//===- llvm/ADT/StringExtras.h - Useful string functions --------*- C++ -*-===// // // The LLVM Compiler Infrastructure // // This file is distributed under the University of Illinois Open Source // License. See LICENSE.TXT for details. // //===----------------------------------------------------------------------===// // // This file contains some functions that are useful when dealing with strings. // //===----------------------------------------------------------------------===// #ifndef LLVM_ADT_STRINGEXTRAS_H #define LLVM_ADT_STRINGEXTRAS_H #include "llvm/ADT/ArrayRef.h" #include "llvm/ADT/SmallString.h" #include "llvm/ADT/StringRef.h" #include "llvm/ADT/Twine.h" #include <cassert> #include <cstddef> #include <cstdint> #include <cstdlib> #include <cstring> #include <iterator> #include <string> #include <utility> namespace llvm { template<typename T> class SmallVectorImpl; class raw_ostream; /// hexdigit - Return the hexadecimal character for the /// given number \p X (which should be less than 16). inline char hexdigit(unsigned X, bool LowerCase = false) { const char HexChar = LowerCase ? 'a' : 'A'; return X < 10 ? '0' + X : HexChar + X - 10; } /// Given an array of c-style strings terminated by a null pointer, construct /// a vector of StringRefs representing the same strings without the terminating /// null string. inline std::vector<StringRef> toStringRefArray(const char *const *Strings) { std::vector<StringRef> Result; while (*Strings) Result.push_back(*Strings++); return Result; } /// Construct a string ref from a boolean. inline StringRef toStringRef(bool B) { return StringRef(B ? "true" : "false"); } /// Construct a string ref from an array ref of unsigned chars. inline StringRef toStringRef(ArrayRef<uint8_t> Input) { return StringRef(reinterpret_cast<const char *>(Input.begin()), Input.size()); } /// Construct a string ref from an array ref of unsigned chars. inline ArrayRef<uint8_t> arrayRefFromStringRef(StringRef Input) { return {Input.bytes_begin(), Input.bytes_end()}; } /// 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. 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; } /// Checks if character \p C is one of the 10 decimal digits. inline bool isDigit(char C) { return C >= '0' && C <= '9'; } /// Checks if character \p C is a hexadecimal numeric character. inline bool isHexDigit(char C) { return hexDigitValue(C) != -1U; } /// Checks if character \p C is a valid letter as classified by "C" locale. inline bool isAlpha(char C) { return ('a' <= C && C <= 'z') || ('A' <= C && C <= 'Z'); } /// Checks whether character \p C is either a decimal digit or an uppercase or /// lowercase letter as classified by "C" locale. inline bool isAlnum(char C) { return isAlpha(C) || isDigit(C); } /// Checks whether character \p C is valid ASCII (high bit is zero). inline bool isASCII(char C) { return static_cast<unsigned char>(C) <= 127; } /// Checks whether all characters in S are ASCII. inline bool isASCII(llvm::StringRef S) { for (char C : S) if (LLVM_UNLIKELY(!isASCII(C))) return false; return true; } /// Checks whether character \p C is printable. /// /// Locale-independent version of the C standard library isprint whose results /// may differ on different platforms. inline bool isPrint(char C) { unsigned char UC = static_cast<unsigned char>(C); return (0x20 <= UC) && (UC <= 0x7E); } /// Returns the corresponding lowercase character if \p x is uppercase. inline char toLower(char x) { if (x >= 'A' && x <= 'Z') return x - 'A' + 'a'; return x; } /// Returns the corresponding uppercase character if \p x is lowercase. inline char toUpper(char x) { if (x >= 'a' && x <= 'z') return x - 'a' + 'A'; return x; } inline std::string utohexstr(uint64_t X, bool LowerCase = false) { char Buffer[17]; char *BufPtr = std::end(Buffer); if (X == 0) *--BufPtr = '0'; while (X) { unsigned char Mod = static_cast<unsigned char>(X) & 15; *--BufPtr = hexdigit(Mod, LowerCase); X >>= 4; } return std::string(BufPtr, std::end(Buffer)); } /// Convert buffer \p Input to its hexadecimal representation. /// The returned string is double the size of \p Input. inline std::string toHex(StringRef Input, bool LowerCase = false) { static const char *const LUT = "0123456789ABCDEF"; const uint8_t Offset = LowerCase ? 32 : 0; size_t Length = Input.size(); std::string Output; Output.reserve(2 * Length); for (size_t i = 0; i < Length; ++i) { const unsigned char c = Input[i]; Output.push_back(LUT[c >> 4] | Offset); Output.push_back(LUT[c & 15] | Offset); } return Output; } inline std::string toHex(ArrayRef<uint8_t> Input, bool LowerCase = false) { return toHex(toStringRef(Input), LowerCase); } inline uint8_t hexFromNibbles(char MSB, char LSB) { unsigned U1 = hexDigitValue(MSB); unsigned U2 = hexDigitValue(LSB); assert(U1 != -1U && U2 != -1U); return static_cast<uint8_t>((U1 << 4) | U2); } /// Convert hexadecimal string \p Input to its binary representation. /// The return string is half the size of \p Input. inline std::string fromHex(StringRef Input) { if (Input.empty()) return std::string(); std::string Output; Output.reserve((Input.size() + 1) / 2); if (Input.size() % 2 == 1) { Output.push_back(hexFromNibbles('0', Input.front())); Input = Input.drop_front(); } assert(Input.size() % 2 == 0); while (!Input.empty()) { uint8_t Hex = hexFromNibbles(Input[0], Input[1]); Output.push_back(Hex); Input = Input.drop_front(2); } return Output; } /// Convert the string \p S to an integer of the specified type using /// the radix \p Base. If \p Base is 0, auto-detects the radix. /// Returns true if the number was successfully converted, false otherwise. template <typename N> bool to_integer(StringRef S, N &Num, unsigned Base = 0) { return !S.getAsInteger(Base, Num); } namespace detail { template <typename N> inline bool to_float(const Twine &T, N &Num, N (*StrTo)(const char *, char **)) { SmallString<32> Storage; StringRef S = T.toNullTerminatedStringRef(Storage); char *End; N Temp = StrTo(S.data(), &End); if (*End != '\0') return false; Num = Temp; return true; } } inline bool to_float(const Twine &T, float &Num) { return detail::to_float(T, Num, strtof); } inline bool to_float(const Twine &T, double &Num) { return detail::to_float(T, Num, strtod); } inline bool to_float(const Twine &T, long double &Num) { return detail::to_float(T, Num, strtold); } inline std::string utostr(uint64_t X, bool isNeg = false) { char Buffer[21]; char *BufPtr = std::end(Buffer); 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, std::end(Buffer)); } inline std::string itostr(int64_t X) { if (X < 0) return utostr(static_cast<uint64_t>(-X), true); else return utostr(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); /// 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"); /// 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"); /// Returns the English suffix for an ordinal integer (-st, -nd, -rd, -th). 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"; } } } /// Print each character of the specified string, escaping it if it is not /// printable or if it is an escape char. void printEscapedString(StringRef Name, raw_ostream &Out); /// Print each character of the specified string, escaping HTML special /// characters. void printHTMLEscaped(StringRef String, raw_ostream &Out); /// printLowerCase - Print each character as lowercase if it is uppercase. void printLowerCase(StringRef String, raw_ostream &Out); namespace detail { 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; } 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 S; } template <typename Sep> inline void join_items_impl(std::string &Result, Sep Separator) {} template <typename Sep, typename Arg> inline void join_items_impl(std::string &Result, Sep Separator, const Arg &Item) { Result += Item; } template <typename Sep, typename Arg1, typename... Args> inline void join_items_impl(std::string &Result, Sep Separator, const Arg1 &A1, Args &&... Items) { Result += A1; Result += Separator; join_items_impl(Result, Separator, std::forward<Args>(Items)...); } inline size_t join_one_item_size(char C) { return 1; } inline size_t join_one_item_size(const char *S) { return S ? ::strlen(S) : 0; } template <typename T> inline size_t join_one_item_size(const T &Str) { return Str.size(); } inline size_t join_items_size() { return 0; } template <typename A1> inline size_t join_items_size(const A1 &A) { return join_one_item_size(A); } template <typename A1, typename... Args> inline size_t join_items_size(const A1 &A, Args &&... Items) { return join_one_item_size(A) + join_items_size(std::forward<Args>(Items)...); } } // end namespace detail /// 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) { using tag = typename std::iterator_traits<IteratorT>::iterator_category; return detail::join_impl(Begin, End, Separator, tag()); } /// Joins the strings in the range [R.begin(), R.end()), adding Separator /// between the elements. template <typename Range> inline std::string join(Range &&R, StringRef Separator) { return join(R.begin(), R.end(), Separator); } /// Joins the strings in the parameter pack \p Items, adding \p Separator /// between the elements. All arguments must be implicitly convertible to /// std::string, or there should be an overload of std::string::operator+=() /// that accepts the argument explicitly. template <typename Sep, typename... Args> inline std::string join_items(Sep Separator, Args &&... Items) { std::string Result; if (sizeof...(Items) == 0) return Result; size_t NS = detail::join_one_item_size(Separator); size_t NI = detail::join_items_size(std::forward<Args>(Items)...); Result.reserve(NI + (sizeof...(Items) - 1) * NS + 1); detail::join_items_impl(Result, Separator, std::forward<Args>(Items)...); return Result; } } // end namespace llvm #endif // LLVM_ADT_STRINGEXTRAS_H