X-Git-Url: http://demsky.eecs.uci.edu/git/?a=blobdiff_plain;f=include%2Fllvm%2FADT%2FStringRef.h;h=925777000f52e00c7a0d10c4d0d0a48c57c92eb7;hb=a03948633ae848af9cecce0a8042c7db4dac44d9;hp=11903bef79da451b94e778ff52f7028f126c280e;hpb=f5fdf73238dfd923f33bcbbd397cff6752d9c41e;p=oota-llvm.git diff --git a/include/llvm/ADT/StringRef.h b/include/llvm/ADT/StringRef.h index 11903bef79d..925777000f5 100644 --- a/include/llvm/ADT/StringRef.h +++ b/include/llvm/ADT/StringRef.h @@ -10,10 +10,15 @@ #ifndef LLVM_ADT_STRINGREF_H #define LLVM_ADT_STRINGREF_H +#include #include +#include #include namespace llvm { + template + class SmallVectorImpl; + class APInt; /// StringRef - Represent a constant reference to a string, i.e. a character /// array and a length, which need not be null terminated. @@ -25,7 +30,9 @@ namespace llvm { class StringRef { public: typedef const char *iterator; - static const size_t npos = std::string::npos; + typedef const char *const_iterator; + static const size_t npos = ~size_t(0); + typedef size_t size_type; private: /// The start of the string, in an external buffer. @@ -34,6 +41,12 @@ 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. + size_t min(size_t a, size_t b) const { return a < b ? a : b; } + size_t max(size_t a, size_t b) const { return a > b ? a : b; } + public: /// @name Constructors /// @{ @@ -42,16 +55,16 @@ namespace llvm { /*implicit*/ StringRef() : Data(0), Length(0) {} /// Construct a string ref from a cstring. - /*implicit*/ StringRef(const char *Str) + /*implicit*/ StringRef(const char *Str) : Data(Str), Length(::strlen(Str)) {} - + /// Construct a string ref from a pointer and length. - /*implicit*/ StringRef(const char *_Data, unsigned _Length) - : Data(_Data), Length(_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()) {} + /*implicit*/ StringRef(const std::string &Str) + : Data(Str.data()), Length(Str.length()) {} /// @} /// @name Iterators @@ -73,13 +86,37 @@ namespace llvm { bool empty() const { return Length == 0; } /// size - Get the string size. - unsigned size() const { return Length; } + 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(StringRef RHS) const { + return (Length == RHS.Length && + memcmp(Data, RHS.Data, RHS.Length) == 0); + } + + /// equals_lower - Check for string equality, ignoring case. + bool equals_lower(StringRef RHS) const { + return Length == RHS.Length && compare_lower(RHS) == 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 { + int compare(StringRef RHS) const { // Check the prefix for a mismatch. - if (int Res = memcmp(Data, RHS.Data, std::min(Length, RHS.Length))) + if (int Res = memcmp(Data, RHS.Data, min(Length, RHS.Length))) return Res < 0 ? -1 : 1; // Otherwise the prefixes match, so we only need to check the lengths. @@ -88,6 +125,25 @@ namespace llvm { return Length < RHS.Length ? -1 : 1; } + /// compare_lower - Compare two strings, ignoring case. + int compare_lower(StringRef RHS) const; + + /// \brief Determine the edit distance between this string and another + /// string. + /// + /// \param Other the string to compare this string against. + /// + /// \param AllowReplacements whether to allow character + /// replacements (change one character into another) as a single + /// operation, rather than as two operations (an insertion and a + /// removal). + /// + /// \returns the minimum number of character insertions, removals, + /// or (if \p AllowReplacements is \c true) replacements needed to + /// transform one of the given strings into the other. If zero, + /// the strings are identical. + unsigned edit_distance(StringRef Other, bool AllowReplacements = true); + /// str - Get the contents as an std::string. std::string str() const { return std::string(Data, Length); } @@ -95,59 +151,278 @@ namespace llvm { /// @name Operator Overloads /// @{ - bool operator==(const StringRef &RHS) const { - return Length == RHS.Length && memcmp(Data, RHS.Data, Length) == 0; + char operator[](size_t Index) const { + assert(Index < Length && "Invalid index!"); + return Data[Index]; + } + + /// @} + /// @name Type Conversions + /// @{ + + operator std::string() const { + return str(); } - bool operator!=(const StringRef &RHS) const { return !(*this == RHS); } + /// @} + /// @name String Predicates + /// @{ + + /// startswith - Check if this string starts with the given \arg Prefix. + bool startswith(StringRef Prefix) const { + return Length >= Prefix.Length && + memcmp(Data, Prefix.Data, Prefix.Length) == 0; + } - bool operator<(const StringRef &RHS) const { return compare(RHS) == -1; } + /// endswith - Check if this string ends with the given \arg Suffix. + bool endswith(StringRef Suffix) const { + return Length >= Suffix.Length && + memcmp(end() - Suffix.Length, Suffix.Data, Suffix.Length) == 0; + } - bool operator<=(const StringRef &RHS) const { return compare(RHS) != 1; } + /// @} + /// @name String Searching + /// @{ - bool operator>(const StringRef &RHS) const { return compare(RHS) == 1; } + /// find - Search for the first character \arg C in the string. + /// + /// \return - The index of the first occurrence of \arg 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; + return npos; + } - bool operator>=(const StringRef &RHS) const { return compare(RHS) != -1; } + /// find - Search for the first string \arg Str in the string. + /// + /// \return - The index of the first occurrence of \arg Str, or npos if not + /// found. + size_t find(StringRef Str, size_t From = 0) const; - char operator[](size_t Index) const { - assert(Index < Length && "Invalid index!"); - return Data[Index]; + /// rfind - Search for the last character \arg C in the string. + /// + /// \return - The index of the last occurrence of \arg C, or npos if not + /// found. + size_t rfind(char C, size_t From = npos) const { + From = 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 occurrence of \arg Str, or npos if not + /// found. + size_t rfind(StringRef Str) const; + + /// find_first_of - Find the first character in the string that is \arg C, + /// or npos if not found. Same as find. + size_type find_first_of(char C, size_t = 0) const { return find(C); } + + /// find_first_of - Find the first character in the string that is in \arg + /// Chars, or npos if not found. + /// + /// Note: O(size() * Chars.size()) + size_type find_first_of(StringRef Chars, size_t From = 0) const; + + /// find_first_not_of - Find the first character in the string that is not + /// \arg C or npos if not found. + size_type find_first_not_of(char C, size_t From = 0) const; + + /// find_first_not_of - Find the first character in the string that is not + /// in the string \arg Chars, or npos if not found. + /// + /// Note: O(size() * Chars.size()) + size_type find_first_not_of(StringRef Chars, size_t From = 0) const; + /// @} - /// @name Type Conversions + /// @name Helpful Algorithms /// @{ - operator std::string() const { - return str(); + /// 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(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. + + /// getAsInteger - Parse the current string as an integer of the + /// specified radix, or of an autosensed radix if the radix given + /// is 0. The current value in Result is discarded, and the + /// storage is changed to be wide enough to store the parsed + /// integer. + /// + /// Returns true if the string does not solely consist of a valid + /// non-empty number in the appropriate base. + /// + /// APInt::fromString is superficially similar but assumes the + /// string is well-formed in the given radix. + bool getAsInteger(unsigned Radix, APInt &Result) const; + /// @} - /// @name Utility Functions + /// @name Substring Operations /// @{ - /// substr - Return a reference to a substring of this object. + /// 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 greater than the length of the string then the empty - /// substring will be returned. + /// 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)); + Start = min(Start, Length); + return StringRef(Data + Start, min(N, Length - Start)); } - /// startswith - Check if this string starts with the given \arg Prefix. - bool startswith(const StringRef &Prefix) const { - return substr(0, Prefix.Length) == Prefix; + /// 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 = min(Start, Length); + End = min(max(Start, End), Length); + return StringRef(Data + Start, End - Start); + } + + /// split - Split into two substrings around the first occurrence 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)); + } + + /// split - Split into two substrings around the first occurrence of a + /// separator string. + /// + /// 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 string to split on. + /// \return - The split substrings. + std::pair split(StringRef 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 + Separator.size(), npos)); + } + + /// split - Split into substrings around the occurrences of a separator + /// string. + /// + /// Each substring is stored in \arg A. If \arg MaxSplit is >= 0, at most + /// \arg MaxSplit splits are done and consequently <= \arg MaxSplit + /// elements are added to A. + /// If \arg KeepEmpty is false, empty strings are not added to \arg A. They + /// still count when considering \arg 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, + StringRef Separator, int MaxSplit = -1, + bool KeepEmpty = true) const; + + /// rsplit - Split into two substrings around the last occurrence 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==(StringRef LHS, StringRef RHS) { + return LHS.equals(RHS); + } + + inline bool operator!=(StringRef LHS, StringRef RHS) { + return !(LHS == RHS); + } + + inline bool operator<(StringRef LHS, StringRef RHS) { + return LHS.compare(RHS) == -1; + } + + inline bool operator<=(StringRef LHS, StringRef RHS) { + return LHS.compare(RHS) != 1; + } + + inline bool operator>(StringRef LHS, StringRef RHS) { + return LHS.compare(RHS) == 1; + } + + inline bool operator>=(StringRef LHS, StringRef RHS) { + return LHS.compare(RHS) != -1; + } + + /// @} + } #endif