diff options
Diffstat (limited to 'Source/Asura.Engine/Text')
| -rw-r--r-- | Source/Asura.Engine/Text/Glyph.cpp | 0 | ||||
| -rw-r--r-- | Source/Asura.Engine/Text/Glyph.h | 0 | ||||
| -rw-r--r-- | Source/Asura.Engine/Text/String.cpp | 376 | ||||
| -rw-r--r-- | Source/Asura.Engine/Text/String.hpp | 594 | ||||
| -rw-r--r-- | Source/Asura.Engine/Text/String.inl | 29 | ||||
| -rw-r--r-- | Source/Asura.Engine/Text/Utf.hpp | 720 | ||||
| -rw-r--r-- | Source/Asura.Engine/Text/Utf.inl | 752 |
7 files changed, 0 insertions, 2471 deletions
diff --git a/Source/Asura.Engine/Text/Glyph.cpp b/Source/Asura.Engine/Text/Glyph.cpp deleted file mode 100644 index e69de29..0000000 --- a/Source/Asura.Engine/Text/Glyph.cpp +++ /dev/null diff --git a/Source/Asura.Engine/Text/Glyph.h b/Source/Asura.Engine/Text/Glyph.h deleted file mode 100644 index e69de29..0000000 --- a/Source/Asura.Engine/Text/Glyph.h +++ /dev/null diff --git a/Source/Asura.Engine/Text/String.cpp b/Source/Asura.Engine/Text/String.cpp deleted file mode 100644 index 8c9c55a..0000000 --- a/Source/Asura.Engine/Text/String.cpp +++ /dev/null @@ -1,376 +0,0 @@ -#include "String.hpp" -#include "Utf.hpp" - -namespace AsuraEngine -{ - namespace Text - { - - - //////////////////////////////////////////////////////////// - const std::size_t String::InvalidPos = std::basic_string<uint32>::npos; - - - //////////////////////////////////////////////////////////// - String::String() - { - } - - - //////////////////////////////////////////////////////////// - String::String(char ansiChar, const std::locale& locale) - { - mString += Utf32::DecodeAnsi(ansiChar, locale); - } - - - //////////////////////////////////////////////////////////// - String::String(wchar_t wideChar) - { - mString += Utf32::DecodeWide(wideChar); - } - - - //////////////////////////////////////////////////////////// - String::String(uint32 utf32Char) - { - mString += utf32Char; - } - - - //////////////////////////////////////////////////////////// - String::String(const char* ansiString, const std::locale& locale) - { - if (ansiString) - { - std::size_t length = strlen(ansiString); - if (length > 0) - { - mString.reserve(length + 1); - Utf32::FromAnsi(ansiString, ansiString + length, std::back_inserter(mString), locale); - } - } - } - - - //////////////////////////////////////////////////////////// - String::String(const std::string& ansiString, const std::locale& locale) - { - mString.reserve(ansiString.length() + 1); - Utf32::FromAnsi(ansiString.begin(), ansiString.end(), std::back_inserter(mString), locale); - } - - - //////////////////////////////////////////////////////////// - String::String(const wchar_t* wideString) - { - if (wideString) - { - std::size_t length = std::wcslen(wideString); - if (length > 0) - { - mString.reserve(length + 1); - Utf32::FromWide(wideString, wideString + length, std::back_inserter(mString)); - } - } - } - - - //////////////////////////////////////////////////////////// - String::String(const std::wstring& wideString) - { - mString.reserve(wideString.length() + 1); - Utf32::FromWide(wideString.begin(), wideString.end(), std::back_inserter(mString)); - } - - - //////////////////////////////////////////////////////////// - String::String(const uint32* utf32String) - { - if (utf32String) - mString = utf32String; - } - - - //////////////////////////////////////////////////////////// - String::String(const std::basic_string<uint32>& utf32String) : - mString(utf32String) - { - } - - - //////////////////////////////////////////////////////////// - String::String(const String& copy) : - mString(copy.mString) - { - } - - - //////////////////////////////////////////////////////////// - String::operator std::string() const - { - return ToAnsiString(); - } - - - //////////////////////////////////////////////////////////// - String::operator std::wstring() const - { - return ToWideString(); - } - - - //////////////////////////////////////////////////////////// - std::string String::ToAnsiString(const std::locale& locale) const - { - // Prepare the output string - std::string output; - output.reserve(mString.length() + 1); - - // Convert - Utf32::ToAnsi(mString.begin(), mString.end(), std::back_inserter(output), 0, locale); - - return output; - } - - - //////////////////////////////////////////////////////////// - std::wstring String::ToWideString() const - { - // Prepare the output string - std::wstring output; - output.reserve(mString.length() + 1); - - // Convert - Utf32::ToWide(mString.begin(), mString.end(), std::back_inserter(output), 0); - - return output; - } - - - //////////////////////////////////////////////////////////// - std::basic_string<uint8> String::ToUtf8() const - { - // Prepare the output string - std::basic_string<uint8> output; - output.reserve(mString.length()); - - // Convert - Utf32::ToUtf8(mString.begin(), mString.end(), std::back_inserter(output)); - - return output; - } - - - //////////////////////////////////////////////////////////// - std::basic_string<uint16> String::ToUtf16() const - { - // Prepare the output string - std::basic_string<uint16> output; - output.reserve(mString.length()); - - // Convert - Utf32::ToUtf16(mString.begin(), mString.end(), std::back_inserter(output)); - - return output; - } - - - //////////////////////////////////////////////////////////// - std::basic_string<uint32> String::ToUtf32() const - { - return mString; - } - - - //////////////////////////////////////////////////////////// - String& String::operator =(const String& right) - { - mString = right.mString; - return *this; - } - - - //////////////////////////////////////////////////////////// - String& String::operator +=(const String& right) - { - mString += right.mString; - return *this; - } - - - //////////////////////////////////////////////////////////// - uint32 String::operator [](std::size_t index) const - { - return mString[index]; - } - - - //////////////////////////////////////////////////////////// - uint32& String::operator [](std::size_t index) - { - return mString[index]; - } - - - //////////////////////////////////////////////////////////// - void String::Clear() - { - mString.clear(); - } - - - //////////////////////////////////////////////////////////// - std::size_t String::GetSize() const - { - return mString.size(); - } - - - //////////////////////////////////////////////////////////// - bool String::IsEmpty() const - { - return mString.empty(); - } - - - //////////////////////////////////////////////////////////// - void String::Erase(std::size_t position, std::size_t count) - { - mString.erase(position, count); - } - - - //////////////////////////////////////////////////////////// - void String::Insert(std::size_t position, const String& str) - { - mString.insert(position, str.mString); - } - - - //////////////////////////////////////////////////////////// - std::size_t String::Find(const String& str, std::size_t start) const - { - return mString.find(str.mString, start); - } - - - //////////////////////////////////////////////////////////// - void String::Replace(std::size_t position, std::size_t length, const String& replaceWith) - { - mString.replace(position, length, replaceWith.mString); - } - - - //////////////////////////////////////////////////////////// - void String::Replace(const String& searchFor, const String& replaceWith) - { - std::size_t step = replaceWith.GetSize(); - std::size_t len = searchFor.GetSize(); - std::size_t pos = Find(searchFor); - - // Replace each occurrence of search - while (pos != InvalidPos) - { - Replace(pos, len, replaceWith); - pos = Find(searchFor, pos + step); - } - } - - - //////////////////////////////////////////////////////////// - String String::Substring(std::size_t position, std::size_t length) const - { - return mString.substr(position, length); - } - - - //////////////////////////////////////////////////////////// - const uint32* String::GetData() const - { - return mString.c_str(); - } - - - //////////////////////////////////////////////////////////// - String::Iterator String::Begin() - { - return mString.begin(); - } - - - //////////////////////////////////////////////////////////// - String::ConstIterator String::Begin() const - { - return mString.begin(); - } - - - //////////////////////////////////////////////////////////// - String::Iterator String::End() - { - return mString.end(); - } - - - //////////////////////////////////////////////////////////// - String::ConstIterator String::End() const - { - return mString.end(); - } - - - //////////////////////////////////////////////////////////// - bool operator ==(const String& left, const String& right) - { - return left.mString == right.mString; - } - - - //////////////////////////////////////////////////////////// - bool operator !=(const String& left, const String& right) - { - return !(left == right); - } - - - //////////////////////////////////////////////////////////// - bool operator <(const String& left, const String& right) - { - return left.mString < right.mString; - } - - - //////////////////////////////////////////////////////////// - bool operator >(const String& left, const String& right) - { - return right < left; - } - - - //////////////////////////////////////////////////////////// - bool operator <=(const String& left, const String& right) - { - return !(right < left); - } - - - //////////////////////////////////////////////////////////// - bool operator >=(const String& left, const String& right) - { - return !(left < right); - } - - - //////////////////////////////////////////////////////////// - String operator +(const String& left, const String& right) - { - String string = left; - string += right; - - return string; - } - - - } -} diff --git a/Source/Asura.Engine/Text/String.hpp b/Source/Asura.Engine/Text/String.hpp deleted file mode 100644 index 226735b..0000000 --- a/Source/Asura.Engine/Text/String.hpp +++ /dev/null @@ -1,594 +0,0 @@ -#ifndef __ASURA_ENGINE_STRING_H__ -#define __ASURA_ENGINE_STRING_H__ - -#include "Config.h" -#include <iterator> -#include <locale> -#include <string> - -namespace AsuraEngine -{ - namespace Text - { - - - //////////////////////////////////////////////////////////// - /// \brief Utility string class that automatically handles - /// conversions between types and encodings - /// - //////////////////////////////////////////////////////////// - class String - { - public: - - //////////////////////////////////////////////////////////// - // Types - //////////////////////////////////////////////////////////// - typedef std::basic_string<uint32>::iterator Iterator; ///< Iterator type - typedef std::basic_string<uint32>::const_iterator ConstIterator; ///< Read-only iterator type - - //////////////////////////////////////////////////////////// - // Static member data - //////////////////////////////////////////////////////////// - static const std::size_t InvalidPos; ///< Represents an invalid position in the string - - //////////////////////////////////////////////////////////// - /// \brief Default constructor - /// - /// This constructor creates an empty string. - /// - //////////////////////////////////////////////////////////// - String(); - - //////////////////////////////////////////////////////////// - /// \brief Construct from a single ANSI character and a locale - /// - /// The source character is converted to UTF-32 according - /// to the given locale. - /// - /// \param ansiChar ANSI character to convert - /// \param locale Locale to use for conversion - /// - //////////////////////////////////////////////////////////// - String(char ansiChar, const std::locale& locale = std::locale()); - - //////////////////////////////////////////////////////////// - /// \brief Construct from single wide character - /// - /// \param wideChar Wide character to convert - /// - //////////////////////////////////////////////////////////// - String(wchar_t wideChar); - - //////////////////////////////////////////////////////////// - /// \brief Construct from single UTF-32 character - /// - /// \param utf32Char UTF-32 character to convert - /// - //////////////////////////////////////////////////////////// - String(uint utf32Char); - - //////////////////////////////////////////////////////////// - /// \brief Construct from a null-terminated C-style ANSI string and a locale - /// - /// The source string is converted to UTF-32 according - /// to the given locale. - /// - /// \param ansiString ANSI string to convert - /// \param locale Locale to use for conversion - /// - //////////////////////////////////////////////////////////// - String(const char* ansiString, const std::locale& locale = std::locale()); - - //////////////////////////////////////////////////////////// - /// \brief Construct from an ANSI string and a locale - /// - /// The source string is converted to UTF-32 according - /// to the given locale. - /// - /// \param ansiString ANSI string to convert - /// \param locale Locale to use for conversion - /// - //////////////////////////////////////////////////////////// - String(const std::string& ansiString, const std::locale& locale = std::locale()); - - //////////////////////////////////////////////////////////// - /// \brief Construct from null-terminated C-style wide string - /// - /// \param wideString Wide string to convert - /// - //////////////////////////////////////////////////////////// - String(const wchar_t* wideString); - - //////////////////////////////////////////////////////////// - /// \brief Construct from a wide string - /// - /// \param wideString Wide string to convert - /// - //////////////////////////////////////////////////////////// - String(const std::wstring& wideString); - - //////////////////////////////////////////////////////////// - /// \brief Construct from a null-terminated C-style UTF-32 string - /// - /// \param utf32String UTF-32 string to assign - /// - //////////////////////////////////////////////////////////// - String(const uint* utf32String); - - //////////////////////////////////////////////////////////// - /// \brief Construct from an UTF-32 string - /// - /// \param utf32String UTF-32 string to assign - /// - //////////////////////////////////////////////////////////// - String(const std::basic_string<uint>& utf32String); - - //////////////////////////////////////////////////////////// - /// \brief Copy constructor - /// - /// \param copy Instance to copy - /// - //////////////////////////////////////////////////////////// - String(const String& copy); - - //////////////////////////////////////////////////////////// - /// \brief Create a new sf::String from a UTF-8 encoded string - /// - /// \param begin Forward iterator to the beginning of the UTF-8 sequence - /// \param end Forward iterator to the end of the UTF-8 sequence - /// - /// \return A sf::String containing the source string - /// - /// \see fromUtf16, fromUtf32 - /// - //////////////////////////////////////////////////////////// - template <typename T> - static String FromUtf8(T begin, T end); - - //////////////////////////////////////////////////////////// - /// \brief Create a new sf::String from a UTF-16 encoded string - /// - /// \param begin Forward iterator to the beginning of the UTF-16 sequence - /// \param end Forward iterator to the end of the UTF-16 sequence - /// - /// \return A sf::String containing the source string - /// - /// \see fromUtf8, fromUtf32 - /// - //////////////////////////////////////////////////////////// - template <typename T> - static String FromUtf16(T begin, T end); - - //////////////////////////////////////////////////////////// - /// \brief Create a new sf::String from a UTF-32 encoded string - /// - /// This function is provided for consistency, it is equivalent to - /// using the constructors that takes a const sf::uint* or - /// a std::basic_string<sf::uint>. - /// - /// \param begin Forward iterator to the beginning of the UTF-32 sequence - /// \param end Forward iterator to the end of the UTF-32 sequence - /// - /// \return A sf::String containing the source string - /// - /// \see fromUtf8, fromUtf16 - /// - //////////////////////////////////////////////////////////// - template <typename T> - static String FromUtf32(T begin, T end); - - //////////////////////////////////////////////////////////// - /// \brief Implicit conversion operator to std::string (ANSI string) - /// - /// The current global locale is used for conversion. If you - /// want to explicitly specify a locale, see toAnsiString. - /// Characters that do not fit in the target encoding are - /// discarded from the returned string. - /// This operator is defined for convenience, and is equivalent - /// to calling toAnsiString(). - /// - /// \return Converted ANSI string - /// - /// \see toAnsiString, operator std::wstring - /// - //////////////////////////////////////////////////////////// - operator std::string() const; - - //////////////////////////////////////////////////////////// - /// \brief Implicit conversion operator to std::wstring (wide string) - /// - /// Characters that do not fit in the target encoding are - /// discarded from the returned string. - /// This operator is defined for convenience, and is equivalent - /// to calling toWideString(). - /// - /// \return Converted wide string - /// - /// \see toWideString, operator std::string - /// - //////////////////////////////////////////////////////////// - operator std::wstring() const; - - //////////////////////////////////////////////////////////// - /// \brief Convert the Unicode string to an ANSI string - /// - /// The UTF-32 string is converted to an ANSI string in - /// the encoding defined by \a locale. - /// Characters that do not fit in the target encoding are - /// discarded from the returned string. - /// - /// \param locale Locale to use for conversion - /// - /// \return Converted ANSI string - /// - /// \see toWideString, operator std::string - /// - //////////////////////////////////////////////////////////// - std::string ToAnsiString(const std::locale& locale = std::locale()) const; - - //////////////////////////////////////////////////////////// - /// \brief Convert the Unicode string to a wide string - /// - /// Characters that do not fit in the target encoding are - /// discarded from the returned string. - /// - /// \return Converted wide string - /// - /// \see toAnsiString, operator std::wstring - /// - //////////////////////////////////////////////////////////// - std::wstring ToWideString() const; - - //////////////////////////////////////////////////////////// - /// \brief Convert the Unicode string to a UTF-8 string - /// - /// \return Converted UTF-8 string - /// - /// \see toUtf16, toUtf32 - /// - //////////////////////////////////////////////////////////// - std::basic_string<uint8> ToUtf8() const; - - //////////////////////////////////////////////////////////// - /// \brief Convert the Unicode string to a UTF-16 string - /// - /// \return Converted UTF-16 string - /// - /// \see toUtf8, toUtf32 - /// - //////////////////////////////////////////////////////////// - std::basic_string<uint16> ToUtf16() const; - - //////////////////////////////////////////////////////////// - /// \brief Convert the Unicode string to a UTF-32 string - /// - /// This function doesn't perform any conversion, since the - /// string is already stored as UTF-32 internally. - /// - /// \return Converted UTF-32 string - /// - /// \see toUtf8, toUtf16 - /// - //////////////////////////////////////////////////////////// - std::basic_string<uint> ToUtf32() const; - - //////////////////////////////////////////////////////////// - /// \brief Overload of assignment operator - /// - /// \param right Instance to assign - /// - /// \return Reference to self - /// - //////////////////////////////////////////////////////////// - String& operator =(const String& right); - - //////////////////////////////////////////////////////////// - /// \brief Overload of += operator to append an UTF-32 string - /// - /// \param right String to append - /// - /// \return Reference to self - /// - //////////////////////////////////////////////////////////// - String& operator +=(const String& right); - - //////////////////////////////////////////////////////////// - /// \brief Overload of [] operator to access a character by its position - /// - /// This function provides read-only access to characters. - /// Note: the behavior is undefined if \a index is out of range. - /// - /// \param index Index of the character to get - /// - /// \return Character at position \a index - /// - //////////////////////////////////////////////////////////// - uint operator [](std::size_t index) const; - - //////////////////////////////////////////////////////////// - /// \brief Overload of [] operator to access a character by its position - /// - /// This function provides read and write access to characters. - /// Note: the behavior is undefined if \a index is out of range. - /// - /// \param index Index of the character to get - /// - /// \return Reference to the character at position \a index - /// - //////////////////////////////////////////////////////////// - uint& operator [](std::size_t index); - - //////////////////////////////////////////////////////////// - /// \brief Clear the string - /// - /// This function removes all the characters from the string. - /// - /// \see isEmpty, erase - /// - //////////////////////////////////////////////////////////// - void Clear(); - - //////////////////////////////////////////////////////////// - /// \brief Get the size of the string - /// - /// \return Number of characters in the string - /// - /// \see isEmpty - /// - //////////////////////////////////////////////////////////// - std::size_t GetSize() const; - - //////////////////////////////////////////////////////////// - /// \brief Check whether the string is empty or not - /// - /// \return True if the string is empty (i.e. contains no character) - /// - /// \see clear, getSize - /// - //////////////////////////////////////////////////////////// - bool IsEmpty() const; - - //////////////////////////////////////////////////////////// - /// \brief Erase one or more characters from the string - /// - /// This function removes a sequence of \a count characters - /// starting from \a position. - /// - /// \param position Position of the first character to erase - /// \param count Number of characters to erase - /// - //////////////////////////////////////////////////////////// - void Erase(std::size_t position, std::size_t count = 1); - - //////////////////////////////////////////////////////////// - /// \brief Insert one or more characters into the string - /// - /// This function inserts the characters of \a str - /// into the string, starting from \a position. - /// - /// \param position Position of insertion - /// \param str Characters to insert - /// - //////////////////////////////////////////////////////////// - void Insert(std::size_t position, const String& str); - - //////////////////////////////////////////////////////////// - /// \brief Find a sequence of one or more characters in the string - /// - /// This function searches for the characters of \a str - /// in the string, starting from \a start. - /// - /// \param str Characters to find - /// \param start Where to begin searching - /// - /// \return Position of \a str in the string, or String::InvalidPos if not found - /// - //////////////////////////////////////////////////////////// - std::size_t Find(const String& str, std::size_t start = 0) const; - - //////////////////////////////////////////////////////////// - /// \brief Replace a substring with another string - /// - /// This function replaces the substring that starts at index \a position - /// and spans \a length characters with the string \a replaceWith. - /// - /// \param position Index of the first character to be replaced - /// \param length Number of characters to replace. You can pass InvalidPos to - /// replace all characters until the end of the string. - /// \param replaceWith String that replaces the given substring. - /// - //////////////////////////////////////////////////////////// - void Replace(std::size_t position, std::size_t length, const String& replaceWith); - - //////////////////////////////////////////////////////////// - /// \brief Replace all occurrences of a substring with a replacement string - /// - /// This function replaces all occurrences of \a searchFor in this string - /// with the string \a replaceWith. - /// - /// \param searchFor The value being searched for - /// \param replaceWith The value that replaces found \a searchFor values - /// - //////////////////////////////////////////////////////////// - void Replace(const String& searchFor, const String& replaceWith); - - //////////////////////////////////////////////////////////// - /// \brief Return a part of the string - /// - /// This function returns the substring that starts at index \a position - /// and spans \a length characters. - /// - /// \param position Index of the first character - /// \param length Number of characters to include in the substring (if - /// the string is shorter, as many characters as possible - /// are included). \ref InvalidPos can be used to include all - /// characters until the end of the string. - /// - /// \return String object containing a substring of this object - /// - //////////////////////////////////////////////////////////// - String Substring(std::size_t position, std::size_t length = InvalidPos) const; - - //////////////////////////////////////////////////////////// - /// \brief Get a pointer to the C-style array of characters - /// - /// This functions provides a read-only access to a - /// null-terminated C-style representation of the string. - /// The returned pointer is temporary and is meant only for - /// immediate use, thus it is not recommended to store it. - /// - /// \return Read-only pointer to the array of characters - /// - //////////////////////////////////////////////////////////// - const uint* GetData() const; - - //////////////////////////////////////////////////////////// - /// \brief Return an iterator to the beginning of the string - /// - /// \return Read-write iterator to the beginning of the string characters - /// - /// \see end - /// - //////////////////////////////////////////////////////////// - Iterator Begin(); - - //////////////////////////////////////////////////////////// - /// \brief Return an iterator to the beginning of the string - /// - /// \return Read-only iterator to the beginning of the string characters - /// - /// \see end - /// - //////////////////////////////////////////////////////////// - ConstIterator Begin() const; - - //////////////////////////////////////////////////////////// - /// \brief Return an iterator to the end of the string - /// - /// The end iterator refers to 1 position past the last character; - /// thus it represents an invalid character and should never be - /// accessed. - /// - /// \return Read-write iterator to the end of the string characters - /// - /// \see begin - /// - //////////////////////////////////////////////////////////// - Iterator End(); - - //////////////////////////////////////////////////////////// - /// \brief Return an iterator to the end of the string - /// - /// The end iterator refers to 1 position past the last character; - /// thus it represents an invalid character and should never be - /// accessed. - /// - /// \return Read-only iterator to the end of the string characters - /// - /// \see begin - /// - //////////////////////////////////////////////////////////// - ConstIterator End() const; - - private: - - friend bool operator ==(const String& left, const String& right); - friend bool operator <(const String& left, const String& right); - - //////////////////////////////////////////////////////////// - // Member data - //////////////////////////////////////////////////////////// - std::basic_string<uint> mString; ///< Internal string of UTF-32 characters - }; - - //////////////////////////////////////////////////////////// - /// \relates String - /// \brief Overload of == operator to compare two UTF-32 strings - /// - /// \param left Left operand (a string) - /// \param right Right operand (a string) - /// - /// \return True if both strings are equal - /// - //////////////////////////////////////////////////////////// - bool operator ==(const String& left, const String& right); - - //////////////////////////////////////////////////////////// - /// \relates String - /// \brief Overload of != operator to compare two UTF-32 strings - /// - /// \param left Left operand (a string) - /// \param right Right operand (a string) - /// - /// \return True if both strings are different - /// - //////////////////////////////////////////////////////////// - bool operator !=(const String& left, const String& right); - - //////////////////////////////////////////////////////////// - /// \relates String - /// \brief Overload of < operator to compare two UTF-32 strings - /// - /// \param left Left operand (a string) - /// \param right Right operand (a string) - /// - /// \return True if \a left is lexicographically before \a right - /// - //////////////////////////////////////////////////////////// - bool operator <(const String& left, const String& right); - - //////////////////////////////////////////////////////////// - /// \relates String - /// \brief Overload of > operator to compare two UTF-32 strings - /// - /// \param left Left operand (a string) - /// \param right Right operand (a string) - /// - /// \return True if \a left is lexicographically after \a right - /// - //////////////////////////////////////////////////////////// - bool operator >(const String& left, const String& right); - - //////////////////////////////////////////////////////////// - /// \relates String - /// \brief Overload of <= operator to compare two UTF-32 strings - /// - /// \param left Left operand (a string) - /// \param right Right operand (a string) - /// - /// \return True if \a left is lexicographically before or equivalent to \a right - /// - //////////////////////////////////////////////////////////// - bool operator <=(const String& left, const String& right); - - //////////////////////////////////////////////////////////// - /// \relates String - /// \brief Overload of >= operator to compare two UTF-32 strings - /// - /// \param left Left operand (a string) - /// \param right Right operand (a string) - /// - /// \return True if \a left is lexicographically after or equivalent to \a right - /// - //////////////////////////////////////////////////////////// - bool operator >=(const String& left, const String& right); - - //////////////////////////////////////////////////////////// - /// \relates String - /// \brief Overload of binary + operator to concatenate two strings - /// - /// \param left Left operand (a string) - /// \param right Right operand (a string) - /// - /// \return Concatenated string - /// - //////////////////////////////////////////////////////////// - String operator +(const String& left, const String& right); - - #include "String.inl" - - } -} - -#endif
\ No newline at end of file diff --git a/Source/Asura.Engine/Text/String.inl b/Source/Asura.Engine/Text/String.inl deleted file mode 100644 index ef18228..0000000 --- a/Source/Asura.Engine/Text/String.inl +++ /dev/null @@ -1,29 +0,0 @@ - -//////////////////////////////////////////////////////////// -template <typename T> -String String::fromUtf8(T begin, T end) -{ - String string; - Utf8::toUtf32(begin, end, std::back_inserter(string.m_string)); - return string; -} - - -//////////////////////////////////////////////////////////// -template <typename T> -String String::fromUtf16(T begin, T end) -{ - String string; - Utf16::toUtf32(begin, end, std::back_inserter(string.m_string)); - return string; -} - - -//////////////////////////////////////////////////////////// -template <typename T> -String String::fromUtf32(T begin, T end) -{ - String string; - string.m_string.assign(begin, end); - return string; -} diff --git a/Source/Asura.Engine/Text/Utf.hpp b/Source/Asura.Engine/Text/Utf.hpp deleted file mode 100644 index 2e04ee4..0000000 --- a/Source/Asura.Engine/Text/Utf.hpp +++ /dev/null @@ -1,720 +0,0 @@ -#ifndef __ASURA_UTF_HPP__ -#define __ASURA_UTF_HPP__ - -//////////////////////////////////////////////////////////// -// Headers -//////////////////////////////////////////////////////////// -#include <algorithm> -#include <locale> -#include <string> -#include <cstdlib> - -namespace AsuraEngine -{ - namespace Text - { - - template <unsigned int N> - class Utf; - - //////////////////////////////////////////////////////////// - /// \brief Specialization of the Utf template for UTF-8 - /// - //////////////////////////////////////////////////////////// - template <> - class Utf<8> - { - public: - - //////////////////////////////////////////////////////////// - /// \brief Decode a single UTF-8 character - /// - /// Decoding a character means finding its unique 32-bits - /// code (called the codepoint) in the Unicode standard. - /// - /// \param begin Iterator pointing to the beginning of the input sequence - /// \param end Iterator pointing to the end of the input sequence - /// \param output Codepoint of the decoded UTF-8 character - /// \param replacement Replacement character to use in case the UTF-8 sequence is invalid - /// - /// \return Iterator pointing to one past the last read element of the input sequence - /// - //////////////////////////////////////////////////////////// - template <typename In> - static In Decode(In begin, In end, Uint32& output, Uint32 replacement = 0); - - //////////////////////////////////////////////////////////// - /// \brief Encode a single UTF-8 character - /// - /// Encoding a character means converting a unique 32-bits - /// code (called the codepoint) in the target encoding, UTF-8. - /// - /// \param input Codepoint to encode as UTF-8 - /// \param output Iterator pointing to the beginning of the output sequence - /// \param replacement Replacement for characters not convertible to UTF-8 (use 0 to skip them) - /// - /// \return Iterator to the end of the output sequence which has been written - /// - //////////////////////////////////////////////////////////// - template <typename Out> - static Out Encode(Uint32 input, Out output, Uint8 replacement = 0); - - //////////////////////////////////////////////////////////// - /// \brief Advance to the next UTF-8 character - /// - /// This function is necessary for multi-elements encodings, as - /// a single character may use more than 1 storage element. - /// - /// \param begin Iterator pointing to the beginning of the input sequence - /// \param end Iterator pointing to the end of the input sequence - /// - /// \return Iterator pointing to one past the last read element of the input sequence - /// - //////////////////////////////////////////////////////////// - template <typename In> - static In Next(In begin, In end); - - //////////////////////////////////////////////////////////// - /// \brief Count the number of characters of a UTF-8 sequence - /// - /// This function is necessary for multi-elements encodings, as - /// a single character may use more than 1 storage element, thus the - /// total size can be different from (begin - end). - /// - /// \param begin Iterator pointing to the beginning of the input sequence - /// \param end Iterator pointing to the end of the input sequence - /// - /// \return Iterator pointing to one past the last read element of the input sequence - /// - //////////////////////////////////////////////////////////// - template <typename In> - static std::size_t Count(In begin, In end); - - //////////////////////////////////////////////////////////// - /// \brief Convert an ANSI characters range to UTF-8 - /// - /// The current global locale will be used by default, unless you - /// pass a custom one in the \a locale parameter. - /// - /// \param begin Iterator pointing to the beginning of the input sequence - /// \param end Iterator pointing to the end of the input sequence - /// \param output Iterator pointing to the beginning of the output sequence - /// \param locale Locale to use for conversion - /// - /// \return Iterator to the end of the output sequence which has been written - /// - //////////////////////////////////////////////////////////// - template <typename In, typename Out> - static Out FromAnsi(In begin, In end, Out output, const std::locale& locale = std::locale()); - - //////////////////////////////////////////////////////////// - /// \brief Convert a wide characters range to UTF-8 - /// - /// \param begin Iterator pointing to the beginning of the input sequence - /// \param end Iterator pointing to the end of the input sequence - /// \param output Iterator pointing to the beginning of the output sequence - /// - /// \return Iterator to the end of the output sequence which has been written - /// - //////////////////////////////////////////////////////////// - template <typename In, typename Out> - static Out FromWide(In begin, In end, Out output); - - //////////////////////////////////////////////////////////// - /// \brief Convert a latin-1 (ISO-5589-1) characters range to UTF-8 - /// - /// \param begin Iterator pointing to the beginning of the input sequence - /// \param end Iterator pointing to the end of the input sequence - /// \param output Iterator pointing to the beginning of the output sequence - /// - /// \return Iterator to the end of the output sequence which has been written - /// - //////////////////////////////////////////////////////////// - template <typename In, typename Out> - static Out FromLatin1(In begin, In end, Out output); - - //////////////////////////////////////////////////////////// - /// \brief Convert an UTF-8 characters range to ANSI characters - /// - /// The current global locale will be used by default, unless you - /// pass a custom one in the \a locale parameter. - /// - /// \param begin Iterator pointing to the beginning of the input sequence - /// \param end Iterator pointing to the end of the input sequence - /// \param output Iterator pointing to the beginning of the output sequence - /// \param replacement Replacement for characters not convertible to ANSI (use 0 to skip them) - /// \param locale Locale to use for conversion - /// - /// \return Iterator to the end of the output sequence which has been written - /// - //////////////////////////////////////////////////////////// - template <typename In, typename Out> - static Out ToAnsi(In begin, In end, Out output, char replacement = 0, const std::locale& locale = std::locale()); - - //////////////////////////////////////////////////////////// - /// \brief Convert an UTF-8 characters range to wide characters - /// - /// \param begin Iterator pointing to the beginning of the input sequence - /// \param end Iterator pointing to the end of the input sequence - /// \param output Iterator pointing to the beginning of the output sequence - /// \param replacement Replacement for characters not convertible to wide (use 0 to skip them) - /// - /// \return Iterator to the end of the output sequence which has been written - /// - //////////////////////////////////////////////////////////// - template <typename In, typename Out> - static Out ToWide(In begin, In end, Out output, wchar_t replacement = 0); - - //////////////////////////////////////////////////////////// - /// \brief Convert an UTF-8 characters range to latin-1 (ISO-5589-1) characters - /// - /// \param begin Iterator pointing to the beginning of the input sequence - /// \param end Iterator pointing to the end of the input sequence - /// \param output Iterator pointing to the beginning of the output sequence - /// \param replacement Replacement for characters not convertible to wide (use 0 to skip them) - /// - /// \return Iterator to the end of the output sequence which has been written - /// - //////////////////////////////////////////////////////////// - template <typename In, typename Out> - static Out ToLatin1(In begin, In end, Out output, char replacement = 0); - - //////////////////////////////////////////////////////////// - /// \brief Convert a UTF-8 characters range to UTF-8 - /// - /// This functions does nothing more than a direct copy; - /// it is defined only to provide the same interface as other - /// specializations of the sf::Utf<> template, and allow - /// generic code to be written on top of it. - /// - /// \param begin Iterator pointing to the beginning of the input sequence - /// \param end Iterator pointing to the end of the input sequence - /// \param output Iterator pointing to the beginning of the output sequence - /// - /// \return Iterator to the end of the output sequence which has been written - /// - //////////////////////////////////////////////////////////// - template <typename In, typename Out> - static Out ToUtf8(In begin, In end, Out output); - - //////////////////////////////////////////////////////////// - /// \brief Convert a UTF-8 characters range to UTF-16 - /// - /// \param begin Iterator pointing to the beginning of the input sequence - /// \param end Iterator pointing to the end of the input sequence - /// \param output Iterator pointing to the beginning of the output sequence - /// - /// \return Iterator to the end of the output sequence which has been written - /// - //////////////////////////////////////////////////////////// - template <typename In, typename Out> - static Out ToUtf16(In begin, In end, Out output); - - //////////////////////////////////////////////////////////// - /// \brief Convert a UTF-8 characters range to UTF-32 - /// - /// \param begin Iterator pointing to the beginning of the input sequence - /// \param end Iterator pointing to the end of the input sequence - /// \param output Iterator pointing to the beginning of the output sequence - /// - /// \return Iterator to the end of the output sequence which has been written - /// - //////////////////////////////////////////////////////////// - template <typename In, typename Out> - static Out ToUtf32(In begin, In end, Out output); - }; - - //////////////////////////////////////////////////////////// - /// \brief Specialization of the Utf template for UTF-16 - /// - //////////////////////////////////////////////////////////// - template <> - class Utf<16> - { - public: - - //////////////////////////////////////////////////////////// - /// \brief Decode a single UTF-16 character - /// - /// Decoding a character means finding its unique 32-bits - /// code (called the codepoint) in the Unicode standard. - /// - /// \param begin Iterator pointing to the beginning of the input sequence - /// \param end Iterator pointing to the end of the input sequence - /// \param output Codepoint of the decoded UTF-16 character - /// \param replacement Replacement character to use in case the UTF-8 sequence is invalid - /// - /// \return Iterator pointing to one past the last read element of the input sequence - /// - //////////////////////////////////////////////////////////// - template <typename In> - static In Decode(In begin, In end, Uint32& output, Uint32 replacement = 0); - - //////////////////////////////////////////////////////////// - /// \brief Encode a single UTF-16 character - /// - /// Encoding a character means converting a unique 32-bits - /// code (called the codepoint) in the target encoding, UTF-16. - /// - /// \param input Codepoint to encode as UTF-16 - /// \param output Iterator pointing to the beginning of the output sequence - /// \param replacement Replacement for characters not convertible to UTF-16 (use 0 to skip them) - /// - /// \return Iterator to the end of the output sequence which has been written - /// - //////////////////////////////////////////////////////////// - template <typename Out> - static Out Encode(Uint32 input, Out output, Uint16 replacement = 0); - - //////////////////////////////////////////////////////////// - /// \brief Advance to the next UTF-16 character - /// - /// This function is necessary for multi-elements encodings, as - /// a single character may use more than 1 storage element. - /// - /// \param begin Iterator pointing to the beginning of the input sequence - /// \param end Iterator pointing to the end of the input sequence - /// - /// \return Iterator pointing to one past the last read element of the input sequence - /// - //////////////////////////////////////////////////////////// - template <typename In> - static In Next(In begin, In end); - - //////////////////////////////////////////////////////////// - /// \brief Count the number of characters of a UTF-16 sequence - /// - /// This function is necessary for multi-elements encodings, as - /// a single character may use more than 1 storage element, thus the - /// total size can be different from (begin - end). - /// - /// \param begin Iterator pointing to the beginning of the input sequence - /// \param end Iterator pointing to the end of the input sequence - /// - /// \return Iterator pointing to one past the last read element of the input sequence - /// - //////////////////////////////////////////////////////////// - template <typename In> - static std::size_t Count(In begin, In end); - - //////////////////////////////////////////////////////////// - /// \brief Convert an ANSI characters range to UTF-16 - /// - /// The current global locale will be used by default, unless you - /// pass a custom one in the \a locale parameter. - /// - /// \param begin Iterator pointing to the beginning of the input sequence - /// \param end Iterator pointing to the end of the input sequence - /// \param output Iterator pointing to the beginning of the output sequence - /// \param locale Locale to use for conversion - /// - /// \return Iterator to the end of the output sequence which has been written - /// - //////////////////////////////////////////////////////////// - template <typename In, typename Out> - static Out FromAnsi(In begin, In end, Out output, const std::locale& locale = std::locale()); - - //////////////////////////////////////////////////////////// - /// \brief Convert a wide characters range to UTF-16 - /// - /// \param begin Iterator pointing to the beginning of the input sequence - /// \param end Iterator pointing to the end of the input sequence - /// \param output Iterator pointing to the beginning of the output sequence - /// - /// \return Iterator to the end of the output sequence which has been written - /// - //////////////////////////////////////////////////////////// - template <typename In, typename Out> - static Out FromWide(In begin, In end, Out output); - - //////////////////////////////////////////////////////////// - /// \brief Convert a latin-1 (ISO-5589-1) characters range to UTF-16 - /// - /// \param begin Iterator pointing to the beginning of the input sequence - /// \param end Iterator pointing to the end of the input sequence - /// \param output Iterator pointing to the beginning of the output sequence - /// - /// \return Iterator to the end of the output sequence which has been written - /// - //////////////////////////////////////////////////////////// - template <typename In, typename Out> - static Out FromLatin1(In begin, In end, Out output); - - //////////////////////////////////////////////////////////// - /// \brief Convert an UTF-16 characters range to ANSI characters - /// - /// The current global locale will be used by default, unless you - /// pass a custom one in the \a locale parameter. - /// - /// \param begin Iterator pointing to the beginning of the input sequence - /// \param end Iterator pointing to the end of the input sequence - /// \param output Iterator pointing to the beginning of the output sequence - /// \param replacement Replacement for characters not convertible to ANSI (use 0 to skip them) - /// \param locale Locale to use for conversion - /// - /// \return Iterator to the end of the output sequence which has been written - /// - //////////////////////////////////////////////////////////// - template <typename In, typename Out> - static Out ToAnsi(In begin, In end, Out output, char replacement = 0, const std::locale& locale = std::locale()); - - //////////////////////////////////////////////////////////// - /// \brief Convert an UTF-16 characters range to wide characters - /// - /// \param begin Iterator pointing to the beginning of the input sequence - /// \param end Iterator pointing to the end of the input sequence - /// \param output Iterator pointing to the beginning of the output sequence - /// \param replacement Replacement for characters not convertible to wide (use 0 to skip them) - /// - /// \return Iterator to the end of the output sequence which has been written - /// - //////////////////////////////////////////////////////////// - template <typename In, typename Out> - static Out ToWide(In begin, In end, Out output, wchar_t replacement = 0); - - //////////////////////////////////////////////////////////// - /// \brief Convert an UTF-16 characters range to latin-1 (ISO-5589-1) characters - /// - /// \param begin Iterator pointing to the beginning of the input sequence - /// \param end Iterator pointing to the end of the input sequence - /// \param output Iterator pointing to the beginning of the output sequence - /// \param replacement Replacement for characters not convertible to wide (use 0 to skip them) - /// - /// \return Iterator to the end of the output sequence which has been written - /// - //////////////////////////////////////////////////////////// - template <typename In, typename Out> - static Out ToLatin1(In begin, In end, Out output, char replacement = 0); - - //////////////////////////////////////////////////////////// - /// \brief Convert a UTF-16 characters range to UTF-8 - /// - /// \param begin Iterator pointing to the beginning of the input sequence - /// \param end Iterator pointing to the end of the input sequence - /// \param output Iterator pointing to the beginning of the output sequence - /// - /// \return Iterator to the end of the output sequence which has been written - /// - //////////////////////////////////////////////////////////// - template <typename In, typename Out> - static Out ToUtf8(In begin, In end, Out output); - - //////////////////////////////////////////////////////////// - /// \brief Convert a UTF-16 characters range to UTF-16 - /// - /// This functions does nothing more than a direct copy; - /// it is defined only to provide the same interface as other - /// specializations of the sf::Utf<> template, and allow - /// generic code to be written on top of it. - /// - /// \param begin Iterator pointing to the beginning of the input sequence - /// \param end Iterator pointing to the end of the input sequence - /// \param output Iterator pointing to the beginning of the output sequence - /// - /// \return Iterator to the end of the output sequence which has been written - /// - //////////////////////////////////////////////////////////// - template <typename In, typename Out> - static Out ToUtf16(In begin, In end, Out output); - - //////////////////////////////////////////////////////////// - /// \brief Convert a UTF-16 characters range to UTF-32 - /// - /// \param begin Iterator pointing to the beginning of the input sequence - /// \param end Iterator pointing to the end of the input sequence - /// \param output Iterator pointing to the beginning of the output sequence - /// - /// \return Iterator to the end of the output sequence which has been written - /// - //////////////////////////////////////////////////////////// - template <typename In, typename Out> - static Out ToUtf32(In begin, In end, Out output); - }; - - //////////////////////////////////////////////////////////// - /// \brief Specialization of the Utf template for UTF-32 - /// - //////////////////////////////////////////////////////////// - template <> - class Utf<32> - { - public: - - //////////////////////////////////////////////////////////// - /// \brief Decode a single UTF-32 character - /// - /// Decoding a character means finding its unique 32-bits - /// code (called the codepoint) in the Unicode standard. - /// For UTF-32, the character value is the same as the codepoint. - /// - /// \param begin Iterator pointing to the beginning of the input sequence - /// \param end Iterator pointing to the end of the input sequence - /// \param output Codepoint of the decoded UTF-32 character - /// \param replacement Replacement character to use in case the UTF-8 sequence is invalid - /// - /// \return Iterator pointing to one past the last read element of the input sequence - /// - //////////////////////////////////////////////////////////// - template <typename In> - static In Decode(In begin, In end, Uint32& output, Uint32 replacement = 0); - - //////////////////////////////////////////////////////////// - /// \brief Encode a single UTF-32 character - /// - /// Encoding a character means converting a unique 32-bits - /// code (called the codepoint) in the target encoding, UTF-32. - /// For UTF-32, the codepoint is the same as the character value. - /// - /// \param input Codepoint to encode as UTF-32 - /// \param output Iterator pointing to the beginning of the output sequence - /// \param replacement Replacement for characters not convertible to UTF-32 (use 0 to skip them) - /// - /// \return Iterator to the end of the output sequence which has been written - /// - //////////////////////////////////////////////////////////// - template <typename Out> - static Out Encode(Uint32 input, Out output, Uint32 replacement = 0); - - //////////////////////////////////////////////////////////// - /// \brief Advance to the next UTF-32 character - /// - /// This function is trivial for UTF-32, which can store - /// every character in a single storage element. - /// - /// \param begin Iterator pointing to the beginning of the input sequence - /// \param end Iterator pointing to the end of the input sequence - /// - /// \return Iterator pointing to one past the last read element of the input sequence - /// - //////////////////////////////////////////////////////////// - template <typename In> - static In Next(In begin, In end); - - //////////////////////////////////////////////////////////// - /// \brief Count the number of characters of a UTF-32 sequence - /// - /// This function is trivial for UTF-32, which can store - /// every character in a single storage element. - /// - /// \param begin Iterator pointing to the beginning of the input sequence - /// \param end Iterator pointing to the end of the input sequence - /// - /// \return Iterator pointing to one past the last read element of the input sequence - /// - //////////////////////////////////////////////////////////// - template <typename In> - static std::size_t Count(In begin, In end); - - //////////////////////////////////////////////////////////// - /// \brief Convert an ANSI characters range to UTF-32 - /// - /// The current global locale will be used by default, unless you - /// pass a custom one in the \a locale parameter. - /// - /// \param begin Iterator pointing to the beginning of the input sequence - /// \param end Iterator pointing to the end of the input sequence - /// \param output Iterator pointing to the beginning of the output sequence - /// \param locale Locale to use for conversion - /// - /// \return Iterator to the end of the output sequence which has been written - /// - //////////////////////////////////////////////////////////// - template <typename In, typename Out> - static Out FromAnsi(In begin, In end, Out output, const std::locale& locale = std::locale()); - - //////////////////////////////////////////////////////////// - /// \brief Convert a wide characters range to UTF-32 - /// - /// \param begin Iterator pointing to the beginning of the input sequence - /// \param end Iterator pointing to the end of the input sequence - /// \param output Iterator pointing to the beginning of the output sequence - /// - /// \return Iterator to the end of the output sequence which has been written - /// - //////////////////////////////////////////////////////////// - template <typename In, typename Out> - static Out FromWide(In begin, In end, Out output); - - //////////////////////////////////////////////////////////// - /// \brief Convert a latin-1 (ISO-5589-1) characters range to UTF-32 - /// - /// \param begin Iterator pointing to the beginning of the input sequence - /// \param end Iterator pointing to the end of the input sequence - /// \param output Iterator pointing to the beginning of the output sequence - /// - /// \return Iterator to the end of the output sequence which has been written - /// - //////////////////////////////////////////////////////////// - template <typename In, typename Out> - static Out FromLatin1(In begin, In end, Out output); - - //////////////////////////////////////////////////////////// - /// \brief Convert an UTF-32 characters range to ANSI characters - /// - /// The current global locale will be used by default, unless you - /// pass a custom one in the \a locale parameter. - /// - /// \param begin Iterator pointing to the beginning of the input sequence - /// \param end Iterator pointing to the end of the input sequence - /// \param output Iterator pointing to the beginning of the output sequence - /// \param replacement Replacement for characters not convertible to ANSI (use 0 to skip them) - /// \param locale Locale to use for conversion - /// - /// \return Iterator to the end of the output sequence which has been written - /// - //////////////////////////////////////////////////////////// - template <typename In, typename Out> - static Out ToAnsi(In begin, In end, Out output, char replacement = 0, const std::locale& locale = std::locale()); - - //////////////////////////////////////////////////////////// - /// \brief Convert an UTF-32 characters range to wide characters - /// - /// \param begin Iterator pointing to the beginning of the input sequence - /// \param end Iterator pointing to the end of the input sequence - /// \param output Iterator pointing to the beginning of the output sequence - /// \param replacement Replacement for characters not convertible to wide (use 0 to skip them) - /// - /// \return Iterator to the end of the output sequence which has been written - /// - //////////////////////////////////////////////////////////// - template <typename In, typename Out> - static Out ToWide(In begin, In end, Out output, wchar_t replacement = 0); - - //////////////////////////////////////////////////////////// - /// \brief Convert an UTF-16 characters range to latin-1 (ISO-5589-1) characters - /// - /// \param begin Iterator pointing to the beginning of the input sequence - /// \param end Iterator pointing to the end of the input sequence - /// \param output Iterator pointing to the beginning of the output sequence - /// \param replacement Replacement for characters not convertible to wide (use 0 to skip them) - /// - /// \return Iterator to the end of the output sequence which has been written - /// - //////////////////////////////////////////////////////////// - template <typename In, typename Out> - static Out ToLatin1(In begin, In end, Out output, char replacement = 0); - - //////////////////////////////////////////////////////////// - /// \brief Convert a UTF-32 characters range to UTF-8 - /// - /// \param begin Iterator pointing to the beginning of the input sequence - /// \param end Iterator pointing to the end of the input sequence - /// \param output Iterator pointing to the beginning of the output sequence - /// - /// \return Iterator to the end of the output sequence which has been written - /// - //////////////////////////////////////////////////////////// - template <typename In, typename Out> - static Out ToUtf8(In begin, In end, Out output); - - //////////////////////////////////////////////////////////// - /// \brief Convert a UTF-32 characters range to UTF-16 - /// - /// \param begin Iterator pointing to the beginning of the input sequence - /// \param end Iterator pointing to the end of the input sequence - /// \param output Iterator pointing to the beginning of the output sequence - /// - /// \return Iterator to the end of the output sequence which has been written - /// - //////////////////////////////////////////////////////////// - template <typename In, typename Out> - static Out ToUtf16(In begin, In end, Out output); - - //////////////////////////////////////////////////////////// - /// \brief Convert a UTF-32 characters range to UTF-32 - /// - /// This functions does nothing more than a direct copy; - /// it is defined only to provide the same interface as other - /// specializations of the sf::Utf<> template, and allow - /// generic code to be written on top of it. - /// - /// \param begin Iterator pointing to the beginning of the input sequence - /// \param end Iterator pointing to the end of the input sequence - /// \param output Iterator pointing to the beginning of the output sequence - /// - /// \return Iterator to the end of the output sequence which has been written - /// - //////////////////////////////////////////////////////////// - template <typename In, typename Out> - static Out ToUtf32(In begin, In end, Out output); - - //////////////////////////////////////////////////////////// - /// \brief Decode a single ANSI character to UTF-32 - /// - /// This function does not exist in other specializations - /// of sf::Utf<>, it is defined for convenience (it is used by - /// several other conversion functions). - /// - /// \param input Input ANSI character - /// \param locale Locale to use for conversion - /// - /// \return Converted character - /// - //////////////////////////////////////////////////////////// - template <typename In> - static Uint32 DecodeAnsi(In input, const std::locale& locale = std::locale()); - - //////////////////////////////////////////////////////////// - /// \brief Decode a single wide character to UTF-32 - /// - /// This function does not exist in other specializations - /// of sf::Utf<>, it is defined for convenience (it is used by - /// several other conversion functions). - /// - /// \param input Input wide character - /// - /// \return Converted character - /// - //////////////////////////////////////////////////////////// - template <typename In> - static Uint32 DecodeWide(In input); - - //////////////////////////////////////////////////////////// - /// \brief Encode a single UTF-32 character to ANSI - /// - /// This function does not exist in other specializations - /// of sf::Utf<>, it is defined for convenience (it is used by - /// several other conversion functions). - /// - /// \param codepoint Iterator pointing to the beginning of the input sequence - /// \param output Iterator pointing to the beginning of the output sequence - /// \param replacement Replacement if the input character is not convertible to ANSI (use 0 to skip it) - /// \param locale Locale to use for conversion - /// - /// \return Iterator to the end of the output sequence which has been written - /// - //////////////////////////////////////////////////////////// - template <typename Out> - static Out EncodeAnsi(Uint32 codepoint, Out output, char replacement = 0, const std::locale& locale = std::locale()); - - //////////////////////////////////////////////////////////// - /// \brief Encode a single UTF-32 character to wide - /// - /// This function does not exist in other specializations - /// of sf::Utf<>, it is defined for convenience (it is used by - /// several other conversion functions). - /// - /// \param codepoint Iterator pointing to the beginning of the input sequence - /// \param output Iterator pointing to the beginning of the output sequence - /// \param replacement Replacement if the input character is not convertible to wide (use 0 to skip it) - /// - /// \return Iterator to the end of the output sequence which has been written - /// - //////////////////////////////////////////////////////////// - template <typename Out> - static Out EncodeWide(Uint32 codepoint, Out output, wchar_t replacement = 0); - }; - -#include "Utf.inl" - - // Make typedefs to get rid of the template syntax - typedef Utf<8> Utf8; - typedef Utf<16> Utf16; - typedef Utf<32> Utf32; - - } // namespace sf - -} - - -#endif // SFML_UTF_HPP diff --git a/Source/Asura.Engine/Text/Utf.inl b/Source/Asura.Engine/Text/Utf.inl deleted file mode 100644 index 69a523b..0000000 --- a/Source/Asura.Engine/Text/Utf.inl +++ /dev/null @@ -1,752 +0,0 @@ -//////////////////////////////////////////////////////////// -// -// SFML - Simple and Fast Multimedia Library -// Copyright (C) 2007-2019 Laurent Gomila (laurent@sfml-dev.org) -// -// This software is provided 'as-is', without any express or implied warranty. -// In no event will the authors be held liable for any damages arising from the use of this software. -// -// Permission is granted to anyone to use this software for any purpose, -// including commercial applications, and to alter it and redistribute it freely, -// subject to the following restrictions: -// -// 1. The origin of this software must not be misrepresented; -// you must not claim that you wrote the original software. -// If you use this software in a product, an acknowledgment -// in the product documentation would be appreciated but is not required. -// -// 2. Altered source versions must be plainly marked as such, -// and must not be misrepresented as being the original software. -// -// 3. This notice may not be removed or altered from any source distribution. -// -//////////////////////////////////////////////////////////// - - -//////////////////////////////////////////////////////////// -// References: -// -// https://www.unicode.org/ -// https://www.unicode.org/Public/PROGRAMS/CVTUTF/ConvertUTF.c -// https://www.unicode.org/Public/PROGRAMS/CVTUTF/ConvertUTF.h -// https://people.w3.org/rishida/scripts/uniview/conversion -// -//////////////////////////////////////////////////////////// - - -//////////////////////////////////////////////////////////// -template <typename In> -In Utf<8>::Decode(In begin, In end, Uint32& output, Uint32 replacement) -{ - // Some useful precomputed data - static const int trailing[256] = - { - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - 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, - 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 3, 3, 3, 3, 3, 3, 4, 4, 4, 4, 5, 5, 5, 5 - }; - static const Uint32 offsets[6] = - { - 0x00000000, 0x00003080, 0x000E2080, 0x03C82080, 0xFA082080, 0x82082080 - }; - - // decode the character - int trailingBytes = trailing[static_cast<Uint8>(*begin)]; - if (begin + trailingBytes < end) - { - output = 0; - switch (trailingBytes) - { - case 5: output += static_cast<Uint8>(*begin++); output <<= 6; - case 4: output += static_cast<Uint8>(*begin++); output <<= 6; - case 3: output += static_cast<Uint8>(*begin++); output <<= 6; - case 2: output += static_cast<Uint8>(*begin++); output <<= 6; - case 1: output += static_cast<Uint8>(*begin++); output <<= 6; - case 0: output += static_cast<Uint8>(*begin++); - } - output -= offsets[trailingBytes]; - } - else - { - // Incomplete character - begin = end; - output = replacement; - } - - return begin; -} - - -//////////////////////////////////////////////////////////// -template <typename Out> -Out Utf<8>::Encode(Uint32 input, Out output, Uint8 replacement) -{ - // Some useful precomputed data - static const Uint8 firstBytes[7] = - { - 0x00, 0x00, 0xC0, 0xE0, 0xF0, 0xF8, 0xFC - }; - - // encode the character - if ((input > 0x0010FFFF) || ((input >= 0xD800) && (input <= 0xDBFF))) - { - // Invalid character - if (replacement) - *output++ = replacement; - } - else - { - // Valid character - - // Get the number of bytes to write - std::size_t bytestoWrite = 1; - if (input < 0x80) bytestoWrite = 1; - else if (input < 0x800) bytestoWrite = 2; - else if (input < 0x10000) bytestoWrite = 3; - else if (input <= 0x0010FFFF) bytestoWrite = 4; - - // Extract the bytes to write - Uint8 bytes[4]; - switch (bytestoWrite) - { - case 4: bytes[3] = static_cast<Uint8>((input | 0x80) & 0xBF); input >>= 6; - case 3: bytes[2] = static_cast<Uint8>((input | 0x80) & 0xBF); input >>= 6; - case 2: bytes[1] = static_cast<Uint8>((input | 0x80) & 0xBF); input >>= 6; - case 1: bytes[0] = static_cast<Uint8> (input | firstBytes[bytestoWrite]); - } - - // Add them to the output - output = std::copy(bytes, bytes + bytestoWrite, output); - } - - return output; -} - - -//////////////////////////////////////////////////////////// -template <typename In> -In Utf<8>::Next(In begin, In end) -{ - Uint32 codepoint; - return Decode(begin, end, codepoint); -} - - -//////////////////////////////////////////////////////////// -template <typename In> -std::size_t Utf<8>::Count(In begin, In end) -{ - std::size_t length = 0; - while (begin < end) - { - begin = Next(begin, end); - ++length; - } - - return length; -} - - -//////////////////////////////////////////////////////////// -template <typename In, typename Out> -Out Utf<8>::FromAnsi(In begin, In end, Out output, const std::locale& locale) -{ - while (begin < end) - { - Uint32 codepoint = Utf<32>::DecodeAnsi(*begin++, locale); - output = Encode(codepoint, output); - } - - return output; -} - - -//////////////////////////////////////////////////////////// -template <typename In, typename Out> -Out Utf<8>::FromWide(In begin, In end, Out output) -{ - while (begin < end) - { - Uint32 codepoint = Utf<32>::DecodeWide(*begin++); - output = Encode(codepoint, output); - } - - return output; -} - - -//////////////////////////////////////////////////////////// -template <typename In, typename Out> -Out Utf<8>::FromLatin1(In begin, In end, Out output) -{ - // Latin-1 is directly compatible with Unicode encodings, - // and can thus be treated as (a sub-range of) UTF-32 - while (begin < end) - output = Encode(*begin++, output); - - return output; -} - - -//////////////////////////////////////////////////////////// -template <typename In, typename Out> -Out Utf<8>::ToAnsi(In begin, In end, Out output, char replacement, const std::locale& locale) -{ - while (begin < end) - { - Uint32 codepoint; - begin = Decode(begin, end, codepoint); - output = Utf<32>::EncodeAnsi(codepoint, output, replacement, locale); - } - - return output; -} - - -//////////////////////////////////////////////////////////// -template <typename In, typename Out> -Out Utf<8>::ToWide(In begin, In end, Out output, wchar_t replacement) -{ - while (begin < end) - { - Uint32 codepoint; - begin = Decode(begin, end, codepoint); - output = Utf<32>::EncodeWide(codepoint, output, replacement); - } - - return output; -} - - -//////////////////////////////////////////////////////////// -template <typename In, typename Out> -Out Utf<8>::ToLatin1(In begin, In end, Out output, char replacement) -{ - // Latin-1 is directly compatible with Unicode encodings, - // and can thus be treated as (a sub-range of) UTF-32 - while (begin < end) - { - Uint32 codepoint; - begin = Decode(begin, end, codepoint); - *output++ = codepoint < 256 ? static_cast<char>(codepoint) : replacement; - } - - return output; -} - - -//////////////////////////////////////////////////////////// -template <typename In, typename Out> -Out Utf<8>::ToUtf8(In begin, In end, Out output) -{ - return std::copy(begin, end, output); -} - - -//////////////////////////////////////////////////////////// -template <typename In, typename Out> -Out Utf<8>::ToUtf16(In begin, In end, Out output) -{ - while (begin < end) - { - Uint32 codepoint; - begin = Decode(begin, end, codepoint); - output = Utf<16>::Encode(codepoint, output); - } - - return output; -} - - -//////////////////////////////////////////////////////////// -template <typename In, typename Out> -Out Utf<8>::ToUtf32(In begin, In end, Out output) -{ - while (begin < end) - { - Uint32 codepoint; - begin = Decode(begin, end, codepoint); - *output++ = codepoint; - } - - return output; -} - - -//////////////////////////////////////////////////////////// -template <typename In> -In Utf<16>::Decode(In begin, In end, Uint32& output, Uint32 replacement) -{ - Uint16 first = *begin++; - - // If it's a surrogate pair, first convert to a single UTF-32 character - if ((first >= 0xD800) && (first <= 0xDBFF)) - { - if (begin < end) - { - Uint32 second = *begin++; - if ((second >= 0xDC00) && (second <= 0xDFFF)) - { - // The second element is valid: convert the two elements to a UTF-32 character - output = ((first - 0xD800) << 10) + (second - 0xDC00) + 0x0010000; - } - else - { - // Invalid character - output = replacement; - } - } - else - { - // Invalid character - begin = end; - output = replacement; - } - } - else - { - // We can make a direct copy - output = first; - } - - return begin; -} - - -//////////////////////////////////////////////////////////// -template <typename Out> -Out Utf<16>::Encode(Uint32 input, Out output, Uint16 replacement) -{ - if (input <= 0xFFFF) - { - // The character can be copied directly, we just need to check if it's in the valid range - if ((input >= 0xD800) && (input <= 0xDFFF)) - { - // Invalid character (this range is reserved) - if (replacement) - *output++ = replacement; - } - else - { - // Valid character directly convertible to a single UTF-16 character - *output++ = static_cast<Uint16>(input); - } - } - else if (input > 0x0010FFFF) - { - // Invalid character (greater than the maximum Unicode value) - if (replacement) - *output++ = replacement; - } - else - { - // The input character will be converted to two UTF-16 elements - input -= 0x0010000; - *output++ = static_cast<Uint16>((input >> 10) + 0xD800); - *output++ = static_cast<Uint16>((input & 0x3FFUL) + 0xDC00); - } - - return output; -} - - -//////////////////////////////////////////////////////////// -template <typename In> -In Utf<16>::Next(In begin, In end) -{ - Uint32 codepoint; - return Decode(begin, end, codepoint); -} - - -//////////////////////////////////////////////////////////// -template <typename In> -std::size_t Utf<16>::Count(In begin, In end) -{ - std::size_t length = 0; - while (begin < end) - { - begin = Next(begin, end); - ++length; - } - - return length; -} - - -//////////////////////////////////////////////////////////// -template <typename In, typename Out> -Out Utf<16>::FromAnsi(In begin, In end, Out output, const std::locale& locale) -{ - while (begin < end) - { - Uint32 codepoint = Utf<32>::DecodeAnsi(*begin++, locale); - output = Encode(codepoint, output); - } - - return output; -} - - -//////////////////////////////////////////////////////////// -template <typename In, typename Out> -Out Utf<16>::FromWide(In begin, In end, Out output) -{ - while (begin < end) - { - Uint32 codepoint = Utf<32>::DecodeWide(*begin++); - output = Encode(codepoint, output); - } - - return output; -} - - -//////////////////////////////////////////////////////////// -template <typename In, typename Out> -Out Utf<16>::FromLatin1(In begin, In end, Out output) -{ - // Latin-1 is directly compatible with Unicode encodings, - // and can thus be treated as (a sub-range of) UTF-32 - return std::copy(begin, end, output); -} - - -//////////////////////////////////////////////////////////// -template <typename In, typename Out> -Out Utf<16>::ToAnsi(In begin, In end, Out output, char replacement, const std::locale& locale) -{ - while (begin < end) - { - Uint32 codepoint; - begin = Decode(begin, end, codepoint); - output = Utf<32>::EncodeAnsi(codepoint, output, replacement, locale); - } - - return output; -} - - -//////////////////////////////////////////////////////////// -template <typename In, typename Out> -Out Utf<16>::ToWide(In begin, In end, Out output, wchar_t replacement) -{ - while (begin < end) - { - Uint32 codepoint; - begin = Decode(begin, end, codepoint); - output = Utf<32>::EncodeWide(codepoint, output, replacement); - } - - return output; -} - - -//////////////////////////////////////////////////////////// -template <typename In, typename Out> -Out Utf<16>::ToLatin1(In begin, In end, Out output, char replacement) -{ - // Latin-1 is directly compatible with Unicode encodings, - // and can thus be treated as (a sub-range of) UTF-32 - while (begin < end) - { - *output++ = *begin < 256 ? static_cast<char>(*begin) : replacement; - begin++; - } - - return output; -} - - -//////////////////////////////////////////////////////////// -template <typename In, typename Out> -Out Utf<16>::ToUtf8(In begin, In end, Out output) -{ - while (begin < end) - { - Uint32 codepoint; - begin = Decode(begin, end, codepoint); - output = Utf<8>::Encode(codepoint, output); - } - - return output; -} - - -//////////////////////////////////////////////////////////// -template <typename In, typename Out> -Out Utf<16>::ToUtf16(In begin, In end, Out output) -{ - return std::copy(begin, end, output); -} - - -//////////////////////////////////////////////////////////// -template <typename In, typename Out> -Out Utf<16>::ToUtf32(In begin, In end, Out output) -{ - while (begin < end) - { - Uint32 codepoint; - begin = Decode(begin, end, codepoint); - *output++ = codepoint; - } - - return output; -} - - -//////////////////////////////////////////////////////////// -template <typename In> -In Utf<32>::Decode(In begin, In /*end*/, Uint32& output, Uint32 /*replacement*/) -{ - output = *begin++; - return begin; -} - - -//////////////////////////////////////////////////////////// -template <typename Out> -Out Utf<32>::Encode(Uint32 input, Out output, Uint32 /*replacement*/) -{ - *output++ = input; - return output; -} - - -//////////////////////////////////////////////////////////// -template <typename In> -In Utf<32>::Next(In begin, In /*end*/) -{ - return ++begin; -} - - -//////////////////////////////////////////////////////////// -template <typename In> -std::size_t Utf<32>::Count(In begin, In end) -{ - return begin - end; -} - - -//////////////////////////////////////////////////////////// -template <typename In, typename Out> -Out Utf<32>::FromAnsi(In begin, In end, Out output, const std::locale& locale) -{ - while (begin < end) - *output++ = DecodeAnsi(*begin++, locale); - - return output; -} - - -//////////////////////////////////////////////////////////// -template <typename In, typename Out> -Out Utf<32>::FromWide(In begin, In end, Out output) -{ - while (begin < end) - *output++ = DecodeWide(*begin++); - - return output; -} - - -//////////////////////////////////////////////////////////// -template <typename In, typename Out> -Out Utf<32>::FromLatin1(In begin, In end, Out output) -{ - // Latin-1 is directly compatible with Unicode encodings, - // and can thus be treated as (a sub-range of) UTF-32 - return std::copy(begin, end, output); -} - - -//////////////////////////////////////////////////////////// -template <typename In, typename Out> -Out Utf<32>::ToAnsi(In begin, In end, Out output, char replacement, const std::locale& locale) -{ - while (begin < end) - output = EncodeAnsi(*begin++, output, replacement, locale); - - return output; -} - - -//////////////////////////////////////////////////////////// -template <typename In, typename Out> -Out Utf<32>::ToWide(In begin, In end, Out output, wchar_t replacement) -{ - while (begin < end) - output = EncodeWide(*begin++, output, replacement); - - return output; -} - - -//////////////////////////////////////////////////////////// -template <typename In, typename Out> -Out Utf<32>::ToLatin1(In begin, In end, Out output, char replacement) -{ - // Latin-1 is directly compatible with Unicode encodings, - // and can thus be treated as (a sub-range of) UTF-32 - while (begin < end) - { - *output++ = *begin < 256 ? static_cast<char>(*begin) : replacement; - begin++; - } - - return output; -} - - -//////////////////////////////////////////////////////////// -template <typename In, typename Out> -Out Utf<32>::ToUtf8(In begin, In end, Out output) -{ - while (begin < end) - output = Utf<8>::Encode(*begin++, output); - - return output; -} - -//////////////////////////////////////////////////////////// -template <typename In, typename Out> -Out Utf<32>::ToUtf16(In begin, In end, Out output) -{ - while (begin < end) - output = Utf<16>::Encode(*begin++, output); - - return output; -} - - -//////////////////////////////////////////////////////////// -template <typename In, typename Out> -Out Utf<32>::ToUtf32(In begin, In end, Out output) -{ - return std::copy(begin, end, output); -} - - -//////////////////////////////////////////////////////////// -template <typename In> -Uint32 Utf<32>::DecodeAnsi(In input, const std::locale& locale) -{ - // On Windows, GCC's standard library (glibc++) has almost - // no support for Unicode stuff. As a consequence, in this - // context we can only use the default locale and ignore - // the one passed as parameter. - - #if defined(SFML_SYSTEM_WINDOWS) && /* if Windows ... */ \ - (defined(__GLIBCPP__) || defined (__GLIBCXX__)) && /* ... and standard library is glibc++ ... */ \ - !(defined(__SGI_STL_PORT) || defined(_STLPORT_VERSION)) /* ... and STLPort is not used on top of it */ - - (void)locale; // to avoid warnings - - wchar_t character = 0; - mbtowc(&character, &input, 1); - return static_cast<Uint32>(character); - - #else - - // Get the facet of the locale which deals with character conversion - const std::ctype<wchar_t>& facet = std::use_facet< std::ctype<wchar_t> >(locale); - - // Use the facet to convert each character of the input string - return static_cast<Uint32>(facet.widen(input)); - - #endif -} - - -//////////////////////////////////////////////////////////// -template <typename In> -Uint32 Utf<32>::DecodeWide(In input) -{ - // The encoding of wide characters is not well defined and is left to the system; - // however we can safely assume that it is UCS-2 on Windows and - // UCS-4 on Unix systems. - // In both cases, a simple copy is enough (UCS-2 is a subset of UCS-4, - // and UCS-4 *is* UTF-32). - - return input; -} - - -//////////////////////////////////////////////////////////// -template <typename Out> -Out Utf<32>::EncodeAnsi(Uint32 codepoint, Out output, char replacement, const std::locale& locale) -{ - // On Windows, gcc's standard library (glibc++) has almost - // no support for Unicode stuff. As a consequence, in this - // context we can only use the default locale and ignore - // the one passed as parameter. - - #if defined(SFML_SYSTEM_WINDOWS) && /* if Windows ... */ \ - (defined(__GLIBCPP__) || defined (__GLIBCXX__)) && /* ... and standard library is glibc++ ... */ \ - !(defined(__SGI_STL_PORT) || defined(_STLPORT_VERSION)) /* ... and STLPort is not used on top of it */ - - (void)locale; // to avoid warnings - - char character = 0; - if (wctomb(&character, static_cast<wchar_t>(codepoint)) >= 0) - *output++ = character; - else if (replacement) - *output++ = replacement; - - return output; - - #else - - // Get the facet of the locale which deals with character conversion - const std::ctype<wchar_t>& facet = std::use_facet< std::ctype<wchar_t> >(locale); - - // Use the facet to convert each character of the input string - *output++ = facet.narrow(static_cast<wchar_t>(codepoint), replacement); - - return output; - - #endif -} - - -//////////////////////////////////////////////////////////// -template <typename Out> -Out Utf<32>::EncodeWide(Uint32 codepoint, Out output, wchar_t replacement) -{ - // The encoding of wide characters is not well defined and is left to the system; - // however we can safely assume that it is UCS-2 on Windows and - // UCS-4 on Unix systems. - // For UCS-2 we need to check if the source characters fits in (UCS-2 is a subset of UCS-4). - // For UCS-4 we can do a direct copy (UCS-4 *is* UTF-32). - - switch (sizeof(wchar_t)) - { - case 4: - { - *output++ = static_cast<wchar_t>(codepoint); - break; - } - - default: - { - if ((codepoint <= 0xFFFF) && ((codepoint < 0xD800) || (codepoint > 0xDFFF))) - { - *output++ = static_cast<wchar_t>(codepoint); - } - else if (replacement) - { - *output++ = replacement; - } - break; - } - } - - return output; -} |