X-Git-Url: http://demsky.eecs.uci.edu/git/?a=blobdiff_plain;f=include%2Fllvm%2FADT%2FStringRef.h;h=cd846031c5a02030e0b269033e89b51e32955fff;hb=58aae3841cb054e909d6b5251399bfd7478653bc;hp=a7442666d678d0f59c02e0f0ec8f255499f3e2cf;hpb=d5b1f8a8426e82990dafc6e3336fefc6635c8fa4;p=oota-llvm.git diff --git a/include/llvm/ADT/StringRef.h b/include/llvm/ADT/StringRef.h index a7442666d67..cd846031c5a 100644 --- a/include/llvm/ADT/StringRef.h +++ b/include/llvm/ADT/StringRef.h @@ -10,14 +10,27 @@ #ifndef LLVM_ADT_STRINGREF_H #define LLVM_ADT_STRINGREF_H +#include "llvm/Support/type_traits.h" + +#include #include #include -#include +#include #include +#include namespace llvm { template class SmallVectorImpl; + class APInt; + class hash_code; + class StringRef; + + /// Helper functions for StringRef::getAsInteger. + bool getAsUnsignedInteger(StringRef Str, unsigned Radix, + unsigned long long &Result); + + bool getAsSignedInteger(StringRef Str, unsigned Radix, long long &Result); /// StringRef - Represent a constant reference to a string, i.e. a character /// array and a length, which need not be null terminated. @@ -29,6 +42,7 @@ 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; @@ -42,16 +56,16 @@ namespace llvm { // 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; + 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) { + if (Length == 0) { return 0; } + return ::memcmp(Lhs,Rhs,Length); } - + public: /// @name Constructors /// @{ @@ -61,11 +75,17 @@ namespace llvm { /// Construct a string ref from a cstring. /*implicit*/ StringRef(const char *Str) - : Data(Str), Length(::strlen(Str)) {} + : Data(Str) { + assert(Str && "StringRef cannot be built from a NULL argument"); + Length = ::strlen(Str); // invoking strlen(NULL) is undefined behavior + } /// Construct a string ref from a pointer and length. /*implicit*/ StringRef(const char *data, size_t length) - : Data(data), Length(length) {} + : Data(data), Length(length) { + assert((data || length == 0) && + "StringRef cannot be built from a NULL argument with non-null length"); + } /// Construct a string ref from an std::string. /*implicit*/ StringRef(const std::string &Str) @@ -109,7 +129,7 @@ namespace llvm { /// 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); + compareMemory(Data, RHS.Data, RHS.Length) == 0); } /// equals_lower - Check for string equality, ignoring case. @@ -121,7 +141,7 @@ namespace llvm { /// 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, min(Length, RHS.Length))) + if (int Res = compareMemory(Data, RHS.Data, min(Length, RHS.Length))) return Res < 0 ? -1 : 1; // Otherwise the prefixes match, so we only need to check the lengths. @@ -133,8 +153,36 @@ namespace llvm { /// 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). + /// + /// \param MaxEditDistance If non-zero, the maximum edit distance that + /// this routine is allowed to compute. If the edit distance will exceed + /// that maximum, returns \c MaxEditDistance+1. + /// + /// \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, + unsigned MaxEditDistance = 0); + /// 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 @@ -160,13 +208,13 @@ namespace llvm { /// 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; + compareMemory(Data, Prefix.Data, Prefix.Length) == 0; } /// 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; + compareMemory(end() - Suffix.Length, Suffix.Data, Suffix.Length) == 0; } /// @} @@ -175,7 +223,7 @@ 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 = min(From, Length), e = Length; i != e; ++i) @@ -186,13 +234,13 @@ 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 = min(From, Length); @@ -207,18 +255,20 @@ 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 = 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 @@ -228,9 +278,31 @@ 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; + /// find_last_of - Find the last character in the string that is \arg C, or + /// npos if not found. + size_type find_last_of(char C, size_t From = npos) const { + return rfind(C, From); + } + + /// find_last_of - Find the last character in the string that is in \arg C, + /// or npos if not found. + /// + /// Note: O(size() + Chars.size()) + size_type find_last_of(StringRef Chars, size_t From = npos) const; + + /// find_last_not_of - Find the last character in the string that is not + /// \arg C, or npos if not found. + size_type find_last_not_of(char C, size_t From = npos) const; + + /// find_last_not_of - Find the last character in the string that is not in + /// \arg Chars, or npos if not found. + /// + /// Note: O(size() + Chars.size()) + size_type find_last_not_of(StringRef Chars, size_t From = npos) const; + /// @} /// @name Helpful Algorithms /// @{ @@ -254,14 +326,52 @@ namespace llvm { /// /// 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. + /// erroneous if empty or if it overflows T. /// - 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; + template + typename enable_if_c::is_signed, bool>::type + getAsInteger(unsigned Radix, T &Result) const { + long long LLVal; + if (getAsSignedInteger(*this, Radix, LLVal) || + static_cast(LLVal) != LLVal) + return true; + Result = LLVal; + return false; + } - // TODO: Provide overloads for int/unsigned that check for overflow. + template + typename enable_if_c::is_signed, bool>::type + getAsInteger(unsigned Radix, T &Result) const { + unsigned long long ULLVal; + if (getAsUnsignedInteger(*this, Radix, ULLVal) || + static_cast(ULLVal) != ULLVal) + return true; + Result = ULLVal; + return false; + } + + /// 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 String Operations + /// @{ + + // lower - Convert the given ASCII string to lowercase. + std::string lower() const; + + /// upper - Convert the given ASCII string to uppercase. + std::string upper() const; /// @} /// @name Substring Operations @@ -280,6 +390,20 @@ namespace llvm { Start = min(Start, Length); return StringRef(Data + Start, min(N, Length - Start)); } + + /// drop_front - Return a StringRef equal to 'this' but with the first + /// elements dropped. + StringRef drop_front(unsigned N = 1) const { + assert(size() >= N && "Dropping more elements than exist"); + return substr(N); + } + + /// drop_back - Return a StringRef equal to 'this' but with the last + /// elements dropped. + StringRef drop_back(unsigned N = 1) const { + assert(size() >= N && "Dropping more elements than exist"); + return substr(0, size()-N); + } /// slice - Return a reference to the substring from [Start, End). /// @@ -297,7 +421,7 @@ namespace llvm { 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) @@ -314,7 +438,7 @@ 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) @@ -331,7 +455,7 @@ namespace llvm { return std::make_pair(slice(0, Idx), slice(Idx + Separator.size(), npos)); } - /// split - Split into substrings around the occurences of a separator + /// 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 @@ -345,12 +469,12 @@ namespace llvm { /// \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. - /// \parm KeepEmpty - True if empty substring should be added. + /// \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 occurence of a + /// 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) @@ -367,6 +491,24 @@ namespace llvm { return std::make_pair(slice(0, Idx), slice(Idx+1, npos)); } + /// ltrim - Return string with consecutive characters in \arg Chars starting + /// from the left removed. + StringRef ltrim(StringRef Chars = " \t\n\v\f\r") const { + return drop_front(std::min(Length, find_first_not_of(Chars))); + } + + /// rtrim - Return string with consecutive characters in \arg Chars starting + /// from the right removed. + StringRef rtrim(StringRef Chars = " \t\n\v\f\r") const { + return drop_back(Length - std::min(Length, find_last_not_of(Chars) + 1)); + } + + /// trim - Return string with consecutive characters in \arg Chars starting + /// from the left and right removed. + StringRef trim(StringRef Chars = " \t\n\v\f\r") const { + return ltrim(Chars).rtrim(Chars); + } + /// @} }; @@ -397,8 +539,19 @@ namespace llvm { return LHS.compare(RHS) != -1; } + inline std::string &operator+=(std::string &buffer, llvm::StringRef string) { + return buffer.append(string.data(), string.size()); + } + /// @} + /// \brief Compute a hash_code for a StringRef. + hash_code hash_value(StringRef S); + + // StringRefs can be treated like a POD type. + template struct isPodLike; + template <> struct isPodLike { static const bool value = true; }; + } #endif