X-Git-Url: http://demsky.eecs.uci.edu/git/?a=blobdiff_plain;f=include%2Fllvm%2FADT%2FStringExtras.h;h=9503e0f805a76d5195e9fffcc63fa3943bc2807e;hb=255f89faee13dc491cb64fbeae3c763e7e2ea4e6;hp=e40e409802d25c1ab4b213227987c417fe7371db;hpb=07bf7efa0ac1f7ca8ca57a675dd8c6e2c52df73a;p=oota-llvm.git diff --git a/include/llvm/ADT/StringExtras.h b/include/llvm/ADT/StringExtras.h index e40e409802d..9503e0f805a 100644 --- a/include/llvm/ADT/StringExtras.h +++ b/include/llvm/ADT/StringExtras.h @@ -14,19 +14,17 @@ #ifndef LLVM_ADT_STRINGEXTRAS_H #define LLVM_ADT_STRINGEXTRAS_H +#include "llvm/ADT/StringRef.h" #include "llvm/Support/DataTypes.h" -#include "llvm/ADT/APFloat.h" -#include -#include -#include -#include namespace llvm { +template class SmallVectorImpl; -/// 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; +/// 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; } /// utohex_buffer - Emit the specified number into the buffer specified by @@ -55,15 +53,14 @@ static inline char *utohex_buffer(IntTy X, char *BufferEnd) { } static inline std::string utohexstr(uint64_t X) { - char Buffer[40]; - return utohex_buffer(X, Buffer+40); + 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) { @@ -73,17 +70,13 @@ static inline std::string utostr_32(uint32_t X, bool isNeg = false) { 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[21]; + char *BufPtr = Buffer+21; - char Buffer[40]; - char *BufPtr = Buffer+39; - - *BufPtr = 0; // Null terminate buffer... if (X == 0) *--BufPtr = '0'; // Handle special case... while (X) { @@ -92,7 +85,7 @@ static inline std::string utostr(uint64_t X, bool isNeg = false) { } if (isNeg) *--BufPtr = '-'; // Add negative sign... - return std::string(BufPtr); + return std::string(BufPtr, Buffer+21); } @@ -103,131 +96,57 @@ static inline std::string itostr(int64_t X) { return utostr(static_cast(X)); } -static inline std::string itohexstr(int64_t X) { - return utohexstr(static_cast(X)); -} - -static inline std::string ftostr(double V) { - char Buffer[200]; - sprintf(Buffer, "%20.6e", V); - char *B = Buffer; - while (*B == ' ') ++B; - return B; -} - -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 ""; // error -} - -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; -} - -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; -} - -/// 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(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(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? -} - -/// StringsEqualNoCase - Return true if the two null-terminated C strings are -/// equal, ignoring - -static inline bool StringsEqualNoCase(const char *LHS, const char *RHS, - unsigned len) { - - for (unsigned i = 0; i < len; ++i) { - if (tolower(LHS[i]) != tolower(RHS[i])) - return false; - - // If RHS[i] == 0 then LHS[i] == 0 or otherwise we would have returned - // at the previous branch as tolower('\0') == '\0'. - if (RHS[i] == 0) - return true; - } - - return true; -} - -/// CStrInCStrNoCase - Portable version of strcasestr. Locates the first -/// occurance of c-string 's2' in string 's1', ignoring case. Returns -/// NULL if 's2' cannot be found. -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. - ++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 's2' appears in 's1'. - return *I2 == '\0' ? s1 : 0; -} +/// 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 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 &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 &OutFragments, + StringRef Delimiters = " \t\n\v\f\r"); + +/// 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; +} + +/// 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"; + } + } +} } // End llvm namespace