StringRef.h

Go to the documentation of this file.

//===--- StringRef.h - Constant String Reference Wrapper --------*- C++ -*-===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//

#ifndef LLVM_ADT_STRINGREF_H
#define LLVM_ADT_STRINGREF_H

#include <cassert>
#include <cstring>
#include <utility>
#include <string>

namespace llvm {
  template<typename T>
  class SmallVectorImpl;
  class APInt;

  class StringRef {
  public:
    typedef const char *iterator;
    typedef const char *const_iterator;
    static const size_t npos = ~size_t(0);
    typedef size_t size_type;

  private:
    const char *Data;

    size_t Length;

    // Workaround PR5482: nearly all gcc 4.x miscompile StringRef and std::min()
    // Changing the arg of min to be an integer, instead of a reference to an
    // integer works around this bug.
    static size_t min(size_t a, size_t b) { return a < b ? a : b; }
    static size_t max(size_t a, size_t b) { return a > b ? a : b; }
    
    // Workaround memcmp issue with null pointers (undefined behavior)
    // by providing a specialized version
    static int compareMemory(const char *Lhs, const char *Rhs, size_t Length) {
      if (Length == 0) { return 0; }
      return ::memcmp(Lhs,Rhs,Length);
    }
    
  public:

    /*implicit*/ StringRef() : Data(0), Length(0) {}

    /*implicit*/ StringRef(const char *Str)
      : Data(Str) {
        assert(Str && "StringRef cannot be built from a NULL argument");
        Length = ::strlen(Str); // invoking strlen(NULL) is undefined behavior
      }

    /*implicit*/ StringRef(const char *data, size_t length)
      : Data(data), Length(length) {
        assert((data || length == 0) &&
        "StringRef cannot be built from a NULL argument with non-null length");
      }

    /*implicit*/ StringRef(const std::string &Str)
      : Data(Str.data()), Length(Str.length()) {}


    iterator begin() const { return Data; }

    iterator end() const { return Data + Length; }


    const char *data() const { return Data; }

    bool empty() const { return Length == 0; }

    size_t size() const { return Length; }

    char front() const {
      assert(!empty());
      return Data[0];
    }

    char back() const {
      assert(!empty());
      return Data[Length-1];
    }

    bool equals(StringRef RHS) const {
      return (Length == RHS.Length &&
              compareMemory(Data, RHS.Data, RHS.Length) == 0);
    }

    bool equals_lower(StringRef RHS) const {
      return Length == RHS.Length && compare_lower(RHS) == 0;
    }

    int compare(StringRef RHS) const {
      // Check the prefix for a mismatch.
      if (int Res = compareMemory(Data, RHS.Data, min(Length, RHS.Length)))
        return Res < 0 ? -1 : 1;

      // Otherwise the prefixes match, so we only need to check the lengths.
      if (Length == RHS.Length)
        return 0;
      return Length < RHS.Length ? -1 : 1;
    }

    int compare_lower(StringRef RHS) const;

    int compare_numeric(StringRef RHS) const;

    unsigned edit_distance(StringRef Other, bool AllowReplacements = true,
                           unsigned MaxEditDistance = 0);

    std::string str() const {
      if (Data == 0) return std::string();
      return std::string(Data, Length);
    }


    char operator[](size_t Index) const {
      assert(Index < Length && "Invalid index!");
      return Data[Index];
    }


    operator std::string() const {
      return str();
    }


    bool startswith(StringRef Prefix) const {
      return Length >= Prefix.Length &&
             compareMemory(Data, Prefix.Data, Prefix.Length) == 0;
    }

    bool endswith(StringRef Suffix) const {
      return Length >= Suffix.Length &&
        compareMemory(end() - Suffix.Length, Suffix.Data, Suffix.Length) == 0;
    }


    size_t find(char C, size_t From = 0) const {
      for (size_t i = min(From, Length), e = Length; i != e; ++i)
        if (Data[i] == C)
          return i;
      return npos;
    }

    size_t find(StringRef Str, size_t From = 0) const;

    size_t rfind(char C, size_t From = npos) const {
      From = min(From, Length);
      size_t i = From;
      while (i != 0) {
        --i;
        if (Data[i] == C)
          return i;
      }
      return npos;
    }

    size_t rfind(StringRef Str) const;

    size_type find_first_of(char C, size_t From = 0) const {
      return find(C, From);
    }

    size_type find_first_of(StringRef Chars, size_t From = 0) const;

    size_type find_first_not_of(char C, size_t From = 0) const;

    size_type find_first_not_of(StringRef Chars, size_t From = 0) const;

    size_type find_last_of(char C, size_t From = npos) const {
      return rfind(C, From);
    }

    size_type find_last_of(StringRef Chars, size_t From = npos) const;


    size_t count(char C) const {
      size_t Count = 0;
      for (size_t i = 0, e = Length; i != e; ++i)
        if (Data[i] == C)
          ++Count;
      return Count;
    }

    size_t count(StringRef Str) const;

    bool getAsInteger(unsigned Radix, long long &Result) const;
    bool getAsInteger(unsigned Radix, unsigned long long &Result) const;
    bool getAsInteger(unsigned Radix, int &Result) const;
    bool getAsInteger(unsigned Radix, unsigned &Result) const;

    // TODO: Provide overloads for int/unsigned that check for overflow.

    bool getAsInteger(unsigned Radix, APInt &Result) const;


    StringRef substr(size_t Start, size_t N = npos) const {
      Start = min(Start, Length);
      return StringRef(Data + Start, min(N, Length - Start));
    }

    StringRef slice(size_t Start, size_t End) const {
      Start = min(Start, Length);
      End = min(max(Start, End), Length);
      return StringRef(Data + Start, End - Start);
    }

    std::pair<StringRef, StringRef> split(char Separator) const {
      size_t Idx = find(Separator);
      if (Idx == npos)
        return std::make_pair(*this, StringRef());
      return std::make_pair(slice(0, Idx), slice(Idx+1, npos));
    }

    std::pair<StringRef, StringRef> split(StringRef Separator) const {
      size_t Idx = find(Separator);
      if (Idx == npos)
        return std::make_pair(*this, StringRef());
      return std::make_pair(slice(0, Idx), slice(Idx + Separator.size(), npos));
    }

    void split(SmallVectorImpl<StringRef> &A,
               StringRef Separator, int MaxSplit = -1,
               bool KeepEmpty = true) const;

    std::pair<StringRef, StringRef> rsplit(char Separator) const {
      size_t Idx = rfind(Separator);
      if (Idx == npos)
        return std::make_pair(*this, StringRef());
      return std::make_pair(slice(0, Idx), slice(Idx+1, npos));
    }

  };


  inline bool operator==(StringRef LHS, StringRef RHS) {
    return LHS.equals(RHS);
  }

  inline bool operator!=(StringRef LHS, StringRef RHS) {
    return !(LHS == RHS);
  }

  inline bool operator<(StringRef LHS, StringRef RHS) {
    return LHS.compare(RHS) == -1;
  }

  inline bool operator<=(StringRef LHS, StringRef RHS) {
    return LHS.compare(RHS) != 1;
  }

  inline bool operator>(StringRef LHS, StringRef RHS) {
    return LHS.compare(RHS) == 1;
  }

  inline bool operator>=(StringRef LHS, StringRef RHS) {
    return LHS.compare(RHS) != -1;
  }

  inline std::string &operator+=(std::string &buffer, llvm::StringRef string) {
    return buffer.append(string.data(), string.size());
  }


  // StringRefs can be treated like a POD type.
  template <typename T> struct isPodLike;
  template <> struct isPodLike<StringRef> { static const bool value = true; };

}

#endif

---