MemoryCopy streamers and CMake features

This commit is contained in:
Jack Andersen 2015-07-07 20:03:08 -10:00
parent c65ef591f5
commit b7ba46b995
34 changed files with 397 additions and 1124 deletions

BIN
Athena.icns Normal file

Binary file not shown.

BIN
Athena.ico Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 90 KiB

View File

@ -36,9 +36,6 @@ ATHENA_PRO=true
include(Athena.pri)
OTHER_FILES += \
.travis.yml
unix {
isEmpty(PREFIX) {
PREFIX = /usr/local

22
AthenaConfig.cmake.in Normal file
View File

@ -0,0 +1,22 @@
# - Config file for the Athena package
# It defines the following variables
# ATHENA_INCLUDE_DIR - include directory for Athena
# ATHENA_LIBRARIES - libraries to link against
# ATHENA_ICON - path to Athena.ico
# Compute paths
get_filename_component(ATHENA_CMAKE_DIR "${CMAKE_CURRENT_LIST_FILE}" PATH)
set(ATHENA_INCLUDE_DIR "@CONF_INCLUDE_DIR@")
# Our library dependencies (contains definitions for IMPORTED targets)
if(NOT TARGET AthenaCore AND NOT Athena_BINARY_DIR)
include("${ATHENA_CMAKE_DIR}/AthenaTargets.cmake")
endif()
# These are IMPORTED targets created by AthenaTargets.cmake
set(ATHENA_LIBRARIES AthenaCore AthenaSakura AthenaZelda AthenaWiiSave)
# Set icon location if on windows
if(WIN32 AND NOT CYGWIN)
set(ATHENA_ICON "@CONF_ICON_DIR@")
endif()

View File

@ -0,0 +1,11 @@
set(PACKAGE_VERSION "@ATHENA_VERSION@")
# Check whether the requested PACKAGE_FIND_VERSION is compatible
if("${PACKAGE_VERSION}" VERSION_LESS "${PACKAGE_FIND_VERSION}")
set(PACKAGE_VERSION_COMPATIBLE FALSE)
else()
set(PACKAGE_VERSION_COMPATIBLE TRUE)
if ("${PACKAGE_VERSION}" VERSION_EQUAL "${PACKAGE_FIND_VERSION}")
set(PACKAGE_VERSION_EXACT TRUE)
endif()
endif()

View File

@ -56,10 +56,6 @@ HEADERS += \
$$PWD/include/LZ77/LZLookupTable.hpp \
$$PWD/include/LZ77/LZType10.hpp \
$$PWD/include/LZ77/LZType11.hpp \
$$PWD/include/utf8.h \
$$PWD/include/utf8/checked.h \
$$PWD/include/utf8/core.h \
$$PWD/include/utf8/unchecked.h \
$$PWD/include/Athena/FileInfo.hpp \
$$PWD/include/Athena/Dir.hpp \
$$PWD/include/gekko_support.h \

View File

@ -1,10 +1,24 @@
cmake_minimum_required(VERSION 3.0)
project(Athena)
##################
# Athena Version #
##################
set(ATHENA_MAJOR_VERSION 2)
set(ATHENA_MINOR_VERSION 0)
set(ATHENA_PATCH_VERSION 0)
set(ATHENA_VERSION
${ATHENA_MAJOR_VERSION}.${ATHENA_MINOR_VERSION}.${ATHENA_PATCH_VERSION})
################
# Athena Build #
################
add_subdirectory(extern)
file(GLOB ATHENA_HEADERS include/Athena/*.hpp)
include_directories(include)
include_directories(include ${LZO_INCLUDE_DIR} ${ZLIB_INCLUDE_DIR})
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -std=c++11")
if(WIN32)
@ -134,8 +148,94 @@ add_library(AthenaZelda
include/Athena/SkywardSwordQuest.hpp
)
# Offer the user the choice of overriding the installation directories
set(INSTALL_LIB_DIR lib CACHE PATH "Installation directory for libraries")
set(INSTALL_INCLUDE_DIR include CACHE PATH "Installation directory for header files")
if(WIN32 AND NOT CYGWIN)
set(DEF_INSTALL_CMAKE_DIR cmake)
else()
set(DEF_INSTALL_CMAKE_DIR lib/cmake/Athena)
endif()
set(INSTALL_CMAKE_DIR ${DEF_INSTALL_CMAKE_DIR} CACHE PATH "Installation directory for CMake files")
install(DIRECTORY include DESTINATION include/Athena)
# Make relative paths absolute (needed later on)
foreach(p LIB INCLUDE CMAKE)
set(var INSTALL_${p}_DIR)
if(NOT IS_ABSOLUTE "${${var}}")
set(ABS_${var} "${CMAKE_INSTALL_PREFIX}/${${var}}")
else()
set(ABS_${var} "${${var}}")
endif()
endforeach()
# Define installs
install(DIRECTORY include/ DESTINATION ${INSTALL_INCLUDE_DIR}/Athena)
install(TARGETS AthenaCore AthenaSakura AthenaWiiSave AthenaZelda
DESTINATION lib/Athena)
DESTINATION ${INSTALL_LIB_DIR} EXPORT AthenaTargets)
if(WIN32 AND NOT CYGWIN)
install(FILES Athena.ico DESTINATION ${INSTALL_LIB_DIR})
elseif(UNIX)
install(FILES lib/pkgconfig/libAthena.pc
DESTINATION ${INSTALL_LIB_DIR}/pkgconfig)
endif()
##################
# Package Export #
##################
# Add all targets to the build-tree export set
export(TARGETS AthenaCore AthenaSakura AthenaWiiSave AthenaZelda
FILE "${PROJECT_BINARY_DIR}/AthenaTargets.cmake")
# Export the package for use from the build-tree
# (this registers the build-tree with a global CMake-registry)
export(PACKAGE Athena)
# Create the AthenaConfig.cmake
# ... for the build tree
set(CONF_INCLUDE_DIR "${PROJECT_SOURCE_DIR}/include")
set(CONF_ICON_DIR "${PROJECT_SOURCE_DIR}/Athena.ico")
configure_file(AthenaConfig.cmake.in "${PROJECT_BINARY_DIR}/AthenaConfig.cmake" @ONLY)
# ... for the install tree
file(RELATIVE_PATH REL_INCLUDE_DIR "${ABS_INSTALL_CMAKE_DIR}" "${ABS_INSTALL_INCLUDE_DIR}")
file(RELATIVE_PATH REL_ICON_DIR "${ABS_INSTALL_CMAKE_DIR}" "${ABS_INSTALL_LIB_DIR}/Athena.ico")
set(CONF_INCLUDE_DIR "\${ATHENA_CMAKE_DIR}/${REL_INCLUDE_DIR}")
set(CONF_ICON_DIR "\${ATHENA_CMAKE_DIR}/${REL_ICON_DIR}")
configure_file(AthenaConfig.cmake.in "${PROJECT_BINARY_DIR}${CMAKE_FILES_DIRECTORY}/AthenaConfig.cmake" @ONLY)
# ... for both
configure_file(AthenaConfigVersion.cmake.in "${PROJECT_BINARY_DIR}/AthenaConfigVersion.cmake" @ONLY)
# Install AthenaConfig.cmake
install(FILES
"${PROJECT_BINARY_DIR}${CMAKE_FILES_DIRECTORY}/AthenaConfig.cmake"
"${PROJECT_BINARY_DIR}/AthenaConfigVersion.cmake"
DESTINATION ${INSTALL_CMAKE_DIR} COMPONENT dev)
# Install the export set for use with the install-tree
install(EXPORT AthenaTargets DESTINATION ${INSTALL_CMAKE_DIR} COMPONENT dev)
#########
# CPack #
#########
include(InstallRequiredSystemLibraries)
set(CPACK_PACKAGE_DESCRIPTION_SUMMARY "Athena")
set(CPACK_PACKAGE_VENDOR "2015 Antidote / Jackoalan")
set(CPACK_PACKAGE_DESCRIPTION_FILE "${CMAKE_CURRENT_SOURCE_DIR}/README.md")
set(CPACK_RESOURCE_FILE_LICENSE "${CMAKE_CURRENT_SOURCE_DIR}/LICENSE")
set(CPACK_PACKAGE_VERSION_MAJOR ${ATHENA_MAJOR_VERSION})
set(CPACK_PACKAGE_VERSION_MINOR ${ATHENA_MINOR_VERSION})
set(CPACK_PACKAGE_VERSION_PATCH ${ATHENA_PATCH_VERSION})
set(CPACK_PACKAGE_INSTALL_DIRECTORY "Athena")
if(WIN32 AND NOT UNIX)
# There is a bug in NSI that does not handle full unix paths properly. Make
# sure there is at least one set of four (4) backlasshes.
set(CPACK_PACKAGE_ICON "${CMAKE_CURRENT_SOURCE_DIR}/Athena.ico")
set(CPACK_NSIS_INSTALLED_ICON_NAME "Athena.ico")
set(CPACK_NSIS_DISPLAY_NAME "Athena")
set(CPACK_NSIS_URL_INFO_ABOUT "http://libathena.github.io")
set(CPACK_NSIS_CONTACT "antidote.crk@gmail.com")
set(CPACK_NSIS_MODIFY_PATH ON)
endif()
include(CPack)

View File

@ -1,14 +1,14 @@
# PKGBUILD for libAthena
_pkgname=libathena
pkgname=$_pkgname-git
pkgver=1.1.0.59.g582d2ce
pkgver=1.1.0.60.g8ca7027
pkgrel=1
pkgdesc="Basic cross platform IO library"
arch=('i686' 'x86_64')
source=("${pkgname%-*}::git+https://github.com/libAthena/Athena.git")
options=(staticlibs)
license="MIT"
makedepends=('git qt5-base sed')
makedepends=('git cmake sed')
md5sums=('SKIP')
sha256sums=('SKIP')
@ -19,11 +19,13 @@ pkgver() {
build() {
cd "$srcdir/$_pkgname"
qmake PREFIX="$pkgdir/usr" && make
mkdir build && cd build
cmake -DCMAKE_INSTALL_PREFIX="$pkgdir/usr" ..
make
}
package() {
cd "$srcdir/$_pkgname"
qmake PREFIX="$pkgdir/usr" && make install
cd "$srcdir/$_pkgname/build"
make install
}

View File

@ -1,4 +1,6 @@
add_library(lzo
find_library(LZO_LIB lzo2)
if(LZO_LIB STREQUAL LZO_LIB-NOTFOUND)
add_library(lzo2
src/lzo1.c
src/lzo1_99.c
src/lzo1a.c
@ -71,3 +73,7 @@ add_library(lzo
include/lzo/lzoconf.h
include/lzo/lzodefs.h
include/lzo/lzoutil.h)
install(DIRECTORY include/lzo DESTINATION include/lzo)
install(TARGETS lzo2 DESTINATION lib)
set(LZO_INCLUDE_DIR ${CMAKE_CURRENT_SOURCE_DIR}/include CACHE PATH "LZO include path" FORCE)
endif()

View File

@ -1,4 +1,6 @@
add_library(zlib
find_package(ZLIB)
if(NOT ZLIB_FOUND)
add_library(z
adler32.c
compress.c
crc32.c
@ -20,4 +22,8 @@ add_library(zlib
trees.h
zconf.h
zlib.h
zutil.h)
zutil.h)
install(FILES zconf.h zlib.h DESTINATION include)
install(TARGETS z DESTINATION lib)
set(ZLIB_INCLUDE_DIR ${CMAKE_CURRENT_SOURCE_DIR} CACHE PATH "Zlib include path" FORCE)
endif()

View File

@ -35,9 +35,9 @@ namespace io
* all work is done using a memory buffer, and not read directly from the disk.
* \sa BinaryReader
*/
class ALTTPFileReader : protected MemoryReader
class ALTTPFileReader : protected MemoryCopyReader
{
MEMORYREADER_BASE();
MEMORYCOPYREADER_BASE();
public:
/*! \brief This constructor takes an existing buffer to read from.

View File

@ -34,9 +34,9 @@ namespace io
* all work is done using a memory buffer, and not written directly to the disk.
* \sa BinaryReader
*/
class ALTTPFileWriter : protected MemoryWriter
class ALTTPFileWriter : protected MemoryCopyWriter
{
MEMORYWRITER_BASE();
MEMORYCOPYWRITER_BASE();
public:
/*! \brief This constructor takes an existing buffer to write to.

View File

@ -34,9 +34,9 @@ namespace io
* all work is done using a memory buffer, and not read directly from the disk.
* \sa BinaryReader
*/
class MCFileReader : public MemoryReader
class MCFileReader : public MemoryCopyReader
{
MEMORYREADER_BASE();
MEMORYCOPYREADER_BASE();
public:
/*!
* \brief This constructor takes an existing buffer to read from.

View File

@ -35,9 +35,9 @@ namespace io
* all work is done using a memory buffer, and not written directly from the disk.
* \sa BinaryWriter
*/
class MCFileWriter : protected MemoryWriter
class MCFileWriter : protected MemoryCopyWriter
{
MEMORYWRITER_BASE();
MEMORYCOPYWRITER_BASE();
public:
/*!
* \brief This constructor takes an existing buffer to write to.

View File

@ -20,21 +20,13 @@ namespace io
class MemoryReader : public IStreamReader
{
public:
~MemoryReader();
/*! \brief This constructor takes an existing buffer to read from.
/*! \brief This constructor references an existing buffer to read from.
*
* \param data The existing buffer
* \param length The length of the existing buffer
*/
MemoryReader(const atUint8* data, atUint64 length);
/*! \brief This constructor creates an instance from a file on disk.
*
* \param filename The file to create the stream from
*/
MemoryReader(const std::string& filename);
/*! \brief Sets the buffers position relative to the specified position.<br />
* It seeks relative to the current position by default.
* \param position where in the buffer to seek
@ -78,14 +70,44 @@ public:
*/
atUint8* data() const;
/*! \brief Reads a specified number of bytes to user-allocated buffer
* \param buf User-allocated buffer pointer
* \param len Length to read
* \return Number of bytes read
*/
atUint64 readUBytesToBuf(void* buf, atUint64 len);
protected:
const atUint8* m_data;
atUint64 m_length;
atUint64 m_position;
};
class MemoryCopyReader : public MemoryReader
{
public:
/*! \brief This constructor copies an existing buffer to read from.
*
* \param data The existing buffer
* \param length The length of the existing buffer
*/
MemoryCopyReader(const atUint8* data, atUint64 length);
/*! \brief This constructor creates an instance from a file on disk.
*
* \param filename The file to create the stream from
*/
MemoryCopyReader(const std::string& filename)
: MemoryReader(NULL, 0),
m_filepath(filename)
{loadData();}
void setData(const atUint8* data, atUint64 length);
protected:
void loadData();
atUint8* m_data;
atUint64 m_length;
std::unique_ptr<atUint8[]> m_dataCopy;
std::string m_filepath; //!< Path to the target file
atUint64 m_position;
};
} // io
@ -98,4 +120,11 @@ private: \
#endif // MEMORYREADER_BASE
#ifndef MEMORYCOPYREADER_BASE
#define MEMORYCOPYREADER_BASE() \
private: \
typedef Athena::io::MemoryCopyReader base
#endif // MEMORYCOPYREADER_BASE
#endif // MEMORYREADER_HPP

View File

@ -21,21 +21,13 @@ namespace io
class MemoryWriter : public IStreamWriter
{
public:
~MemoryWriter();
/*! \brief This constructor takes an existing buffer to write to.
/*! \brief This constructor references an existing buffer to write to in-place.
*
* \param data The existing buffer
* \param length The length of the existing buffer
*/
explicit MemoryWriter(atUint8* data = nullptr, atUint64 length = 0x10);
/*! \brief This constructor creates an instance from a file on disk.
*
* \param filename The file to create the stream from
*/
MemoryWriter(const std::string& filename, std::function<void(int)> progressFun = nullptr);
explicit MemoryWriter(atUint8* data, atUint64 length);
/*! \brief Sets the buffers position relative to the specified position.<br />
* It seeks relative to the current position by default.
@ -70,7 +62,7 @@ public:
* \param length The length of the new buffer.
* \throw IOException
*/
void setData(const atUint8* data, atUint64 length);
void setData(atUint8* data, atUint64 length);
/*! \brief Returns a copy of the current buffer.<br />
@ -111,13 +103,62 @@ public:
void writeUBytes(const atUint8* data, atUint64 len);
protected:
MemoryWriter() {}
atUint8* m_data;
atUint64 m_length;
std::string m_filepath; //!< Path to the target file
atUint64 m_position;
std::string m_filepath; //!< Path to the target file
};
class MemoryCopyWriter : public MemoryWriter
{
public:
/*! \brief This constructor copies an existing buffer to write to.
*
* \param data The existing buffer
* \param length The length of the existing buffer
*/
explicit MemoryCopyWriter(atUint8* data=nullptr, atUint64 length=0x10);
/*! \brief This constructor creates an instance from a file on disk.
*
* \param filename The file to create the stream from
*/
MemoryCopyWriter(const std::string& filename);
/*! \brief Sets the buffers position relative to the specified position.<br />
* It seeks relative to the current position by default.
* \param position where in the buffer to seek
* \param origin The Origin to seek \sa SeekOrigin
*/
void seek(atInt64 pos, SeekOrigin origin = SeekOrigin::Current);
/*! \brief Sets the buffer to the given one, deleting the current one.<br />
* <b>BEWARE:</b> As this deletes the current buffer it WILL cause a loss of data
* if that was not the intent.<br />
* Once you pass the data to setData <b>DO NOT</b> delete the buffer
* as Stream now owns the address, this is done to keep memory usage down.
* \param data The new buffer.
* \param length The length of the new buffer.
* \throw IOException
*/
void setData(const atUint8* data, atUint64 length);
/*! \brief Writes the given buffer with the specified length, buffers can be bigger than the length
* however it's undefined behavior to try and write a buffer which is smaller than the given length.
*
* \param data The buffer to write
* \param length The amount to write
*/
void writeUBytes(const atUint8* data, atUint64 len);
protected:
std::unique_ptr<atUint8[]> m_dataCopy;
private:
void resize(atUint64 newSize);
};
}
}
@ -126,4 +167,11 @@ private:
private: \
typedef Athena::io::MemoryWriter base
#endif // BINARYWRITER_BASE
#ifndef MEMORYCOPYWRITER_BASE
#define MEMORYCOPYWRITER_BASE() \
private: \
typedef Athena::io::MemoryCopyWriter base
#endif // BINARYWRITER_BASE
#endif // MEMORYWRITER_HPP

View File

@ -24,9 +24,9 @@ namespace Athena
class SkywardSwordFile;
namespace io
{
class SkywardSwordFileReader : public MemoryReader
class SkywardSwordFileReader : public MemoryCopyReader
{
MEMORYREADER_BASE();
MEMORYCOPYREADER_BASE();
public:
SkywardSwordFileReader(atUint8* data, atUint64 length);

View File

@ -26,9 +26,9 @@ class SkywardSwordFile;
namespace io
{
class SkywardSwordFileWriter : public MemoryWriter
class SkywardSwordFileWriter : public MemoryCopyWriter
{
MEMORYWRITER_BASE();
MEMORYCOPYWRITER_BASE();
public:
SkywardSwordFileWriter(atUint8* data, atUint64 len);
SkywardSwordFileWriter(const std::string& filename);

View File

@ -29,9 +29,9 @@ class SpriteFile;
namespace io
{
class SpriteFileReader : public MemoryReader
class SpriteFileReader : public MemoryCopyReader
{
MEMORYREADER_BASE();
MEMORYCOPYREADER_BASE();
public:
SpriteFileReader(atUint8* data, atUint64 length);
SpriteFileReader(const std::string& filepath);

View File

@ -29,9 +29,9 @@ class SpriteFile;
namespace io
{
class SpriteFileWriter : public MemoryWriter
class SpriteFileWriter : public MemoryCopyWriter
{
MEMORYWRITER_BASE();
MEMORYCOPYWRITER_BASE();
public:
SpriteFileWriter(atUint8* data, atUint64 length);

View File

@ -37,9 +37,9 @@ namespace io
* all work is done using a memory buffer, and not read directly from the disk.
* \sa BinaryReader
*/
class WiiSaveReader : protected MemoryReader
class WiiSaveReader : protected MemoryCopyReader
{
MEMORYREADER_BASE();
MEMORYCOPYREADER_BASE();
public:
/*! \brief This constructor takes an existing buffer to read from.
*

View File

@ -36,9 +36,9 @@ namespace io
* all work is done using a memory buffer, and not written directly to the disk.
* \sa BinaryReader
*/
class WiiSaveWriter : protected MemoryWriter
class WiiSaveWriter : protected MemoryCopyWriter
{
MEMORYWRITER_BASE();
MEMORYCOPYWRITER_BASE();
public:
/*! \brief This constructor creates an instance from a file on disk.
*

View File

@ -29,9 +29,9 @@ namespace io
/*!
* \brief The ZQuestFileReader class
*/
class ZQuestFileReader : protected MemoryReader
class ZQuestFileReader : protected MemoryCopyReader
{
MEMORYREADER_BASE();
MEMORYCOPYREADER_BASE();
public:
/*!

View File

@ -29,9 +29,9 @@ namespace io
/*!
* \brief The ZQuestFileWriter class
*/
class ZQuestFileWriter : protected MemoryWriter
class ZQuestFileWriter : protected MemoryCopyWriter
{
MEMORYWRITER_BASE();
MEMORYCOPYWRITER_BASE();
public:
/*!

View File

@ -1,34 +0,0 @@
// Copyright 2006 Nemanja Trifunovic
/*
Permission is hereby granted, free of charge, to any person or organization
obtaining a copy of the software and accompanying documentation covered by
this license (the "Software") to use, reproduce, display, distribute,
execute, and transmit the Software, and to prepare derivative works of the
Software, and to permit third-parties to whom the Software is furnished to
do so, all subject to the following:
The copyright notices in the Software and this entire statement, including
the above license grant, this restriction and the following disclaimer,
must be included in all copies of the Software, in whole or in part, and
all derivative works of the Software, unless such copies or derivative
works are solely in the form of machine-executable object code generated by
a source language processor.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT. IN NO EVENT
SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE
FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE,
ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
DEALINGS IN THE SOFTWARE.
*/
#ifndef UTF8_FOR_CPP_2675DCD0_9480_4c0c_B92A_CC14C027B731
#define UTF8_FOR_CPP_2675DCD0_9480_4c0c_B92A_CC14C027B731
#include "utf8/checked.h"
#include "utf8/unchecked.h"
#endif // header guard

View File

@ -1,370 +0,0 @@
// Copyright 2006 Nemanja Trifunovic
/*
Permission is hereby granted, free of charge, to any person or organization
obtaining a copy of the software and accompanying documentation covered by
this license (the "Software") to use, reproduce, display, distribute,
execute, and transmit the Software, and to prepare derivative works of the
Software, and to permit third-parties to whom the Software is furnished to
do so, all subject to the following:
The copyright notices in the Software and this entire statement, including
the above license grant, this restriction and the following disclaimer,
must be included in all copies of the Software, in whole or in part, and
all derivative works of the Software, unless such copies or derivative
works are solely in the form of machine-executable object code generated by
a source language processor.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT. IN NO EVENT
SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE
FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE,
ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
DEALINGS IN THE SOFTWARE.
*/
#ifndef UTF8_FOR_CPP_CHECKED_H_2675DCD0_9480_4c0c_B92A_CC14C027B731
#define UTF8_FOR_CPP_CHECKED_H_2675DCD0_9480_4c0c_B92A_CC14C027B731
#include "core.h"
#include <stdexcept>
namespace utf8
{
// Base for the exceptions that may be thrown from the library
class exception : public ::std::exception
{
};
// Exceptions that may be thrown from the library functions.
class invalid_code_point : public exception
{
uint32_t cp;
public:
invalid_code_point(uint32_t cp) : cp(cp) {}
virtual const char* what() const throw() { return "Invalid code point"; }
uint32_t code_point() const {return cp;}
};
class invalid_utf8 : public exception
{
uint8_t u8;
public:
invalid_utf8(uint8_t u) : u8(u) {}
virtual const char* what() const throw() { return "Invalid UTF-8"; }
uint8_t utf8_octet() const {return u8;}
};
class invalid_utf16 : public exception
{
uint16_t u16;
public:
invalid_utf16(uint16_t u) : u16(u) {}
virtual const char* what() const throw() { return "Invalid UTF-16"; }
uint16_t utf16_word() const {return u16;}
};
class not_enough_room : public exception
{
public:
virtual const char* what() const throw() { return "Not enough space"; }
};
/// The library API - functions intended to be called by the users
template <typename octet_iterator>
octet_iterator append(uint32_t cp, octet_iterator result)
{
if (!utf8::internal::is_code_point_valid(cp))
throw invalid_code_point(cp);
if (cp < 0x80) // one octet
*(result++) = static_cast<uint8_t>(cp);
else if (cp < 0x800) // two octets
{
*(result++) = static_cast<uint8_t>((cp >> 6) | 0xc0);
*(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80);
}
else if (cp < 0x10000) // three octets
{
*(result++) = static_cast<uint8_t>((cp >> 12) | 0xe0);
*(result++) = static_cast<uint8_t>(((cp >> 6) & 0x3f) | 0x80);
*(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80);
}
else // four octets
{
*(result++) = static_cast<uint8_t>((cp >> 18) | 0xf0);
*(result++) = static_cast<uint8_t>(((cp >> 12) & 0x3f) | 0x80);
*(result++) = static_cast<uint8_t>(((cp >> 6) & 0x3f) | 0x80);
*(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80);
}
return result;
}
template <typename octet_iterator, typename output_iterator>
output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out, uint32_t replacement)
{
while (start != end)
{
octet_iterator sequence_start = start;
internal::utf_error err_code = utf8::internal::validate_next(start, end);
switch (err_code)
{
case internal::UTF8_OK :
for (octet_iterator it = sequence_start; it != start; ++it)
*out++ = *it;
break;
case internal::NOT_ENOUGH_ROOM:
throw not_enough_room();
case internal::INVALID_LEAD:
utf8::append(replacement, out);
++start;
break;
case internal::INCOMPLETE_SEQUENCE:
case internal::OVERLONG_SEQUENCE:
case internal::INVALID_CODE_POINT:
utf8::append(replacement, out);
++start;
// just one replacement mark for the sequence
while (start != end && utf8::internal::is_trail(*start))
++start;
break;
}
}
return out;
}
template <typename octet_iterator, typename output_iterator>
inline output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out)
{
static const uint32_t replacement_marker = utf8::internal::mask16(0xfffd);
return utf8::replace_invalid(start, end, out, replacement_marker);
}
template <typename octet_iterator>
uint32_t next(octet_iterator& it, octet_iterator end)
{
uint32_t cp = 0;
internal::utf_error err_code = utf8::internal::validate_next(it, end, cp);
switch (err_code)
{
case internal::UTF8_OK :
break;
case internal::NOT_ENOUGH_ROOM :
throw not_enough_room();
case internal::INVALID_LEAD :
case internal::INCOMPLETE_SEQUENCE :
case internal::OVERLONG_SEQUENCE :
throw invalid_utf8(*it);
case internal::INVALID_CODE_POINT :
throw invalid_code_point(cp);
}
return cp;
}
template <typename octet_iterator>
uint32_t peek_next(octet_iterator it, octet_iterator end)
{
return utf8::next(it, end);
}
template <typename octet_iterator>
uint32_t prior(octet_iterator& it, octet_iterator start)
{
// can't do much if it == start
if (it == start)
throw not_enough_room();
octet_iterator end = it;
// Go back until we hit either a lead octet or start
while (utf8::internal::is_trail(*(--it)))
if (it == start)
throw invalid_utf8(*it); // error - no lead byte in the sequence
return utf8::peek_next(it, end);
}
/// Deprecated in versions that include "prior"
template <typename octet_iterator>
uint32_t previous(octet_iterator& it, octet_iterator pass_start)
{
octet_iterator end = it;
while (utf8::internal::is_trail(*(--it)))
if (it == pass_start)
throw invalid_utf8(*it); // error - no lead byte in the sequence
octet_iterator temp = it;
return utf8::next(temp, end);
}
template <typename octet_iterator, typename distance_type>
void advance(octet_iterator& it, distance_type n, octet_iterator end)
{
for (distance_type i = 0; i < n; ++i)
utf8::next(it, end);
}
template <typename octet_iterator>
typename std::iterator_traits<octet_iterator>::difference_type
distance(octet_iterator first, octet_iterator last)
{
typename std::iterator_traits<octet_iterator>::difference_type dist;
for (dist = 0; first < last; ++dist)
utf8::next(first, last);
return dist;
}
template <typename u16bit_iterator, typename octet_iterator>
octet_iterator utf16to8(u16bit_iterator start, u16bit_iterator end, octet_iterator result)
{
while (start != end)
{
uint32_t cp = utf8::internal::mask16(*start++);
// Take care of surrogate pairs first
if (utf8::internal::is_lead_surrogate(cp))
{
if (start != end)
{
uint32_t trail_surrogate = utf8::internal::mask16(*start++);
if (utf8::internal::is_trail_surrogate(trail_surrogate))
cp = (cp << 10) + trail_surrogate + internal::SURROGATE_OFFSET;
else
throw invalid_utf16(static_cast<uint16_t>(trail_surrogate));
}
else
throw invalid_utf16(static_cast<uint16_t>(cp));
}
// Lone trail surrogate
else if (utf8::internal::is_trail_surrogate(cp))
throw invalid_utf16(static_cast<uint16_t>(cp));
result = utf8::append(cp, result);
}
return result;
}
template <typename u16bit_iterator, typename octet_iterator>
u16bit_iterator utf8to16(octet_iterator start, octet_iterator end, u16bit_iterator result)
{
while (start != end)
{
uint32_t cp = utf8::next(start, end);
if (cp > 0xffff) //make a surrogate pair
{
*result++ = static_cast<uint16_t>((cp >> 10) + internal::LEAD_OFFSET);
*result++ = static_cast<uint16_t>((cp & 0x3ff) + internal::TRAIL_SURROGATE_MIN);
}
else
*result++ = static_cast<uint16_t>(cp);
}
return result;
}
template <typename octet_iterator, typename u32bit_iterator>
octet_iterator utf32to8(u32bit_iterator start, u32bit_iterator end, octet_iterator result)
{
while (start != end)
result = utf8::append(*(start++), result);
return result;
}
template <typename octet_iterator, typename u32bit_iterator>
u32bit_iterator utf8to32(octet_iterator start, octet_iterator end, u32bit_iterator result)
{
while (start != end)
(*result++) = utf8::next(start, end);
return result;
}
// The iterator class
template <typename octet_iterator>
class iterator : public std::iterator <std::bidirectional_iterator_tag, uint32_t>
{
octet_iterator it;
octet_iterator range_start;
octet_iterator range_end;
public:
iterator() {};
explicit iterator(const octet_iterator& octet_it,
const octet_iterator& range_start,
const octet_iterator& range_end) :
it(octet_it), range_start(range_start), range_end(range_end)
{
if (it < range_start || it > range_end)
throw std::out_of_range("Invalid utf-8 iterator position");
}
// the default "big three" are OK
octet_iterator base() const { return it; }
uint32_t operator * () const
{
octet_iterator temp = it;
return utf8::next(temp, range_end);
}
bool operator == (const iterator& rhs) const
{
if (range_start != rhs.range_start || range_end != rhs.range_end)
throw std::logic_error("Comparing utf-8 iterators defined with different ranges");
return (it == rhs.it);
}
bool operator != (const iterator& rhs) const
{
return !(operator == (rhs));
}
iterator& operator ++ ()
{
utf8::next(it, range_end);
return *this;
}
iterator operator ++ (int)
{
iterator temp = *this;
utf8::next(it, range_end);
return temp;
}
iterator& operator -- ()
{
utf8::prior(it, range_start);
return *this;
}
iterator operator -- (int)
{
iterator temp = *this;
utf8::prior(it, range_start);
return temp;
}
}; // class iterator
} // namespace utf8
#endif //header guard

View File

@ -1,347 +0,0 @@
// Copyright 2006 Nemanja Trifunovic
/*
Permission is hereby granted, free of charge, to any person or organization
obtaining a copy of the software and accompanying documentation covered by
this license (the "Software") to use, reproduce, display, distribute,
execute, and transmit the Software, and to prepare derivative works of the
Software, and to permit third-parties to whom the Software is furnished to
do so, all subject to the following:
The copyright notices in the Software and this entire statement, including
the above license grant, this restriction and the following disclaimer,
must be included in all copies of the Software, in whole or in part, and
all derivative works of the Software, unless such copies or derivative
works are solely in the form of machine-executable object code generated by
a source language processor.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT. IN NO EVENT
SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE
FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE,
ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
DEALINGS IN THE SOFTWARE.
*/
#ifndef UTF8_FOR_CPP_CORE_H_2675DCD0_9480_4c0c_B92A_CC14C027B731
#define UTF8_FOR_CPP_CORE_H_2675DCD0_9480_4c0c_B92A_CC14C027B731
#include <iterator>
namespace utf8
{
// The typedefs for 8-bit, 16-bit and 32-bit unsigned integers
// You may need to change them to match your system.
// These typedefs have the same names as ones from cstdint, or boost/cstdint
typedef unsigned char uint8_t;
typedef unsigned short uint16_t;
typedef unsigned int uint32_t;
// Helper code - not intended to be directly called by the library users. May be changed at any time
namespace internal
{
// Unicode constants
// Leading (high) surrogates: 0xd800 - 0xdbff
// Trailing (low) surrogates: 0xdc00 - 0xdfff
const uint16_t LEAD_SURROGATE_MIN = 0xd800u;
const uint16_t LEAD_SURROGATE_MAX = 0xdbffu;
const uint16_t TRAIL_SURROGATE_MIN = 0xdc00u;
const uint16_t TRAIL_SURROGATE_MAX = 0xdfffu;
const uint16_t LEAD_OFFSET = LEAD_SURROGATE_MIN - (0x10000 >> 10);
const uint32_t SURROGATE_OFFSET = 0x10000u - (LEAD_SURROGATE_MIN << 10) - TRAIL_SURROGATE_MIN;
// Maximum valid value for a Unicode code point
const uint32_t CODE_POINT_MAX = 0x0010ffffu;
template<typename octet_type>
inline uint8_t mask8(octet_type oc)
{
return static_cast<uint8_t>(0xff & oc);
}
template<typename u16_type>
inline uint16_t mask16(u16_type oc)
{
return static_cast<uint16_t>(0xffff & oc);
}
template<typename octet_type>
inline bool is_trail(octet_type oc)
{
return ((utf8::internal::mask8(oc) >> 6) == 0x2);
}
template <typename u16>
inline bool is_lead_surrogate(u16 cp)
{
return (cp >= LEAD_SURROGATE_MIN && cp <= LEAD_SURROGATE_MAX);
}
template <typename u16>
inline bool is_trail_surrogate(u16 cp)
{
return (cp >= TRAIL_SURROGATE_MIN && cp <= TRAIL_SURROGATE_MAX);
}
template <typename u16>
inline bool is_surrogate(u16 cp)
{
return (cp >= LEAD_SURROGATE_MIN && cp <= TRAIL_SURROGATE_MAX);
}
template <typename u32>
inline bool is_code_point_valid(u32 cp)
{
return (cp <= CODE_POINT_MAX && !utf8::internal::is_surrogate(cp));
}
template <typename octet_iterator>
inline typename std::iterator_traits<octet_iterator>::difference_type
sequence_length(octet_iterator lead_it)
{
uint8_t lead = utf8::internal::mask8(*lead_it);
if (lead < 0x80)
return 1;
else if ((lead >> 5) == 0x6)
return 2;
else if ((lead >> 4) == 0xe)
return 3;
else if ((lead >> 3) == 0x1e)
return 4;
else
return 0;
}
template <typename octet_difference_type>
inline bool is_overlong_sequence(uint32_t cp, octet_difference_type length)
{
if (cp < 0x80)
{
if (length != 1)
return true;
}
else if (cp < 0x800)
{
if (length != 2)
return true;
}
else if (cp < 0x10000)
{
if (length != 3)
return true;
}
return false;
}
enum utf_error {UTF8_OK, NOT_ENOUGH_ROOM, INVALID_LEAD, INCOMPLETE_SEQUENCE, OVERLONG_SEQUENCE, INVALID_CODE_POINT};
/// Helper for get_sequence_x
template <typename octet_iterator>
utf_error increase_safely(octet_iterator& it, octet_iterator end)
{
if (++it == end)
return NOT_ENOUGH_ROOM;
if (!utf8::internal::is_trail(*it))
return INCOMPLETE_SEQUENCE;
return UTF8_OK;
}
#define UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(IT, END) {utf_error ret = increase_safely(IT, END); if (ret != UTF8_OK) return ret;}
/// get_sequence_x functions decode utf-8 sequences of the length x
template <typename octet_iterator>
utf_error get_sequence_1(octet_iterator& it, octet_iterator end, uint32_t& code_point)
{
if (it == end)
return NOT_ENOUGH_ROOM;
code_point = utf8::internal::mask8(*it);
return UTF8_OK;
}
template <typename octet_iterator>
utf_error get_sequence_2(octet_iterator& it, octet_iterator end, uint32_t& code_point)
{
if (it == end)
return NOT_ENOUGH_ROOM;
code_point = utf8::internal::mask8(*it);
UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)
code_point = ((code_point << 6) & 0x7ff) + ((*it) & 0x3f);
return UTF8_OK;
}
template <typename octet_iterator>
utf_error get_sequence_3(octet_iterator& it, octet_iterator end, uint32_t& code_point)
{
if (it == end)
return NOT_ENOUGH_ROOM;
code_point = utf8::internal::mask8(*it);
UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)
code_point = ((code_point << 12) & 0xffff) + ((utf8::internal::mask8(*it) << 6) & 0xfff);
UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)
code_point += (*it) & 0x3f;
return UTF8_OK;
}
template <typename octet_iterator>
utf_error get_sequence_4(octet_iterator& it, octet_iterator end, uint32_t& code_point)
{
if (it == end)
return NOT_ENOUGH_ROOM;
code_point = utf8::internal::mask8(*it);
UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)
code_point = ((code_point << 18) & 0x1fffff) + ((utf8::internal::mask8(*it) << 12) & 0x3ffff);
UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)
code_point += (utf8::internal::mask8(*it) << 6) & 0xfff;
UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)
code_point += (*it) & 0x3f;
return UTF8_OK;
}
#undef UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR
template <typename octet_iterator>
utf_error validate_next(octet_iterator& it, octet_iterator end, uint32_t& code_point)
{
// Save the original value of it so we can go back in case of failure
// Of course, it does not make much sense with i.e. stream iterators
octet_iterator original_it = it;
uint32_t cp = 0;
// Determine the sequence length based on the lead octet
typedef typename std::iterator_traits<octet_iterator>::difference_type octet_difference_type;
const octet_difference_type length = utf8::internal::sequence_length(it);
// Get trail octets and calculate the code point
utf_error err = UTF8_OK;
switch (length)
{
case 0:
return INVALID_LEAD;
case 1:
err = utf8::internal::get_sequence_1(it, end, cp);
break;
case 2:
err = utf8::internal::get_sequence_2(it, end, cp);
break;
case 3:
err = utf8::internal::get_sequence_3(it, end, cp);
break;
case 4:
err = utf8::internal::get_sequence_4(it, end, cp);
break;
}
if (err == UTF8_OK)
{
// Decoding succeeded. Now, security checks...
if (utf8::internal::is_code_point_valid(cp))
{
if (!utf8::internal::is_overlong_sequence(cp, length))
{
// Passed! Return here.
code_point = cp;
++it;
return UTF8_OK;
}
else
err = OVERLONG_SEQUENCE;
}
else
err = INVALID_CODE_POINT;
}
// Failure branch - restore the original value of the iterator
it = original_it;
return err;
}
template <typename octet_iterator>
inline utf_error validate_next(octet_iterator& it, octet_iterator end)
{
uint32_t ignored;
return utf8::internal::validate_next(it, end, ignored);
}
} // namespace internal
/// The library API - functions intended to be called by the users
// Byte order mark
const uint8_t bom[] = {0xef, 0xbb, 0xbf};