//===----------------------------------------------------------------------===//
#include "llvm/ADT/StringRef.h"
+#include "llvm/ADT/APInt.h"
+#include <bitset>
using namespace llvm;
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) {
return Length < RHS.Length ? -1 : 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) {
+ if (Data[I] == RHS.Data[I])
+ continue;
+ if (ascii_isdigit(Data[I]) && ascii_isdigit(RHS.Data[I])) {
+ // The longer sequence of numbers is larger. This doesn't really handle
+ // prefixed zeros well.
+ for (size_t 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;
+ }
+ }
+ return Data[I] < RHS.Data[I] ? -1 : 1;
+ }
+ if (Length == RHS.Length)
+ 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) {
/// 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;
}
/// 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;
}
return Count;
}
+static unsigned GetAutoSenseRadix(StringRef &Str) {
+ if (Str.startswith("0x")) {
+ Str = Str.substr(2);
+ return 16;
+ } else if (Str.startswith("0b")) {
+ Str = Str.substr(2);
+ return 2;
+ } else if (Str.startswith("0")) {
+ return 8;
+ } else {
+ 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) {
// Autosense radix if not specified.
- if (Radix == 0) {
- if (Str.startswith("0x")) {
- Str = Str.substr(2);
- Radix = 16;
- } else if (Str.startswith("0b")) {
- Str = Str.substr(2);
- Radix = 2;
- } else if (Str.startswith("0"))
- Radix = 8;
- else
- Radix = 10;
- }
+ if (Radix == 0)
+ Radix = GetAutoSenseRadix(Str);
// Empty strings (after the radix autosense) are invalid.
if (Str.empty()) return true;
Result = Val;
return false;
}
+
+bool StringRef::getAsInteger(unsigned Radix, APInt &Result) const {
+ StringRef Str = *this;
+
+ // Autosense radix if not specified.
+ if (Radix == 0)
+ Radix = GetAutoSenseRadix(Str);
+
+ assert(Radix > 1 && Radix <= 36);
+
+ // Empty strings (after the radix autosense) are invalid.
+ if (Str.empty()) return true;
+
+ // Skip leading zeroes. This can be a significant improvement if
+ // it means we don't need > 64 bits.
+ while (!Str.empty() && Str.front() == '0')
+ Str = Str.substr(1);
+
+ // If it was nothing but zeroes....
+ if (Str.empty()) {
+ Result = APInt(64, 0);
+ return false;
+ }
+
+ // (Over-)estimate the required number of bits.
+ unsigned Log2Radix = 0;
+ while ((1U << Log2Radix) < Radix) Log2Radix++;
+ bool IsPowerOf2Radix = ((1U << Log2Radix) == Radix);
+
+ unsigned BitWidth = Log2Radix * Str.size();
+ if (BitWidth < Result.getBitWidth())
+ BitWidth = Result.getBitWidth(); // don't shrink the result
+ else
+ Result.zext(BitWidth);
+
+ APInt RadixAP, CharAP; // unused unless !IsPowerOf2Radix
+ if (!IsPowerOf2Radix) {
+ // These must have the same bit-width as Result.
+ RadixAP = APInt(BitWidth, Radix);
+ CharAP = APInt(BitWidth, 0);
+ }
+
+ // Parse all the bytes of the string given this radix.
+ Result = 0;
+ while (!Str.empty()) {
+ unsigned CharVal;
+ if (Str[0] >= '0' && Str[0] <= '9')
+ CharVal = Str[0]-'0';
+ else if (Str[0] >= 'a' && Str[0] <= 'z')
+ CharVal = Str[0]-'a'+10;
+ else if (Str[0] >= 'A' && Str[0] <= 'Z')
+ 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;
+ Result |= CharVal;
+ } else {
+ Result *= RadixAP;
+ CharAP = CharVal;
+ Result += CharAP;
+ }
+
+ Str = Str.substr(1);
+ }
+
+ return false;
+}