X-Git-Url: http://demsky.eecs.uci.edu/git/?a=blobdiff_plain;f=lib%2FSupport%2FStringRef.cpp;h=abe570f6df4bedf163f2d66bc90869327ac5428b;hb=a9498a2ee63f11ca925497199b96abcefdd70582;hp=2b262dcd3fa71445425f61672760f65d07dc4e6b;hpb=1e7ad3993d8700488895fa372ecad55443f53485;p=oota-llvm.git diff --git a/lib/Support/StringRef.cpp b/lib/Support/StringRef.cpp index 2b262dcd3fa..abe570f6df4 100644 --- a/lib/Support/StringRef.cpp +++ b/lib/Support/StringRef.cpp @@ -9,6 +9,10 @@ #include "llvm/ADT/StringRef.h" #include "llvm/ADT/APInt.h" +#include "llvm/ADT/OwningPtr.h" +#include "llvm/ADT/Hashing.h" +#include "llvm/ADT/edit_distance.h" +#include using namespace llvm; @@ -23,67 +27,88 @@ static char ascii_tolower(char x) { return x; } +static char ascii_toupper(char x) { + if (x >= 'a' && x <= 'z') + return x - 'a' + 'A'; + return x; +} + +static bool ascii_isdigit(char x) { + return x >= '0' && x <= '9'; +} + /// compare_lower - Compare strings, ignoring case. int StringRef::compare_lower(StringRef RHS) const { for (size_t I = 0, E = min(Length, RHS.Length); I != E; ++I) { - char LHC = ascii_tolower(Data[I]); - char RHC = ascii_tolower(RHS.Data[I]); + unsigned char LHC = ascii_tolower(Data[I]); + unsigned char RHC = ascii_tolower(RHS.Data[I]); if (LHC != RHC) return LHC < RHC ? -1 : 1; } if (Length == RHS.Length) - return 0; + return 0; return Length < RHS.Length ? -1 : 1; } -// Compute the edit distance between the two given strings. -unsigned StringRef::edit_distance(llvm::StringRef Other, - bool AllowReplacements) { - // The algorithm implemented below is the "classic" - // dynamic-programming algorithm for computing the Levenshtein - // distance, which is described here: - // - // http://en.wikipedia.org/wiki/Levenshtein_distance - // - // Although the algorithm is typically described using an m x n - // array, only two rows are used at a time, so this implemenation - // just keeps two separate vectors for those two rows. - size_type m = size(); - size_type n = Other.size(); - - const unsigned SmallBufferSize = 64; - unsigned SmallBuffer[SmallBufferSize]; - unsigned *Allocated = 0; - unsigned *previous = SmallBuffer; - if (2*(n + 1) > SmallBufferSize) - Allocated = previous = new unsigned [2*(n+1)]; - unsigned *current = previous + (n + 1); - - for (unsigned i = 0; i <= n; ++i) - previous[i] = i; - - for (size_type y = 1; y <= m; ++y) { - current[0] = y; - for (size_type x = 1; x <= n; ++x) { - if (AllowReplacements) { - current[x] = min(previous[x-1] + ((*this)[y-1] == Other[x-1]? 0u:1u), - min(current[x-1], previous[x])+1); - } - else { - if ((*this)[y-1] == Other[x-1]) current[x] = previous[x-1]; - else current[x] = min(current[x-1], previous[x]) + 1; +/// compare_numeric - Compare strings, handle embedded numbers. +int StringRef::compare_numeric(StringRef RHS) const { + for (size_t I = 0, E = min(Length, RHS.Length); I != E; ++I) { + // Check for sequences of digits. + if (ascii_isdigit(Data[I]) && ascii_isdigit(RHS.Data[I])) { + // The longer sequence of numbers is considered larger. + // This doesn't really handle prefixed zeros well. + size_t J; + for (J = I + 1; J != E + 1; ++J) { + bool ld = J < Length && ascii_isdigit(Data[J]); + bool rd = J < RHS.Length && ascii_isdigit(RHS.Data[J]); + if (ld != rd) + return rd ? -1 : 1; + if (!rd) + break; } + // The two number sequences have the same length (J-I), just memcmp them. + if (int Res = compareMemory(Data + I, RHS.Data + I, J - I)) + return Res < 0 ? -1 : 1; + // Identical number sequences, continue search after the numbers. + I = J - 1; + continue; } - - unsigned *tmp = current; - current = previous; - previous = tmp; + if (Data[I] != RHS.Data[I]) + return (unsigned char)Data[I] < (unsigned char)RHS.Data[I] ? -1 : 1; } + if (Length == RHS.Length) + return 0; + return Length < RHS.Length ? -1 : 1; +} - unsigned Result = previous[n]; - delete [] Allocated; - +// Compute the edit distance between the two given strings. +unsigned StringRef::edit_distance(llvm::StringRef Other, + bool AllowReplacements, + unsigned MaxEditDistance) { + return llvm::ComputeEditDistance( + llvm::ArrayRef(data(), size()), + llvm::ArrayRef(Other.data(), Other.size()), + AllowReplacements, MaxEditDistance); +} + +//===----------------------------------------------------------------------===// +// String Operations +//===----------------------------------------------------------------------===// + +std::string StringRef::lower() const { + std::string Result(size(), char()); + for (size_type i = 0, e = size(); i != e; ++i) { + Result[i] = ascii_tolower(Data[i]); + } + return Result; +} + +std::string StringRef::upper() const { + std::string Result(size(), char()); + for (size_type i = 0, e = size(); i != e; ++i) { + Result[i] = ascii_toupper(Data[i]); + } return Result; } @@ -94,21 +119,47 @@ unsigned StringRef::edit_distance(llvm::StringRef Other, /// 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 StringRef::find(StringRef Str, size_t From) const { size_t N = Str.size(); if (N > Length) return npos; - for (size_t e = Length - N + 1, i = min(From, e); i != e; ++i) - if (substr(i, N).equals(Str)) - return i; + + // For short haystacks or unsupported needles fall back to the naive algorithm + if (Length < 16 || N > 255 || N == 0) { + for (size_t e = Length - N + 1, i = min(From, e); i != e; ++i) + if (substr(i, N).equals(Str)) + return i; + return npos; + } + + if (From >= Length) + return npos; + + // Build the bad char heuristic table, with uint8_t to reduce cache thrashing. + uint8_t BadCharSkip[256]; + std::memset(BadCharSkip, N, 256); + for (unsigned i = 0; i != N-1; ++i) + BadCharSkip[(uint8_t)Str[i]] = N-1-i; + + unsigned Len = Length-From, Pos = From; + while (Len >= N) { + if (substr(Pos, N).equals(Str)) // See if this is the correct substring. + return Pos; + + // Otherwise skip the appropriate number of bytes. + uint8_t Skip = BadCharSkip[(uint8_t)(*this)[Pos+N-1]]; + Len -= Skip; + Pos += Skip; + } + 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 +/// \return - The index of the last occurrence of \arg Str, or npos if not /// found. size_t StringRef::rfind(StringRef Str) const { size_t N = Str.size(); @@ -125,11 +176,15 @@ size_t StringRef::rfind(StringRef Str) const { /// 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()) StringRef::size_type StringRef::find_first_of(StringRef Chars, size_t From) const { + std::bitset<1 << CHAR_BIT> CharBits; + for (size_type i = 0; i != Chars.size(); ++i) + CharBits.set((unsigned char)Chars[i]); + for (size_type i = min(From, Length), e = Length; i != e; ++i) - if (Chars.find(Data[i]) != npos) + if (CharBits.test((unsigned char)Data[i])) return i; return npos; } @@ -146,15 +201,55 @@ StringRef::size_type StringRef::find_first_not_of(char C, size_t From) 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()) +/// Note: O(size() + Chars.size()) StringRef::size_type StringRef::find_first_not_of(StringRef Chars, size_t From) const { + std::bitset<1 << CHAR_BIT> CharBits; + for (size_type i = 0; i != Chars.size(); ++i) + CharBits.set((unsigned char)Chars[i]); + for (size_type i = min(From, Length), e = Length; i != e; ++i) - if (Chars.find(Data[i]) == npos) + if (!CharBits.test((unsigned char)Data[i])) return i; return npos; } +/// 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()) +StringRef::size_type StringRef::find_last_of(StringRef Chars, + size_t From) const { + std::bitset<1 << CHAR_BIT> CharBits; + for (size_type i = 0; i != Chars.size(); ++i) + CharBits.set((unsigned char)Chars[i]); + + for (size_type i = min(From, Length) - 1, e = -1; i != e; --i) + if (CharBits.test((unsigned char)Data[i])) + return i; + return npos; +} + +void StringRef::split(SmallVectorImpl &A, + StringRef Separators, int MaxSplit, + bool KeepEmpty) const { + StringRef rest = *this; + + // rest.data() is used to distinguish cases like "a," that splits into + // "a" + "" and "a" that splits into "a" + 0. + for (int splits = 0; + rest.data() != NULL && (MaxSplit < 0 || splits < MaxSplit); + ++splits) { + std::pair p = rest.split(Separators); + + if (KeepEmpty || p.first.size() != 0) + A.push_back(p.first); + rest = p.second; + } + // If we have a tail left, add it. + if (rest.data() != NULL && (rest.size() != 0 || KeepEmpty)) + A.push_back(rest); +} //===----------------------------------------------------------------------===// // Helpful Algorithms @@ -190,15 +285,15 @@ static unsigned GetAutoSenseRadix(StringRef &Str) { /// GetAsUnsignedInteger - Workhorse method that converts a integer character /// sequence of radix up to 36 to an unsigned long long value. -static bool GetAsUnsignedInteger(StringRef Str, unsigned Radix, - unsigned long long &Result) { +bool llvm::getAsUnsignedInteger(StringRef Str, unsigned Radix, + unsigned long long &Result) { // Autosense radix if not specified. if (Radix == 0) Radix = GetAutoSenseRadix(Str); - + // Empty strings (after the radix autosense) are invalid. if (Str.empty()) return true; - + // Parse all the bytes of the string given this radix. Watch for overflow. Result = 0; while (!Str.empty()) { @@ -211,74 +306,52 @@ static bool GetAsUnsignedInteger(StringRef Str, unsigned Radix, CharVal = Str[0]-'A'+10; else return true; - + // If the parsed value is larger than the integer radix, the string is // invalid. if (CharVal >= Radix) return true; - + // Add in this character. unsigned long long PrevResult = Result; Result = Result*Radix+CharVal; - + // Check for overflow. if (Result < PrevResult) return true; Str = Str.substr(1); } - - return false; -} -bool StringRef::getAsInteger(unsigned Radix, unsigned long long &Result) const { - return GetAsUnsignedInteger(*this, Radix, Result); + return false; } - -bool StringRef::getAsInteger(unsigned Radix, long long &Result) const { +bool llvm::getAsSignedInteger(StringRef Str, unsigned Radix, + long long &Result) { unsigned long long ULLVal; - + // Handle positive strings first. - if (empty() || front() != '-') { - if (GetAsUnsignedInteger(*this, Radix, ULLVal) || + if (Str.empty() || Str.front() != '-') { + if (getAsUnsignedInteger(Str, Radix, ULLVal) || // Check for value so large it overflows a signed value. (long long)ULLVal < 0) return true; Result = ULLVal; return false; } - + // Get the positive part of the value. - if (GetAsUnsignedInteger(substr(1), Radix, ULLVal) || + if (getAsUnsignedInteger(Str.substr(1), Radix, ULLVal) || // Reject values so large they'd overflow as negative signed, but allow // "-0". This negates the unsigned so that the negative isn't undefined // on signed overflow. (long long)-ULLVal > 0) return true; - - Result = -ULLVal; - return false; -} -bool StringRef::getAsInteger(unsigned Radix, int &Result) const { - long long Val; - if (getAsInteger(Radix, Val) || - (int)Val != Val) - return true; - Result = Val; + Result = -ULLVal; return false; } -bool StringRef::getAsInteger(unsigned Radix, unsigned &Result) const { - unsigned long long Val; - if (getAsInteger(Radix, Val) || - (unsigned)Val != Val) - return true; - Result = Val; - return false; -} - bool StringRef::getAsInteger(unsigned Radix, APInt &Result) const { StringRef Str = *this; @@ -287,7 +360,7 @@ bool StringRef::getAsInteger(unsigned Radix, APInt &Result) const { Radix = GetAutoSenseRadix(Str); assert(Radix > 1 && Radix <= 36); - + // Empty strings (after the radix autosense) are invalid. if (Str.empty()) return true; @@ -311,7 +384,7 @@ bool StringRef::getAsInteger(unsigned Radix, APInt &Result) const { if (BitWidth < Result.getBitWidth()) BitWidth = Result.getBitWidth(); // don't shrink the result else - Result.zext(BitWidth); + Result = Result.zext(BitWidth); APInt RadixAP, CharAP; // unused unless !IsPowerOf2Radix if (!IsPowerOf2Radix) { @@ -332,12 +405,12 @@ bool StringRef::getAsInteger(unsigned Radix, APInt &Result) const { CharVal = Str[0]-'A'+10; else return true; - + // If the parsed value is larger than the integer radix, the string is // invalid. if (CharVal >= Radix) return true; - + // Add in this character. if (IsPowerOf2Radix) { Result <<= Log2Radix; @@ -350,6 +423,12 @@ bool StringRef::getAsInteger(unsigned Radix, APInt &Result) const { Str = Str.substr(1); } - + return false; } + + +// Implementation of StringRef hashing. +hash_code llvm::hash_value(StringRef S) { + return hash_combine_range(S.begin(), S.end()); +}