#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 <bitset>
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) {
- unsigned char LHC = ascii_tolower(Data[I]);
- unsigned char RHC = ascii_tolower(RHS.Data[I]);
+// strncasecmp() is not available on non-POSIX systems, so define an
+// alternative function here.
+static int ascii_strncasecmp(const char *LHS, const char *RHS, size_t Length) {
+ for (size_t I = 0; I < Length; ++I) {
+ unsigned char LHC = ascii_tolower(LHS[I]);
+ unsigned char RHC = ascii_tolower(RHS[I]);
if (LHC != RHC)
return LHC < RHC ? -1 : 1;
}
+ return 0;
+}
+/// compare_lower - Compare strings, ignoring case.
+int StringRef::compare_lower(StringRef RHS) const {
+ if (int Res = ascii_strncasecmp(Data, RHS.Data, std::min(Length, RHS.Length)))
+ return Res;
if (Length == RHS.Length)
return 0;
return Length < RHS.Length ? -1 : 1;
}
+/// Check if this string starts with the given \p Prefix, ignoring case.
+bool StringRef::startswith_lower(StringRef Prefix) const {
+ return Length >= Prefix.Length &&
+ ascii_strncasecmp(Data, Prefix.Data, Prefix.Length) == 0;
+}
+
+/// Check if this string ends with the given \p Suffix, ignoring case.
+bool StringRef::endswith_lower(StringRef Suffix) const {
+ return Length >= Suffix.Length &&
+ ascii_strncasecmp(end() - Suffix.Length, Suffix.Data, Suffix.Length) == 0;
+}
+
/// 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) {
+ for (size_t I = 0, E = std::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.
// Compute the edit distance between the two given strings.
unsigned StringRef::edit_distance(llvm::StringRef Other,
bool AllowReplacements,
- unsigned MaxEditDistance) {
+ unsigned MaxEditDistance) const {
return llvm::ComputeEditDistance(
- llvm::ArrayRef<char>(data(), size()),
- llvm::ArrayRef<char>(Other.data(), Other.size()),
+ makeArrayRef(data(), size()),
+ makeArrayRef(Other.data(), Other.size()),
AllowReplacements, MaxEditDistance);
}
/// \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 {
+ if (From > Length)
+ return npos;
+
+ const char *Needle = Str.data();
size_t N = Str.size();
- if (N > Length)
+ if (N == 0)
+ return From;
+
+ size_t Size = Length - From;
+ if (Size < N)
return npos;
+ const char *Start = Data + From;
+ const char *Stop = Start + (Size - N + 1);
+
// 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;
+ if (Size < 16 || N > 255) {
+ do {
+ if (std::memcmp(Start, Needle, N) == 0)
+ return Start - Data;
+ ++Start;
+ } while (Start < Stop);
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;
+ do {
+ if (std::memcmp(Start, Needle, N) == 0)
+ return Start - Data;
// Otherwise skip the appropriate number of bytes.
- uint8_t Skip = BadCharSkip[(uint8_t)(*this)[Pos+N-1]];
- Len -= Skip;
- Pos += Skip;
- }
+ Start += BadCharSkip[(uint8_t)Start[N-1]];
+ } while (Start < Stop);
return npos;
}
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)
+ for (size_type i = std::min(From, Length), e = Length; i != e; ++i)
if (CharBits.test((unsigned char)Data[i]))
return i;
return npos;
/// find_first_not_of - Find the first character in the string that is not
/// \arg C or npos if not found.
StringRef::size_type StringRef::find_first_not_of(char C, size_t From) const {
- for (size_type i = min(From, Length), e = Length; i != e; ++i)
+ for (size_type i = std::min(From, Length), e = Length; i != e; ++i)
if (Data[i] != C)
return i;
return npos;
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)
+ for (size_type i = std::min(From, Length), e = Length; i != e; ++i)
if (!CharBits.test((unsigned char)Data[i]))
return i;
return npos;
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)
+ for (size_type i = std::min(From, Length) - 1, e = -1; i != e; --i)
if (CharBits.test((unsigned char)Data[i]))
return i;
return npos;
}
+/// find_last_not_of - Find the last character in the string that is not
+/// \arg C, or npos if not found.
+StringRef::size_type StringRef::find_last_not_of(char C, size_t From) const {
+ for (size_type i = std::min(From, Length) - 1, e = -1; i != e; --i)
+ if (Data[i] != C)
+ return i;
+ return npos;
+}
+
+/// 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())
+StringRef::size_type StringRef::find_last_not_of(StringRef Chars,
+ size_t From) const {
+ std::bitset<1 << CHAR_BIT> CharBits;
+ for (size_type i = 0, e = Chars.size(); i != e; ++i)
+ CharBits.set((unsigned char)Chars[i]);
+
+ for (size_type i = std::min(From, Length) - 1, e = -1; i != e; --i)
+ if (!CharBits.test((unsigned char)Data[i]))
+ return i;
+ return npos;
+}
+
+void StringRef::split(SmallVectorImpl<StringRef> &A,
+ StringRef Separator, int MaxSplit,
+ bool KeepEmpty) const {
+ StringRef S = *this;
+
+ // Count down from MaxSplit. When MaxSplit is -1, this will just split
+ // "forever". This doesn't support splitting more than 2^31 times
+ // intentionally; if we ever want that we can make MaxSplit a 64-bit integer
+ // but that seems unlikely to be useful.
+ while (MaxSplit-- != 0) {
+ size_t Idx = S.find(Separator);
+ if (Idx == npos)
+ break;
+
+ // Push this split.
+ if (KeepEmpty || Idx > 0)
+ A.push_back(S.slice(0, Idx));
+
+ // Jump forward.
+ S = S.slice(Idx + Separator.size(), npos);
+ }
+
+ // Push the tail.
+ if (KeepEmpty || !S.empty())
+ A.push_back(S);
+}
+
+void StringRef::split(SmallVectorImpl<StringRef> &A, char Separator,
+ int MaxSplit, bool KeepEmpty) const {
+ StringRef S = *this;
+
+ // Count down from MaxSplit. When MaxSplit is -1, this will just split
+ // "forever". This doesn't support splitting more than 2^31 times
+ // intentionally; if we ever want that we can make MaxSplit a 64-bit integer
+ // but that seems unlikely to be useful.
+ while (MaxSplit-- != 0) {
+ size_t Idx = S.find(Separator);
+ if (Idx == npos)
+ break;
+
+ // Push this split.
+ if (KeepEmpty || Idx > 0)
+ A.push_back(S.slice(0, Idx));
+
+ // Jump forward.
+ S = S.slice(Idx + 1, npos);
+ }
+
+ // Push the tail.
+ if (KeepEmpty || !S.empty())
+ A.push_back(S);
+}
+
//===----------------------------------------------------------------------===//
// Helpful Algorithms
//===----------------------------------------------------------------------===//
if (Str.startswith("0x")) {
Str = Str.substr(2);
return 16;
- } else if (Str.startswith("0b")) {
+ }
+
+ if (Str.startswith("0b")) {
Str = Str.substr(2);
return 2;
- } else if (Str.startswith("0")) {
+ }
+
+ if (Str.startswith("0o")) {
+ Str = Str.substr(2);
return 8;
- } else {
- return 10;
}
+
+ if (Str.startswith("0"))
+ return 8;
+
+ return 10;
}
/// 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);
unsigned long long PrevResult = Result;
Result = Result*Radix+CharVal;
- // Check for overflow.
- if (Result < PrevResult)
+ // Check for overflow by shifting back and seeing if bits were lost.
+ if (Result/Radix < PrevResult)
return true;
Str = Str.substr(1);
return false;
}
-bool StringRef::getAsInteger(unsigned Radix, unsigned long long &Result) const {
- return GetAsUnsignedInteger(*this, Radix, Result);
-}
-
-
-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;
}
// 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.
return false;
}
-bool StringRef::getAsInteger(unsigned Radix, int &Result) const {
- long long Val;
- if (getAsInteger(Radix, Val) ||
- (int)Val != Val)
- return true;
- Result = Val;
- 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;
unsigned BitWidth = Log2Radix * Str.size();
if (BitWidth < Result.getBitWidth())
BitWidth = Result.getBitWidth(); // don't shrink the result
- else
+ else if (BitWidth > Result.getBitWidth())
Result = Result.zext(BitWidth);
APInt RadixAP, CharAP; // unused unless !IsPowerOf2Radix
return false;
}
+
+
+// Implementation of StringRef hashing.
+hash_code llvm::hash_value(StringRef S) {
+ return hash_combine_range(S.begin(), S.end());
+}
projects / oota-llvm.git / blobdiff