#ifndef LLVM_ADT_STRINGEXTRAS_H
#define LLVM_ADT_STRINGEXTRAS_H
-#include "llvm/Support/DataTypes.h"
+#include "llvm/System/DataTypes.h"
#include "llvm/ADT/APFloat.h"
+#include "llvm/ADT/StringRef.h"
#include <cctype>
#include <cstdio>
#include <string>
#include <vector>
namespace llvm {
+template<typename T> class SmallVectorImpl;
-static inline std::string utohexstr(uint64_t X) {
- char Buffer[40];
- char *BufPtr = Buffer+39;
+/// hexdigit - Return the (uppercase) hexadecimal character for the
+/// given number \arg X (which should be less than 16).
+static inline char hexdigit(unsigned X) {
+ return X < 10 ? '0' + X : 'A' + X - 10;
+}
- *BufPtr = 0; // Null terminate buffer...
- if (X == 0) *--BufPtr = '0'; // Handle special case...
+/// utohex_buffer - Emit the specified number into the buffer specified by
+/// BufferEnd, returning a pointer to the start of the string. This can be used
+/// like this: (note that the buffer must be large enough to handle any number):
+/// char Buffer[40];
+/// printf("0x%s", utohex_buffer(X, Buffer+40));
+///
+/// This should only be used with unsigned types.
+///
+template<typename IntTy>
+static inline char *utohex_buffer(IntTy X, char *BufferEnd) {
+ char *BufPtr = BufferEnd;
+ *--BufPtr = 0; // Null terminate buffer.
+ if (X == 0) {
+ *--BufPtr = '0'; // Handle special case.
+ return BufPtr;
+ }
while (X) {
unsigned char Mod = static_cast<unsigned char>(X) & 15;
- if (Mod < 10)
- *--BufPtr = '0' + Mod;
- else
- *--BufPtr = 'A' + Mod-10;
+ *--BufPtr = hexdigit(Mod);
X >>= 4;
}
- return std::string(BufPtr);
+ return BufPtr;
+}
+
+static inline std::string utohexstr(uint64_t X) {
+ char Buffer[17];
+ return utohex_buffer(X, Buffer+17);
}
static inline std::string utostr_32(uint32_t X, bool isNeg = false) {
- char Buffer[20];
- char *BufPtr = Buffer+19;
+ char Buffer[11];
+ char *BufPtr = Buffer+11;
- *BufPtr = 0; // Null terminate buffer...
if (X == 0) *--BufPtr = '0'; // Handle special case...
while (X) {
if (isNeg) *--BufPtr = '-'; // Add negative sign...
- return std::string(BufPtr);
+ return std::string(BufPtr, Buffer+11);
}
static inline std::string utostr(uint64_t X, bool isNeg = false) {
- if (X == uint32_t(X))
- return utostr_32(uint32_t(X), isNeg);
-
- char Buffer[40];
- char *BufPtr = Buffer+39;
-
- *BufPtr = 0; // Null terminate buffer...
+ char Buffer[21];
+ char *BufPtr = Buffer+21;
+
if (X == 0) *--BufPtr = '0'; // Handle special case...
-
+
while (X) {
*--BufPtr = '0' + char(X % 10);
X /= 10;
}
-
+
if (isNeg) *--BufPtr = '-'; // Add negative sign...
- return std::string(BufPtr);
+ return std::string(BufPtr, Buffer+21);
}
return utostr(static_cast<uint64_t>(X));
}
-static inline std::string itohexstr(int64_t X) {
- return utohexstr(static_cast<uint64_t>(X));
-}
-
static inline std::string ftostr(double V) {
char Buffer[200];
sprintf(Buffer, "%20.6e", V);
return result;
}
-/// StringsEqualNoCase - Return true if the two strings are equal, ignoring
-/// case.
-static inline bool StringsEqualNoCase(const std::string &LHS,
- const std::string &RHS) {
- if (LHS.size() != RHS.size()) return false;
- for (unsigned i = 0, e = static_cast<unsigned>(LHS.size()); i != e; ++i)
- if (tolower(LHS[i]) != tolower(RHS[i])) return false;
- return true;
-}
-
-/// StringsEqualNoCase - Return true if the two strings are equal, ignoring
-/// case.
-static inline bool StringsEqualNoCase(const std::string &LHS,
- const char *RHS) {
- for (unsigned i = 0, e = static_cast<unsigned>(LHS.size()); i != e; ++i) {
- if (RHS[i] == 0) return false; // RHS too short.
- if (tolower(LHS[i]) != tolower(RHS[i])) return false;
- }
- return RHS[LHS.size()] == 0; // Not too long?
-}
-
-/// CStrInCStrNoCase - Portable version of strcasestr. Locates the first
-/// occurance of c-string 's1' in string 's2', ignoring case. Returns
-/// NULL if 's1' cannot be found.
-static inline const char* CStrInCStrNoCase(const char *s1, const char *s2) {
-
- // Are either strings NULL?
- if (!s1 || !s2)
- return 0;
-
- const char *I1=s1, *I2=s2;
-
- while (*I1 != '\0' || *I2 != '\0' )
- if (tolower(*I1) != tolower(*I2)) { // No match. Start over.
- ++s1; I1 = s1; I2 = s2;
- }
- else { // Character match. Advance to the next character.
- ++I1; ++I2;
- }
-
- // If we exhausted all of the characters in 's2', then 's1' does not occur
- // in it.
- return *I2 == '\0' ? 0 : I1;
-}
+/// StrInStrNoCase - Portable version of strcasestr. Locates the first
+/// occurrence of string 's1' in string 's2', ignoring case. Returns
+/// the offset of s2 in s1 or npos if s2 cannot be found.
+StringRef::size_type StrInStrNoCase(StringRef s1, StringRef s2);
/// getToken - This function extracts one token from source, ignoring any
/// leading characters that appear in the Delimiters string, and ending the
/// token at any of the characters that appear in the Delimiters string. If
/// there are no tokens in the source string, an empty string is returned.
-/// The Source source string is updated in place to remove the returned string
-/// and any delimiter prefix from it.
-std::string getToken(std::string &Source,
- const char *Delimiters = " \t\n\v\f\r");
+/// The function returns a pair containing the extracted token and the
+/// remaining tail string.
+std::pair<StringRef, StringRef> getToken(StringRef Source,
+ StringRef Delimiters = " \t\n\v\f\r");
/// SplitString - Split up the specified string according to the specified
/// delimiters, appending the result fragments to the output list.
-void SplitString(const std::string &Source,
- std::vector<std::string> &OutFragments,
- const char *Delimiters = " \t\n\v\f\r");
-
-/// UnescapeString - Modify the argument string, turning two character sequences
-/// like '\\' 'n' into '\n'. This handles: \e \a \b \f \n \r \t \v \' \\ and
-/// \num (where num is a 1-3 byte octal value).
-void UnescapeString(std::string &Str);
-
-/// EscapeString - Modify the argument string, turning '\\' and anything that
-/// doesn't satisfy std::isprint into an escape sequence.
-void EscapeString(std::string &Str);
+void SplitString(StringRef Source,
+ SmallVectorImpl<StringRef> &OutFragments,
+ StringRef Delimiters = " \t\n\v\f\r");
+
+/// HashString - Hash funtion for strings.
+///
+/// This is the Bernstein hash function.
+//
+// FIXME: Investigate whether a modified bernstein hash function performs
+// better: http://eternallyconfuzzled.com/tuts/algorithms/jsw_tut_hashing.aspx
+// X*33+c -> X*33^c
+static inline unsigned HashString(StringRef Str, unsigned Result = 0) {
+ for (unsigned i = 0, e = Str.size(); i != e; ++i)
+ Result = Result * 33 + Str[i];
+ return Result;
+}
} // End llvm namespace