X-Git-Url: https://git.dogcows.com/gitweb?a=blobdiff_plain;f=otk%2Fustring.hh;h=647bee86f641b69c99b24a5c9b0a80da14e23a70;hb=ef02a0c8ae65f169157c90064a335303e964a4c1;hp=5d011cfc8837a21e196b789168d91602db4a33e4;hpb=711e499c703c5bd3a12183c2cbbd3910c7aba99b;p=chaz%2Fopenbox diff --git a/otk/ustring.hh b/otk/ustring.hh index 5d011cfc..647bee86 100644 --- a/otk/ustring.hh +++ b/otk/ustring.hh @@ -7,6 +7,7 @@ */ extern "C" { +/* #ifdef HAVE_STDINT_H # include #else @@ -14,12 +15,23 @@ extern "C" { # include # endif #endif +*/ } #include namespace otk { +/* +#ifdef HAVE_STDINT_H +typedef uint32_t unichar; +#else +typedef u_int32_t unichar; +#endif +*/ + +#ifndef DOXYGEN_IGNORE + //! The number of bytes to skip to find the next character in the string const char g_utf8_skip[256] = { 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, @@ -32,11 +44,7 @@ const char g_utf8_skip[256] = { 3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,4,4,4,4,4,4,4,4,5,5,5,5,6,6,1,1 }; -#ifdef HAVE_STDINT_H -typedef uint32_t unichar; -#else -typedef u_int32_t unichar; -#endif +#endif // DOXYGEN_IGNORE //! The iterator type for ustring /*! @@ -49,20 +57,22 @@ typedef u_int32_t unichar; write operation would invalidate all other iterators pointing into the same string. */ +/* template class ustring_Iterator { public: typedef std::bidirectional_iterator_tag iterator_category; - typedef unichar value_type; + //typedef unichar value_type; typedef std::string::difference_type difference_type; - typedef value_type reference; + //typedef value_type reference; typedef void pointer; inline ustring_Iterator() {} inline ustring_Iterator(const ustring_Iterator& other) : _pos(other.base()) {} + inline value_type operator*() const { // get a unicode character from the iterator's position @@ -86,6 +96,7 @@ public: return result; } + inline ustring_Iterator & operator++() { pos_ += g_utf8_skip[static_cast(*pos_)]; return *this; @@ -101,9 +112,11 @@ public: private: T _pos; }; +*/ -//! This class provides a simple wrapper to a std::string that is encoded as -//! UTF-8. +//! This class provides a simple wrapper to a std::string that can be encoded +//! as UTF-8. The ustring::utf() member specifies if the given string is UTF-8 +//! encoded. ustrings default to specifying UTF-8 encoding. /*! This class does not handle extended 8-bit ASCII charsets like ISO-8859-1. @@ -116,17 +129,18 @@ private: */ class ustring { std::string _string; - + bool _utf8; + public: typedef std::string::size_type size_type; typedef std::string::difference_type difference_type; - typedef unichar value_type; - typedef unichar & reference; - typedef const unichar & const_reference; + //typedef unichar value_type; + //typedef unichar & reference; + //typedef const unichar & const_reference; - typedef ustring_Iterator iterator; - typedef ustring_Iterator const_iterator; + //typedef ustring_Iterator iterator; + //typedef ustring_Iterator const_iterator; static const size_type npos = std::string::npos; @@ -138,9 +152,40 @@ public: ustring(const ustring& other); ustring& operator=(const ustring& other); ustring(const std::string& src); - ustring::ustring(const char* src); + ustring(const char* src); + + // append to the string + + ustring& operator+=(const ustring& src); + ustring& operator+=(const char* src); + ustring& operator+=(char c); + + // sizes + + ustring::size_type size() const; + ustring::size_type bytes() const; + ustring::size_type capacity() const; + ustring::size_type max_size() const; + bool empty() const; + + // erase substrings + + void clear(); + ustring& erase(size_type i, size_type n=npos); + + // change the string's size + + void resize(size_type n, char c='\0'); + + // internal data + + const char* data() const; + const char* c_str() const; + // encoding + bool utf8() const; + void setUtf8(bool utf8); }; }