Class String

source/core/StarString.hpp:29–295

A Unicode string class, which is a basic UTF-8 aware wrapper around std::string. Provides methods for accessing UTF-32 "Char" type, which provides access to each individual code point. Printing, hashing, copying, and in-order access should be basically as fast as std::string, but the more complex string processing methods may be much worse. All case sensitive / insensitive functionality is base

// case insensitivity is really only appropriate for code / script processing,
// not for general strings.
class String {
public:
  typedef Utf32Type Char;

  // std::basic_string equivalent that guarantees const access time for
  // operator[], etc
  typedef std::basic_string<Char> WideString;

  typedef U8ToU32Iterator<std::string::const_iterator> const_iterator;
  typedef Char value_type;
  typedef value_type const& const_reference;

  enum CaseSensitivity {
    CaseSensitive,
    CaseInsensitive
  };

  // Space, horizontal tab, newline, carriage return, and BOM / ZWNBSP
  static bool isSpace(Char c);
  static bool isAsciiNumber(Char c);
  static bool isAsciiLetter(Char c);

  // These methods only actually work on unicode characters below 127, i.e.
  // ASCII subset.
  static Char toLower(Char c);
  static Char toUpper(Char c);
  static bool charEqual(Char c1, Char c2, CaseSensitivity cs);

  // Join two strings together with a joiner, so that only one instance of the
  // joiner is in between the left and right strings.  For example, joins "foo"
  // and "bar" with "?" to produce "foo?bar".  Gets rid of repeat joiners, so
  // "foo?" and "?bar" with "?" also becomes "foo?bar".  Also, if left or right
  // is empty, does not add a joiner, for example "" and "baz" joined with "?"
  // produces "baz".
  static String joinWith(String const& join, String const& left, String const& right);
  template <typename... StringType>
  static String joinWith(String const& join, String const& first, String const& second, String const& third, StringType const&... rest);

  String();
  String(String const& s);
  String(String&& s);

  // These assume utf8 input
  String(char const* s);
  String(char const* s, size_t n);
  String(std::string const& s);
  String(std::string&& s);

  String(std::wstring const& s);
  String(Char const* s);
  String(Char const* s, size_t n);
  String(Char c, size_t n);

  explicit String(Char c);

  // const& to internal utf8 data
  std::string const& utf8() const;
  std::string takeUtf8();