1; } /// @} } #endif