ucommon
ucommon/unicode.h
Go to the documentation of this file.
00001 // Copyright (C) 2009-2010 David Sugar, Tycho Softworks.
00002 //
00003 // This file is part of GNU uCommon C++.
00004 //
00005 // GNU uCommon C++ is free software: you can redistribute it and/or modify
00006 // it under the terms of the GNU Lesser General Public License as published
00007 // by the Free Software Foundation, either version 3 of the License, or
00008 // (at your option) any later version.
00009 //
00010 // GNU uCommon C++ is distributed in the hope that it will be useful,
00011 // but WITHOUT ANY WARRANTY; without even the implied warranty of
00012 // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
00013 // GNU Lesser General Public License for more details.
00014 //
00015 // You should have received a copy of the GNU Lesser General Public License
00016 // along with GNU uCommon C++.  If not, see <http://www.gnu.org/licenses/>.
00017 
00032 #ifndef _UCOMMON_UNICODE_H_
00033 #define _UCOMMON_UNICODE_H_
00034 
00035 #ifndef _UCOMMON_STRING_H_
00036 #include <ucommon/string.h>
00037 #endif
00038 
00039 NAMESPACE_UCOMMON
00040 
00045 typedef int32_t ucs4_t;
00046 
00050 typedef int16_t ucs2_t;
00051 
00055 typedef void *unicode_t;
00056 
00062 class __EXPORT utf8
00063 {
00064 public:
00068     static const unsigned ucsize;
00069 
00073     static const char *nil;
00074 
00080     static unsigned size(const char *codepoint);
00081 
00087     static size_t count(const char *string);
00088 
00095     static char *offset(char *string, ssize_t position);
00096 
00102     static ucs4_t codepoint(const char *encoded);
00103 
00109     static size_t chars(const unicode_t string);
00110 
00116     static size_t chars(ucs4_t character);
00117 
00124     static size_t unpack(const unicode_t string, CharacterProtocol& buffer);
00125 
00133     static size_t pack(unicode_t unicode, CharacterProtocol& buffer, size_t size);
00134 
00138     static ucs4_t *udup(const char *string);
00139 
00143     static ucs2_t *wdup(const char *string);
00144 
00152     static const char *find(const char *string, ucs4_t character, size_t start = 0);
00153 
00161     static const char *rfind(const char *string, ucs4_t character, size_t end = (size_t)-1l);
00162 
00169     static unsigned ccount(const char *string, ucs4_t character);
00170 
00176     static ucs4_t get(CharacterProtocol& buffer);
00177 
00184     static ucs4_t put(ucs4_t character, CharacterProtocol& buffer);
00185 };
00186 
00193 class __EXPORT UString : public String, public utf8
00194 {
00195 protected:
00199     UString();
00200 
00205     UString(strsize_t size);
00206 
00211     UString(const unicode_t text);
00212 
00219     UString(const char *text, strsize_t size);
00220 
00227     UString(const unicode_t *text, const unicode_t *end);
00228 
00234     UString(const UString& existing);
00235 
00240     virtual ~UString();
00241 
00248     UString get(strsize_t codepoint, strsize_t size = 0) const;
00249 
00256     size_t get(unicode_t unicode, size_t size) const;
00257 
00262     void set(const unicode_t unicode);
00263 
00268     void add(const unicode_t unicode);
00269 
00275     ucs4_t at(int position) const;
00276 
00283     inline size_t operator()(unicode_t unicode, size_t size) const
00284         {return get(unicode, size);};
00285 
00292     UString operator()(int codepoint, strsize_t size) const;
00293 
00301     const char *operator()(int offset) const;
00302 
00308     inline ucs4_t operator[](int position) const
00309         {return UString::at(position);};
00310 
00315     inline strsize_t count(void) const
00316         {return utf8::count(str->text);}
00317 
00323     unsigned ccount(ucs4_t character) const;
00324 
00331     const char *find(ucs4_t character, strsize_t start = 0) const;
00332 
00339     const char *rfind(ucs4_t character, strsize_t end = npos) const;
00340 };
00341 
00347 class __EXPORT utf8_pointer
00348 {
00349 protected:
00350     uint8_t *text;
00351 
00352 public:
00356     utf8_pointer();
00357 
00362     utf8_pointer(const char *string);
00363 
00368     utf8_pointer(const utf8_pointer& copy);
00369 
00374     utf8_pointer& operator ++();
00375 
00380     utf8_pointer& operator --();
00381 
00387     utf8_pointer& operator +=(long offset);
00388 
00394     utf8_pointer& operator -=(long offset);
00395 
00401     utf8_pointer operator+(long offset) const;
00402 
00408     utf8_pointer operator-(long offset) const;
00409 
00414     inline operator bool() const
00415         {return text != NULL;};
00416 
00421     inline bool operator!() const
00422         {return text == NULL;};
00423 
00429     ucs4_t operator[](long codepoint) const;
00430 
00436     utf8_pointer& operator=(const char *string);
00437 
00441     void inc(void);
00442 
00446     void dec(void);
00447 
00453     inline bool operator==(const char *string) const
00454         {return (const char *)text == string;};
00455 
00461     inline bool operator!=(const char *string) const
00462         {return (const char *)text != string;};
00463 
00468     inline  ucs4_t operator*() const
00469         {return utf8::codepoint((const char *)text);};
00470 
00475     inline char *c_str(void) const
00476         {return (char *)text;};
00477 
00482     inline operator char*() const
00483         {return (char *)text;};
00484 
00489     inline size_t len(void) const
00490         {return utf8::count((const char *)text);};
00491 };
00492 
00493 inline ucs4_t *strudup(const char *string)
00494     {return utf8::udup(string);}
00495 
00496 inline ucs2_t *strwdup(const char *string)
00497     {return utf8::wdup(string);}
00498 
00499 __EXPORT unicode_t unidup(const char *string);
00500 
00501 template<>
00502 inline void dupfree<ucs2_t*>(ucs2_t *string)
00503     {::free(string);}
00504 
00505 template<>
00506 inline void dupfree<ucs4_t*>(ucs4_t *string)
00507     {::free(string);}
00508 
00509 template<>
00510 inline void dupfree<unicode_t>(unicode_t string)
00511     {::free(string);}
00512 
00516 typedef UString ustring_t;
00517 
00521 typedef utf8_pointer utf8_t;
00522 
00523 END_NAMESPACE
00524 
00525 #endif