Peerplays_Blockchain/peerplays-fc
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Merge branch 'phoenix' of github.com:InvictusInnovations/fc into phoenix

Browse source
This commit is contained in:
Daniel Larimer 2014-01-14 03:51:20 -05:00
commit d4e5d604a5
19 changed files with 2910 additions and 18 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

14
CMakeLists.txt
View file

@ -11,6 +11,10 @@ INCLUDE_DIRECTORIES( ${CMAKE_SOURCE_DIR} )
INCLUDE_DIRECTORIES( ${CMAKE_SOURCE_DIR}/include )
INCLUDE_DIRECTORIES( ${CMAKE_CURRENT_SOURCE_DIR}/vendor/cyoencode-1.0.2/src )
list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_SOURCE_DIR}/GitVersionGen/")
include(GetGitRevisionDescription)
get_git_head_revision(GIT_REFSPEC GIT_SHA3)
SET( DEFAULT_HEADER_INSTALL_DIR include/\${target} )
SET( DEFAULT_LIBRARY_INSTALL_DIR lib/ )
SET( DEFAULT_EXECUTABLE_INSTALL_DIR bin/ )
@ -77,8 +81,9 @@ set( fc_sources
src/thread/mutex.cpp
src/asio.cpp
src/string.cpp
src/shared_ptr.cpp
src/time.cpp
src/shared_ptr.cpp
src/time.cpp
src/utf8.cpp
src/io/iostream.cpp
src/io/datastream.cpp
src/io/buffered_iostream.cpp
@ -130,6 +135,7 @@ set( fc_sources
# vendor/salsa20/ecrypt.c
${SALSA_SRC}
)
SET_PROPERTY( SOURCE
vendor/salsa20/salsa20.s
PROPERTY LANGUAGE C)
@ -137,6 +143,10 @@ set( fc_sources
set( sources
${fc_sources}
)
configure_file("${CMAKE_CURRENT_SOURCE_DIR}/GitSHA3.cpp.in" "${CMAKE_CURRENT_BINARY_DIR}/GitSHA3.cpp" @ONLY)
list(APPEND sources "${CMAKE_CURRENT_BINARY_DIR}/GitSHA3.cpp" GitSHA3.h)
add_subdirectory( vendor/easylzma )
setup_library( fc SOURCES ${sources} LIBRARY_TYPE STATIC )

4
GitSHA3.cpp.in Normal file
View file

@ -0,0 +1,4 @@
#include "GitSHA3.h"
#define GIT_SHA3 "@GIT_SHA3@"
const char* const g_GIT_SHA3 = GIT_SHA3;

8
GitSHA3.h Normal file
View file

@ -0,0 +1,8 @@
#ifndef __GITSHA3_H
#define __GITSHA3_H
extern const char* const g_GIT_SHA3;
#define APPLICATION_VERSION "1.0 Beta1"
#endif ///__GITSHA3_H

57
fc.natvis Normal file
View file

@ -0,0 +1,57 @@
<?xml version="1.0" encoding="utf-8"?>
<!-- This file contains Debugger Visualizers for the FC library. It's hard to navigate the
FC objects in a debugger because the tricks used in classes like fc::fwd require manual
casting to view the underlying objects in the debugger. This file tells the Visual
Studio debugger how to see through these tricks and traverse the classes naturally.
To install, drop this file in your My Documents\Visual Studio 2012\Visualizers directory
In addition, consider grabbing the .natvis files from the C++ Debugger Visualizers
project here to improve display of boost objects:
https://github.com/KindDragon/CPPDebuggerVisualizers#c-debugger-visualizers-
-->
<AutoVisualizer xmlns="http://schemas.microsoft.com/vstudio/debugger/natvis/2010">
<Type Name="fc::variant">
<Expand>
<Item Name="value" Condition="(fc::variant::type_id)(*(((char*)(&amp;_data)) + sizeof(fc::variant) - 1)) == fc::variant::int64_type">*(const int64_t*)(&amp;_data)</Item>
<Item Name="value" Condition="(fc::variant::type_id)(*(((char*)(&amp;_data)) + sizeof(fc::variant) - 1)) == fc::variant::uint64_type">*(const uint64_t*)(&amp;_data)</Item>
<Item Name="value" Condition="(fc::variant::type_id)(*(((char*)(&amp;_data)) + sizeof(fc::variant) - 1)) == fc::variant::double_type">*(const double*)(&amp;_data)</Item>
<Item Name="value" Condition="(fc::variant::type_id)(*(((char*)(&amp;_data)) + sizeof(fc::variant) - 1)) == fc::variant::bool_type">*(const bool*)(&amp;_data)</Item>
<Item Name="value" Condition="(fc::variant::type_id)(*(((char*)(&amp;_data)) + sizeof(fc::variant) - 1)) == fc::variant::string_type">*(const const_string_ptr*)(&amp;_data)</Item>
<Item Name="value" Condition="(fc::variant::type_id)(*(((char*)(&amp;_data)) + sizeof(fc::variant) - 1)) == fc::variant::array_type">*(const const_variants_ptr*)(&amp;_data)</Item>
<Item Name="value" Condition="(fc::variant::type_id)(*(((char*)(&amp;_data)) + sizeof(fc::variant) - 1)) == fc::variant::object_type">*(const const_variant_object_ptr*)(&amp;_data)</Item>
<Item Name="type">(fc::variant::type_id)(*(((char*)(&amp;_data)) + sizeof(fc::variant) - 1))</Item>
</Expand>
</Type>
<Type Name="fc::fwd&lt;*&gt;">
<DisplayString>{*($T1*)(((_store)._store)._data)}</DisplayString>
<Expand>
<ExpandedItem>($T1*)(((_store)._store)._data)</ExpandedItem>
</Expand>
</Type>
<Type Name="fc::string">
<DisplayString>{my}</DisplayString>
<Expand>
<ExpandedItem>my</ExpandedItem>
</Expand>
</Type>
<Type Name="fc::optional&lt;*&gt;">
<DisplayString Condition="!_valid">invalid</DisplayString>
<DisplayString>valid, value = {*(($T1*)_value)}</DisplayString>
<Expand>
<Item Name="_value">($T1*)_value</Item>
<Item Name="_valid">_valid</Item>
</Expand>
</Type>
<Type Name="fc::path">
<DisplayString>{_p}</DisplayString>
<Expand>
<ExpandedItem>_p</ExpandedItem>
</Expand>
</Type>
</AutoVisualizer>

26
include/fc/filesystem.hpp
View file

@ -30,6 +30,8 @@ namespace fc {
~path();
path( const boost::filesystem::path& );
path( const fc::string& p );
/// Constructor to build path using unicode native characters.
path(const std::wstring& p);
path( const char* );
path( const path& p );
path( path&& p );
@ -45,13 +47,23 @@ namespace fc {
operator boost::filesystem::path& ();
operator const boost::filesystem::path& ()const;
void replace_extension( const fc::path& e );
fc::path stem()const;
fc::path extension()const;
fc::path filename()const;
fc::path parent_path()const;
fc::string string()const;
fc::string generic_string()const;
void replace_extension( const fc::path& e );
fc::path stem()const;
fc::path extension()const;
fc::path filename()const;
fc::path parent_path()const;
fc::string string()const;
fc::string generic_string()const;
std::wstring wstring() const;
std::wstring generic_wstring() const;
/** Retrieves native string path representation and next converts it into
ANSI UTF-8 representation.
It is needed since not all parts of fc library accept unicode paths
(fc::file_mapping).
*/
std::string toNativeAnsiPath() const;
/**
* @brief replaces '/' with '\' in the result of generic_string()

2
include/fc/thread/task.hpp
View file

@ -13,7 +13,7 @@ namespace fc {
void run();
protected:
~task_base();
/// Task priority looks like unsupported feature.
uint64_t _posted_num;
priority _prio;
time_point _when;

26
include/fc/utf8.hpp Normal file
View file

@ -0,0 +1,26 @@
#ifndef __UTF8_HPP
#define __UTF8_HPP
#include <string>
/// This file contains general purpose utilities related to UTF-8 <-> Unicode conversions
namespace fc
{
/** Decodes utf 8 std::string into unicode string.
@param input - input string to be decoded and stored in 'storage'
@param storage - buffer for converted text. Cannot be nullptr.
*/
void decodeUtf8(const std::string& input, std::wstring* storage);
/** Encodes given wide (unicode) string into UTF-8 representation.
@param input - input string to be encoded and stored in 'storage'
@param storage - buffer for converted text. Cannot be nullptr.
*/
void encodeUtf8(const std::wstring& input, std::string* storage);
} /// namespace fc
#endif ///__UTF8_HPP

52
src/filesystem.cpp
View file

@ -4,14 +4,29 @@
#include <fc/fwd_impl.hpp>
#include <fc/utility.hpp>
#include <fc/io/fstream.hpp>
#include <fc/utf8.hpp>
#include <fc/variant.hpp>
#include <boost/config.hpp>
#include <boost/filesystem.hpp>
#include <fc/variant.hpp>
#ifdef WIN32
#include <windows.h>
#endif
namespace fc {
void to_variant( const fc::path& t, variant& v ) {
v = t.generic_string();
std::string path = t.toNativeAnsiPath();
for(auto& c : path)
{
if(c == '\\')
c = '/';
}
v = path;
}
void from_variant( const fc::variant& v, fc::path& t ) {
t = fc::path(v.as_string());
}
@ -29,6 +44,9 @@ namespace fc {
path::path( const fc::string& p )
:_p(p.c_str()){}
path::path(const std::wstring& p)
:_p(p) {}
path::path( const path& p )
:_p(p){}
@ -67,6 +85,36 @@ namespace fc {
fc::string path::generic_string()const {
return _p->generic_string();
}
std::wstring path::wstring() const
{
return _p->wstring();
}
std::wstring path::generic_wstring() const
{
return _p->generic_wstring();
}
std::string path::toNativeAnsiPath() const
{
std::wstring path = generic_wstring();
#ifdef WIN32
const size_t maxPath = 32*1024;
std::vector<wchar_t> shortPath;
shortPath.resize(maxPath + 1);
wchar_t* buffer = shortPath.data();
DWORD res = GetShortPathNameW(path.c_str(), buffer, maxPath);
if(res != 0)
path = buffer;
#endif
std::string filePath;
fc::encodeUtf8(path, &filePath);
return filePath;
}
/**
* @todo use iterators instead of indexes for
* faster performance

8
src/interprocess/mmap_struct.cpp
View file

@ -1,6 +1,9 @@
#include <fc/interprocess/mmap_struct.hpp>
#include <fc/filesystem.hpp>
#include <fc/io/fstream.hpp>
#include <string.h>
namespace fc
@ -29,7 +32,10 @@ namespace fc
bytes_left -= to_write;
}
}
_file_mapping.reset( new fc::file_mapping( file.generic_string().c_str(), fc::read_write ) );
std::string filePath = file.toNativeAnsiPath();
_file_mapping.reset( new fc::file_mapping( filePath.c_str(), fc::read_write ) );
_mapped_region.reset( new fc::mapped_region( *_file_mapping, fc::read_write, 0, s ) );
}
} // namespace fc

7
src/io/fstream.cpp
View file

@ -4,6 +4,7 @@
#include <fc/exception/exception.hpp>
#include <fc/log/logger.hpp>
#include <boost/filesystem/path.hpp>
namespace fc {
class ofstream::impl : public fc::retainable {
@ -23,7 +24,8 @@ namespace fc {
ofstream::~ofstream(){}
void ofstream::open( const fc::path& file, int m ) {
my->ofs.open( file.string().c_str(), std::ios::binary );
const boost::filesystem::path& bfp = file;
my->ofs.open( bfp.native(), std::ios::binary );
}
size_t ofstream::writesome( const char* buf, size_t len ) {
my->ofs.write(buf,len);
@ -49,7 +51,8 @@ namespace fc {
ifstream::~ifstream(){}
void ifstream::open( const fc::path& file, int m ) {
my->ifs.open( file.string().c_str(), std::ios::binary );
const boost::filesystem::path& bfp = file;
my->ifs.open( bfp.native(), std::ios::binary );
}
size_t ifstream::readsome( char* buf, size_t len ) {
auto s = size_t(my->ifs.readsome( buf, len ));

2
src/io/json.cpp
View file

@ -580,7 +580,7 @@ namespace fc
void json::save_to_file( const variant& v, const fc::path& fi, bool pretty )
{
fc::ofstream o( fi.generic_string().c_str() );
fc::ofstream o(fi);
fc::to_stream( o, v );
}
variant json::from_file( const fc::path& p )

7
src/thread/task.cpp
View file

@ -9,7 +9,12 @@
namespace fc {
task_base::task_base(void* func)
:_functor(func){
:
_posted_num(0),
_active_context(nullptr),
_next(nullptr),
_promise_impl(nullptr),
_functor(func){
}
void task_base::run() {

2
src/thread/thread_d.hpp
View file

@ -440,7 +440,7 @@ namespace fc {
void unblock( fc::context* c ) {
if( fc::thread::current().my != this ) {
async( [=](){ unblock(c); } );
self.async( [=](){ unblock(c); } );
return;
}
if( c != current ) ready_push_front(c);

28
src/utf8.cpp Normal file
View file

@ -0,0 +1,28 @@
#include "fc/utf8.hpp"
#include "utf8/checked.h"
#include "utf8/core.h"
#include "utf8/unchecked.h"
#include <assert.h>
namespace fc
{
void decodeUtf8(const std::string& input, std::wstring* storage)
{
assert(storage != nullptr);
utf8::utf8to32(input.begin(), input.end(), std::back_inserter(*storage));
}
void encodeUtf8(const std::wstring& input, std::string* storage)
{
assert(storage != nullptr);
utf8::utf32to8(input.begin(), input.end(), std::back_inserter(*storage));
}
} ///namespace fc

12
src/utf8/ReleaseNotes Normal file
View file

@ -0,0 +1,12 @@
utf8 cpp library
Release 2.3.4
A minor bug fix release. Thanks to all who reported bugs.
Note: Version 2.3.3 contained a regression, and therefore was removed.
Changes from version 2.3.2
- Bug fix [39]: checked.h Line 273 and unchecked.h Line 182 have an extra ';'
- Bug fix [36]: replace_invalid() only works with back_inserter
Files included in the release: utf8.h, core.h, checked.h, unchecked.h, utf8cpp.html, ReleaseNotes

327
src/utf8/checked.h Normal file
View file

@ -0,0 +1,327 @@
// 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:
out = utf8::append (replacement, out);
++start;
break;
case internal::INCOMPLETE_SEQUENCE:
case internal::OVERLONG_SEQUENCE:
case internal::INVALID_CODE_POINT:
out = 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

329
src/utf8/core.h Normal file
View file

@ -0,0 +1,329 @@
// 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};
template <typename octet_iterator>
octet_iterator find_invalid(octet_iterator start, octet_iterator end)
{
octet_iterator result = start;
while (result != end) {
utf8::internal::utf_error err_code = utf8::internal::validate_next(result, end);
if (err_code != internal::UTF8_OK)
return result;
}
return result;
}
template <typename octet_iterator>
inline bool is_valid(octet_iterator start, octet_iterator end)
{
return (utf8::find_invalid(start, end) == end);
}
template <typename octet_iterator>
inline bool starts_with_bom (octet_iterator it, octet_iterator end)
{
return (
((it != end) && (utf8::internal::mask8(*it++)) == bom[0]) &&
((it != end) && (utf8::internal::mask8(*it++)) == bom[1]) &&
((it != end) && (utf8::internal::mask8(*it)) == bom[2])
);
}
//Deprecated in release 2.3
template <typename octet_iterator>
inline bool is_bom (octet_iterator it)
{
return (
(utf8::internal::mask8(*it++)) == bom[0] &&
(utf8::internal::mask8(*it++)) == bom[1] &&
(utf8::internal::mask8(*it)) == bom[2]
);
}
} // namespace utf8
#endif // header guard

228
src/utf8/unchecked.h Normal file
View file

@ -0,0 +1,228 @@
// 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_UNCHECKED_H_2675DCD0_9480_4c0c_B92A_CC14C027B731
#define UTF8_FOR_CPP_UNCHECKED_H_2675DCD0_9480_4c0c_B92A_CC14C027B731
#include "core.h"
namespace utf8
{
namespace unchecked
{
template <typename octet_iterator>
octet_iterator append(uint32_t cp, octet_iterator result)
{
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>
uint32_t next(octet_iterator& it)
{
uint32_t cp = utf8::internal::mask8(*it);
typename std::iterator_traits<octet_iterator>::difference_type length = utf8::internal::sequence_length(it);
switch (length) {
case 1:
break;
case 2:
it++;
cp = ((cp << 6) & 0x7ff) + ((*it) & 0x3f);
break;
case 3:
++it;
cp = ((cp << 12) & 0xffff) + ((utf8::internal::mask8(*it) << 6) & 0xfff);
++it;
cp += (*it) & 0x3f;
break;
case 4:
++it;
cp = ((cp << 18) & 0x1fffff) + ((utf8::internal::mask8(*it) << 12) & 0x3ffff);
++it;
cp += (utf8::internal::mask8(*it) << 6) & 0xfff;
++it;
cp += (*it) & 0x3f;
break;
}
++it;
return cp;
}
template <typename octet_iterator>
uint32_t peek_next(octet_iterator it)
{
return utf8::unchecked::next(it);
}
template <typename octet_iterator>
uint32_t prior(octet_iterator& it)
{
while (utf8::internal::is_trail(*(--it))) ;
octet_iterator temp = it;
return utf8::unchecked::next(temp);
}
// Deprecated in versions that include prior, but only for the sake of consistency (see utf8::previous)
template <typename octet_iterator>
inline uint32_t previous(octet_iterator& it)
{
return utf8::unchecked::prior(it);
}
template <typename octet_iterator, typename distance_type>
void advance (octet_iterator& it, distance_type n)
{
for (distance_type i = 0; i < n; ++i)
utf8::unchecked::next(it);
}
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::unchecked::next(first);
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)) {
uint32_t trail_surrogate = utf8::internal::mask16(*start++);
cp = (cp << 10) + trail_surrogate + internal::SURROGATE_OFFSET;
}
result = utf8::unchecked::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::unchecked::next(start);
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::unchecked::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::unchecked::next(start);
return result;
}
// The iterator class
template <typename octet_iterator>
class iterator : public std::iterator <std::bidirectional_iterator_tag, uint32_t> {
octet_iterator it;
public:
iterator () {}
explicit iterator (const octet_iterator& octet_it): it(octet_it) {}
// the default "big three" are OK
octet_iterator base () const { return it; }
uint32_t operator * () const
{
octet_iterator temp = it;
return utf8::unchecked::next(temp);
}
bool operator == (const iterator& rhs) const
{
return (it == rhs.it);
}
bool operator != (const iterator& rhs) const
{
return !(operator == (rhs));
}
iterator& operator ++ ()
{
::std::advance(it, utf8::internal::sequence_length(it));
return *this;
}
iterator operator ++ (int)
{
iterator temp = *this;
::std::advance(it, utf8::internal::sequence_length(it));
return temp;
}
iterator& operator -- ()
{
utf8::unchecked::prior(it);
return *this;
}
iterator operator -- (int)
{
iterator temp = *this;
utf8::unchecked::prior(it);
return temp;
}
}; // class iterator
} // namespace utf8::unchecked
} // namespace utf8
#endif // header guard

1789
src/utf8/utf8cpp.html Normal file
View file

File diff suppressed because it is too large Load diff