X-Git-Url: http://plrg.eecs.uci.edu/git/?p=oota-llvm.git;a=blobdiff_plain;f=include%2Fllvm%2FADT%2FStringRef.h;h=bc80946a9ea1bfa4700e83007213ad67e9d4914c;hp=5f3e5fba372606e2bc27107a000f0299de9738c1;hb=3dba3be8e521318a6d3000baaf1ce9c458c915f6;hpb=d61918fc6898a89df8b0a03e068f234ded010cdf diff --git a/include/llvm/ADT/StringRef.h b/include/llvm/ADT/StringRef.h index 5f3e5fba372..bc80946a9ea 100644 --- a/include/llvm/ADT/StringRef.h +++ b/include/llvm/ADT/StringRef.h @@ -10,12 +10,26 @@ #ifndef LLVM_ADT_STRINGREF_H #define LLVM_ADT_STRINGREF_H +#include "llvm/Support/Compiler.h" #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. @@ -27,7 +41,9 @@ 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; private: /// The start of the string, in an external buffer. @@ -36,24 +52,42 @@ namespace llvm { /// The length of the string. size_t Length; + // Workaround memcmp issue with null pointers (undefined behavior) + // by providing a specialized version + LLVM_ATTRIBUTE_ALWAYS_INLINE + 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 /// @{ /// Construct an empty string ref. - /*implicit*/ StringRef() : Data(0), Length(0) {} + LLVM_ATTRIBUTE_ALWAYS_INLINE + /*implicit*/ StringRef() : Data(nullptr), Length(0) {} /// Construct a string ref from a cstring. - /*implicit*/ StringRef(const char *Str) - : Data(Str), Length(::strlen(Str)) {} - + LLVM_ATTRIBUTE_ALWAYS_INLINE + /*implicit*/ StringRef(const char *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, unsigned _Length) - : Data(_Data), Length(_Length) {} + LLVM_ATTRIBUTE_ALWAYS_INLINE + /*implicit*/ StringRef(const char *data, size_t 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) - : Data(Str.c_str()), Length(Str.length()) {} + LLVM_ATTRIBUTE_ALWAYS_INLINE + /*implicit*/ StringRef(const std::string &Str) + : Data(Str.data()), Length(Str.length()) {} /// @} /// @name Iterators @@ -63,32 +97,68 @@ 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 /// @{ /// data - Get a pointer to the start of the string (which may not be null /// terminated). + LLVM_ATTRIBUTE_ALWAYS_INLINE const char *data() const { return Data; } /// empty - Check if the string is empty. + LLVM_ATTRIBUTE_ALWAYS_INLINE bool empty() const { return Length == 0; } /// size - Get the string size. + LLVM_ATTRIBUTE_ALWAYS_INLINE 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]; + } + + // 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() in when the relative ordering of inequal strings isn't needed. - bool equals(const StringRef &RHS) const { - return (Length == RHS.Length && - memcmp(Data, RHS.Data, Length) == 0); + /// compare() when the relative ordering of inequal strings isn't needed. + LLVM_ATTRIBUTE_ALWAYS_INLINE + bool equals(StringRef RHS) const { + return (Length == RHS.Length && + compareMemory(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 { + /// is lexicographically less than, equal to, or greater than the \p RHS. + LLVM_ATTRIBUTE_ALWAYS_INLINE + 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 = 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. @@ -97,16 +167,47 @@ 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). + /// + /// \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) const; + /// str - Get the contents as an std::string. - std::string str() const { return std::string(Data, Length); } + std::string str() const { + if (!Data) return std::string(); + return std::string(Data, Length); + } /// @} /// @name Operator Overloads /// @{ - char operator[](size_t Index) const { + char operator[](size_t Index) const { assert(Index < Length && "Invalid index!"); - return Data[Index]; + return Data[Index]; } /// @} @@ -118,60 +219,344 @@ namespace llvm { } /// @} - /// @name Utility Functions + /// @name String Predicates + /// @{ + + /// Check if this string starts with the given \p Prefix. + LLVM_ATTRIBUTE_ALWAYS_INLINE + bool startswith(StringRef Prefix) const { + return Length >= Prefix.Length && + 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. + LLVM_ATTRIBUTE_ALWAYS_INLINE + 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 + /// @{ + + /// Search for the first character \p C in the string. + /// + /// \returns The index of the first occurrence of \p C, or npos if not + /// found. + LLVM_ATTRIBUTE_ALWAYS_INLINE + size_t find(char C, size_t From = 0) const { + 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; + } + + /// Search for the first string \p Str in the string. + /// + /// \returns The index of the first occurrence of \p Str, or npos if not + /// found. + size_t find(StringRef Str, size_t From = 0) const; + + /// Search for the last character \p C in the string. + /// + /// \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 = std::min(From, Length); + size_t i = From; + while (i != 0) { + --i; + if (Data[i] == C) + return i; + } + return npos; + } + + /// Search for the last string \p Str in the string. + /// + /// \returns The index of the last occurrence of \p Str, or npos if not + /// found. + size_t rfind(StringRef Str) const; + + /// Find the first character in the string that is \p C, or npos if not + /// found. Same as find. + size_t find_first_of(char C, size_t From = 0) const { + return find(C, From); + } + + /// Find the first character in the string that is in \p Chars, or npos if + /// not found. + /// + /// Complexity: O(size() + Chars.size()) + size_t find_first_of(StringRef Chars, size_t From = 0) const; + + /// Find the first character in the string that is not \p C or npos if not + /// found. + size_t find_first_not_of(char C, size_t From = 0) const; + + /// Find the first character in the string that is not in the string + /// \p Chars, or npos if not found. + /// + /// Complexity: O(size() + Chars.size()) + size_t find_first_not_of(StringRef Chars, size_t From = 0) const; + + /// Find the last character in the string that is \p C, or npos if not + /// found. + size_t find_last_of(char C, size_t From = npos) const { + return rfind(C, From); + } + + /// Find the last character in the string that is in \p C, or npos if not + /// found. + /// + /// Complexity: O(size() + Chars.size()) + size_t find_last_of(StringRef Chars, size_t From = npos) const; + + /// Find the last character in the string that is not \p C, or npos if not + /// found. + size_t find_last_not_of(char C, size_t From = npos) const; + + /// Find the last character in the string that is not in \p Chars, or + /// npos if not found. + /// + /// Complexity: O(size() + Chars.size()) + size_t find_last_not_of(StringRef Chars, size_t From = npos) const; + + /// @} + /// @name Helpful Algorithms + /// @{ + + /// Return the number of occurrences of \p 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; + } + + /// Return the number of non-overlapped occurrences of \p Str in + /// the string. + size_t count(StringRef Str) const; + + /// Parse the current string as an integer of the specified radix. If + /// \p 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 or if it overflows T. + template + typename std::enable_if::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; + } + + template + 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(static_cast(ULLVal)) != ULLVal) + return true; + Result = ULLVal; + return false; + } + + /// Parse the current string as an integer of the specified \p Radix, or of + /// an autosensed radix if the \p Radix given is 0. The current value in + /// \p 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 + /// @{ + + // Convert the given ASCII string to lowercase. + std::string lower() const; + + /// Convert the given ASCII string to uppercase. + std::string upper() const; + + /// @} + /// @name Substring Operations /// @{ - /// substr - Return a reference to the substring from [Start, Start + N). + /// Return a reference to the substring from [Start, Start + N). /// - /// \param Start - The index of the starting character in the substring; if + /// \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 + /// \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. + /// suffix (starting with \p Start) will be returned. + LLVM_ATTRIBUTE_ALWAYS_INLINE 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). + /// Return a StringRef equal to 'this' but with the first \p N elements + /// dropped. + LLVM_ATTRIBUTE_ALWAYS_INLINE + StringRef drop_front(size_t N = 1) const { + assert(size() >= N && "Dropping more elements than exist"); + return substr(N); + } + + /// Return a StringRef equal to 'this' but with the last \p N elements + /// dropped. + LLVM_ATTRIBUTE_ALWAYS_INLINE + StringRef drop_back(size_t N = 1) const { + assert(size() >= N && "Dropping more elements than exist"); + return substr(0, size()-N); + } + + /// Return a reference to the substring from [Start, End). /// - /// \param Start - The index of the starting character in the substring; if + /// \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 + /// \param End The index following the last character to include in the + /// substring. If this is npos, or less than \p Start, or exceeds the /// number of characters remaining in the string, the string suffix - /// (starting with \arg Start) will be returned. + /// (starting with \p Start) will be returned. + LLVM_ATTRIBUTE_ALWAYS_INLINE 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. + /// Split into two substrings around the first occurrence of a separator + /// character. + /// + /// If \p 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 \p 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. + /// \returns 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 into two substrings around the first occurrence of a separator + /// string. + /// + /// If \p 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 \p 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 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 + 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, + 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 /// - /// If \arg Separator is in the string, then the result is a pair (LHS, RHS) + /// \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. + /// + /// If \p 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 + /// minimal. If \p 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 { - iterator it = std::find(begin(), end(), Separator); - if (it == end()) + std::pair rsplit(char Separator) const { + size_t Idx = rfind(Separator); + if (Idx == npos) return std::make_pair(*this, StringRef()); - return std::make_pair(StringRef(begin(), it - begin()), - StringRef(it + 1, end() - (it + 1))); + return std::make_pair(slice(0, Idx), slice(Idx+1, npos)); + } + + /// Return string with consecutive characters in \p 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))); + } + + /// Return string with consecutive characters in \p 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)); } - /// startswith - Check if this string starts with the given \arg Prefix. - bool startswith(const StringRef &Prefix) const { - return substr(0, Prefix.Length).equals(Prefix); + /// Return string with consecutive characters in \p Chars starting from + /// the left and right removed. + StringRef trim(StringRef Chars = " \t\n\v\f\r") const { + return ltrim(Chars).rtrim(Chars); } /// @} @@ -180,32 +565,44 @@ namespace llvm { /// @name StringRef Comparison Operators /// @{ - inline bool operator==(const StringRef &LHS, const StringRef &RHS) { + LLVM_ATTRIBUTE_ALWAYS_INLINE + inline bool operator==(StringRef LHS, StringRef RHS) { return LHS.equals(RHS); } - inline bool operator!=(const StringRef &LHS, const StringRef &RHS) { + LLVM_ATTRIBUTE_ALWAYS_INLINE + inline bool operator!=(StringRef LHS, StringRef RHS) { return !(LHS == RHS); } - - inline bool operator<(const StringRef &LHS, const StringRef &RHS) { - return LHS.compare(RHS) == -1; + + inline bool operator<(StringRef LHS, StringRef RHS) { + return LHS.compare(RHS) == -1; } - inline bool operator<=(const StringRef &LHS, const StringRef &RHS) { - return LHS.compare(RHS) != 1; + inline bool operator<=(StringRef LHS, StringRef RHS) { + return LHS.compare(RHS) != 1; } - inline bool operator>(const StringRef &LHS, const StringRef &RHS) { - return LHS.compare(RHS) == 1; + inline bool operator>(StringRef LHS, StringRef RHS) { + return LHS.compare(RHS) == 1; } - inline bool operator>=(const StringRef &LHS, const StringRef &RHS) { - return LHS.compare(RHS) != -1; + inline bool operator>=(StringRef LHS, StringRef RHS) { + return LHS.compare(RHS) != -1; + } + + inline std::string &operator+=(std::string &buffer, 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