X-Git-Url: http://demsky.eecs.uci.edu/git/?a=blobdiff_plain;f=include%2Fllvm%2FADT%2FStringRef.h;h=8386d3ee428b1401643d4c6c3eba60b30ade39a1;hb=4c099b8724abf993262366e2a871004a2777becb;hp=12e2c569def56ec063ecc7a7587df498bfbc1465;hpb=a8333d3d107df1e0b6bde986ed0532915e154b65;p=oota-llvm.git diff --git a/include/llvm/ADT/StringRef.h b/include/llvm/ADT/StringRef.h index 12e2c569def..8386d3ee428 100644 --- a/include/llvm/ADT/StringRef.h +++ b/include/llvm/ADT/StringRef.h @@ -10,12 +10,15 @@ #ifndef LLVM_ADT_STRINGREF_H #define LLVM_ADT_STRINGREF_H -#include #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. @@ -27,6 +30,7 @@ namespace llvm { class StringRef { public: typedef const char *iterator; + typedef const char *const_iterator; static const size_t npos = ~size_t(0); typedef size_t size_type; @@ -37,6 +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. + 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; } + public: /// @name Constructors /// @{ @@ -46,7 +56,7 @@ namespace llvm { /// Construct a string ref from a cstring. /*implicit*/ StringRef(const char *Str) - : Data(Str) { if (Str) Length = ::strlen(Str); else Length = 0; } + : Data(Str), Length(::strlen(Str)) {} /// Construct a string ref from a pointer and length. /*implicit*/ StringRef(const char *data, size_t length) @@ -54,7 +64,7 @@ namespace llvm { /// Construct a string ref from an std::string. /*implicit*/ StringRef(const std::string &Str) - : Data(Str.c_str()), Length(Str.length()) {} + : Data(Str.data()), Length(Str.length()) {} /// @} /// @name Iterators @@ -97,11 +107,16 @@ namespace llvm { 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(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. @@ -110,8 +125,34 @@ namespace llvm { return Length < RHS.Length ? -1 : 1; } + /// compare_lower - Compare two strings, ignoring case. + int compare_lower(StringRef RHS) const; + + /// compare_numeric - Compare two strings, treating sequences of digits as + /// numbers. + int compare_numeric(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); } + std::string str() const { + if (Data == 0) return std::string(); + return std::string(Data, Length); + } /// @} /// @name Operator Overloads @@ -136,12 +177,14 @@ namespace llvm { /// startswith - Check if this string starts with the given \arg Prefix. bool startswith(StringRef Prefix) const { - return substr(0, Prefix.Length).equals(Prefix); + return Length >= Prefix.Length && + memcmp(Data, Prefix.Data, Prefix.Length) == 0; } /// endswith - Check if this string ends with the given \arg Suffix. bool endswith(StringRef Suffix) const { - return slice(size() - Suffix.Length, size()).equals(Suffix); + return Length >= Suffix.Length && + memcmp(end() - Suffix.Length, Suffix.Data, Suffix.Length) == 0; } /// @} @@ -150,10 +193,10 @@ namespace llvm { /// 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 + /// \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 = std::min(From, Length), e = Length; i != e; ++i) + for (size_t i = min(From, Length), e = Length; i != e; ++i) if (Data[i] == C) return i; return npos; @@ -161,16 +204,16 @@ namespace llvm { /// 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 + /// \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; /// 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 + /// \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 = std::min(From, Length); + From = min(From, Length); size_t i = From; while (i != 0) { --i; @@ -182,18 +225,20 @@ namespace llvm { /// 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 + /// \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 From = 0) const { return find(C); } + size_type find_first_of(char C, size_t From = 0) const { + return find(C, From); + } /// 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()) + /// 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 @@ -203,7 +248,7 @@ namespace llvm { /// 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()) + /// Note: O(size() + Chars.size()) size_type find_first_not_of(StringRef Chars, size_t From = 0) const; /// @} @@ -238,6 +283,19 @@ namespace llvm { // 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 Substring Operations /// @{ @@ -252,8 +310,8 @@ namespace llvm { /// 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)); } /// slice - Return a reference to the substring from [Start, End). @@ -267,12 +325,12 @@ namespace llvm { /// 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); + Start = min(Start, Length); + End = min(max(Start, End), Length); return StringRef(Data + Start, End - Start); } - /// split - Split into two substrings around the first occurence of a + /// 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) @@ -289,7 +347,7 @@ namespace llvm { return std::make_pair(slice(0, Idx), slice(Idx+1, npos)); } - /// split - Split into two substrings around the first occurence of a + /// 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) @@ -306,7 +364,26 @@ namespace llvm { return std::make_pair(slice(0, Idx), slice(Idx + Separator.size(), npos)); } - /// rsplit - Split into two substrings around the last occurence of a + /// 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)