#ifndef LLVM_ADT_STRINGEXTRAS_H
#define LLVM_ADT_STRINGEXTRAS_H
+#include <iterator>
+#include "llvm/ADT/StringRef.h"
#include "llvm/Support/DataTypes.h"
-#include "llvm/ADT/APFloat.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 hexadecimal character for the
+/// given number \p X (which should be less than 16).
+static inline char hexdigit(unsigned X, bool LowerCase = false) {
+ const char HexChar = LowerCase ? 'a' : 'A';
+ return X < 10 ? '0' + X : HexChar + X - 10;
+}
- *BufPtr = 0; // Null terminate buffer...
- if (X == 0) *--BufPtr = '0'; // Handle special case...
+/// Interpret the given character \p C as a hexadecimal digit and return its
+/// value.
+///
+/// If \p C is not a valid hex digit, -1U is returned.
+static inline unsigned hexDigitValue(char C) {
+ if (C >= '0' && C <= '9') return C-'0';
+ if (C >= 'a' && C <= 'f') return C-'a'+10U;
+ if (C >= 'A' && C <= 'F') return C-'A'+10U;
+ return -1U;
+}
+
+/// 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));
-}
+/// 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);
-static inline std::string ftostr(double V) {
- char Buffer[200];
- sprintf(Buffer, "%20.6e", V);
- char *B = Buffer;
- while (*B == ' ') ++B;
- return B;
-}
+/// 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 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");
-static inline std::string ftostr(const APFloat& V) {
- if (&V.getSemantics() == &APFloat::IEEEdouble)
- return ftostr(V.convertToDouble());
- else if (&V.getSemantics() == &APFloat::IEEEsingle)
- return ftostr((double)V.convertToFloat());
- return "<unknown format in ftostr>"; // error
-}
+/// SplitString - Split up the specified string according to the specified
+/// delimiters, appending the result fragments to the output list.
+void SplitString(StringRef Source,
+ SmallVectorImpl<StringRef> &OutFragments,
+ StringRef Delimiters = " \t\n\v\f\r");
-static inline std::string LowercaseString(const std::string &S) {
- std::string result(S);
- for (unsigned i = 0; i < S.length(); ++i)
- if (isupper(result[i]))
- result[i] = char(tolower(result[i]));
- return result;
+/// HashString - Hash function 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 + (unsigned char)Str[i];
+ return Result;
}
-static inline std::string UppercaseString(const std::string &S) {
- std::string result(S);
- for (unsigned i = 0; i < S.length(); ++i)
- if (islower(result[i]))
- result[i] = char(toupper(result[i]));
- return result;
+/// Returns the English suffix for an ordinal integer (-st, -nd, -rd, -th).
+static inline StringRef getOrdinalSuffix(unsigned Val) {
+ // It is critically important that we do this perfectly for
+ // user-written sequences with over 100 elements.
+ switch (Val % 100) {
+ case 11:
+ case 12:
+ case 13:
+ return "th";
+ default:
+ switch (Val % 10) {
+ case 1: return "st";
+ case 2: return "nd";
+ case 3: return "rd";
+ default: return "th";
+ }
+ }
}
-/// 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;
+template <typename IteratorT>
+inline std::string join_impl(IteratorT Begin, IteratorT End,
+ StringRef Separator, std::input_iterator_tag) {
+ std::string S;
+ if (Begin == End)
+ return S;
+
+ S += (*Begin);
+ while (++Begin != End) {
+ S += Separator;
+ S += (*Begin);
+ }
+ return S;
}
-/// 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;
+template <typename IteratorT>
+inline std::string join_impl(IteratorT Begin, IteratorT End,
+ StringRef Separator, std::forward_iterator_tag) {
+ std::string S;
+ if (Begin == End)
+ return S;
+
+ size_t Len = (std::distance(Begin, End) - 1) * Separator.size();
+ for (IteratorT I = Begin; I != End; ++I)
+ Len += (*Begin).size();
+ S.reserve(Len);
+ S += (*Begin);
+ while (++Begin != End) {
+ S += Separator;
+ S += (*Begin);
}
- return RHS[LHS.size()] == 0; // Not too long?
+ return S;
}
-
-/// 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. NOTE: the arguments are provided
-/// in a different order than strcasestr.
-static inline const char* CStrInCStrNoCase(const char *s1, const char *s2) {
-
- // Are either strings NULL or empty?
- if (!s1 || !s2 || s1[0] == '\0' || s2[0] == '\0')
- return 0;
-
- if (s1 == s2)
- return s1;
-
- const char *I1=s1, *I2=s2;
-
- while (*I1 != '\0' || *I2 != '\0' )
- if (tolower(*I1) != tolower(*I2)) { // No match. Start over.
- ++s2; I1 = s1; I2 = s2;
- }
- else { // Character match. Advance to the next character.
- ++I1; ++I2;
- }
- // If we exhausted all of the characters in 's1', then 's1' appears in 's2'.
- return *I1 == '\0' ? s2 : 0;
+/// Joins the strings in the range [Begin, End), adding Separator between
+/// the elements.
+template <typename IteratorT>
+inline std::string join(IteratorT Begin, IteratorT End, StringRef Separator) {
+ typedef typename std::iterator_traits<IteratorT>::iterator_category tag;
+ return join_impl(Begin, End, Separator, tag());
}
-/// 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");
-
-/// 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);
-
} // End llvm namespace
#endif