Initial html grammar

This commit is contained in:
orosmatthew 2023-09-29 00:30:43 -04:00
parent a341997a17
commit 10b754c984
31 changed files with 3797 additions and 64 deletions

View File

@ -17,9 +17,11 @@ add_subdirectory(external/raylib-4.5.0)
add_subdirectory(external/raylib-cpp-4.5.1) add_subdirectory(external/raylib-cpp-4.5.1)
add_subdirectory(external/utfcpp-3.2.5)
add_executable(browser src/main.cpp src/fetch.cpp add_executable(browser src/main.cpp src/fetch.cpp
src/html_parse.cpp) src/html_parse.cpp)
target_include_directories(browser PRIVATE external/raygui-4.0/src) target_include_directories(browser PRIVATE external/raygui-4.0/src)
target_link_libraries(browser libcurl raylib raylib_cpp) target_link_libraries(browser libcurl raylib raylib_cpp utf8cpp)

15
docs/html_grammar.txt Normal file
View File

@ -0,0 +1,15 @@
Defined Tokens
<str> => any text in quotes ex: "Hello World!"
<ident> => text not inside of quotes ex: h3
---
<doc> ::= [<doctype>] <elem>
<doctype> ::= "<" "!" "doctype" "html" ">"
<elem> ::=
| "<" <ident> <attr>* ">" (<elem> | <inner>)* "<" "/" <ident> ">"
| "<" <ident> <attr>* "/" ">"
<attr> ::= <ident> "=" <str>
<inner> ::= (<ident> | <dot> | <at> | <hash> | <num> | <comma> | <semi>)+

View File

@ -0,0 +1,13 @@
version: 2
jobs:
build:
docker:
- image: nemtrif/utf8cpp:3.1.3
steps:
- checkout
- run: git submodule update --init --recursive --remote
- run: mkdir build
- run: cd build && cmake ..
- run: cd build && cmake --build .
- run: cd build && ctest -VV

4
external/utfcpp-3.2.5/.gitignore vendored Normal file
View File

@ -0,0 +1,4 @@
# VS Code:
.vscode/
# Often used by CMake
build/

3
external/utfcpp-3.2.5/.gitmodules vendored Normal file
View File

@ -0,0 +1,3 @@
[submodule "extern/ftest"]
path = extern/ftest
url = https://github.com/nemtrif/ftest

67
external/utfcpp-3.2.5/CMakeLists.txt vendored Normal file
View File

@ -0,0 +1,67 @@
cmake_minimum_required (VERSION 3.0.2...3.27)
project (utf8cpp VERSION 3.2.5 LANGUAGES CXX)
if(CMAKE_SOURCE_DIR STREQUAL CMAKE_CURRENT_SOURCE_DIR)
set(IS_ROOT_PROJECT ON)
else()
set(IS_ROOT_PROJECT OFF)
endif()
option(UTF8_TESTS "Enable tests for UTF8-CPP" ${IS_ROOT_PROJECT})
option(UTF8_INSTALL "Enable installation for UTF8-CPP" ${IS_ROOT_PROJECT})
option(UTF8_SAMPLES "Enable building samples for UTF8-CPP" ${IS_ROOT_PROJECT})
add_library(utf8cpp INTERFACE)
target_include_directories(utf8cpp INTERFACE
"$<BUILD_INTERFACE:${CMAKE_CURRENT_SOURCE_DIR}/source>"
$<INSTALL_INTERFACE:include/utf8cpp>
)
add_library(utf8::cpp ALIAS utf8cpp)
if(UTF8_INSTALL)
include(CMakePackageConfigHelpers)
if(MSVC)
set(DEF_INSTALL_CMAKE_DIR CMake)
else()
include(GNUInstallDirs) # define CMAKE_INSTALL_*
set(DEF_INSTALL_CMAKE_DIR ${CMAKE_INSTALL_LIBDIR}/cmake/utf8cpp)
endif()
if(${CMAKE_VERSION} VERSION_GREATER "3.14")
set(OPTIONAL_ARCH_INDEPENDENT "ARCH_INDEPENDENT")
endif()
write_basic_package_version_file(
${CMAKE_CURRENT_BINARY_DIR}/utf8cppConfigVersion.cmake
VERSION ${PROJECT_VERSION}
COMPATIBILITY SameMajorVersion
${OPTIONAL_ARCH_INDEPENDENT}
)
configure_package_config_file(
${PROJECT_SOURCE_DIR}/utf8cppConfig.cmake.in
${CMAKE_CURRENT_BINARY_DIR}/utf8cppConfig.cmake
INSTALL_DESTINATION ${DEF_INSTALL_CMAKE_DIR}
)
install(DIRECTORY source/ DESTINATION include/utf8cpp)
install(TARGETS utf8cpp EXPORT utf8cppTargets)
install(EXPORT utf8cppTargets DESTINATION ${DEF_INSTALL_CMAKE_DIR})
install(
FILES
${CMAKE_CURRENT_BINARY_DIR}/utf8cppConfig.cmake
${CMAKE_CURRENT_BINARY_DIR}/utf8cppConfigVersion.cmake
DESTINATION
${DEF_INSTALL_CMAKE_DIR}
)
endif()
if(UTF8_SAMPLES)
add_executable(docsample ${PROJECT_SOURCE_DIR}/samples/docsample.cpp)
target_link_libraries(docsample PRIVATE utf8::cpp)
endif()
if(UTF8_TESTS)
enable_testing()
add_subdirectory(tests)
endif()

23
external/utfcpp-3.2.5/LICENSE vendored Normal file
View File

@ -0,0 +1,23 @@
Boost Software License - Version 1.0 - August 17th, 2003
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.

1507
external/utfcpp-3.2.5/README.md vendored Normal file

File diff suppressed because it is too large Load Diff

View File

@ -0,0 +1,64 @@
#include "../source/utf8.h"
#include <iostream>
#include <fstream>
#include <string>
#include <vector>
using namespace std;
int main(int argc, char** argv)
{
if (argc != 2) {
cout << "\nUsage: docsample filename\n";
return 0;
}
const char* test_file_path = argv[1];
// Open the test file (must be UTF-8 encoded)
ifstream fs8(test_file_path);
if (!fs8.is_open()) {
cout << "Could not open " << test_file_path << endl;
return 0;
}
unsigned line_count = 1;
string line;
// Play with all the lines in the file
while (getline(fs8, line)) {
// check for invalid utf-8 (for a simple yes/no check, there is also utf8::is_valid function)
#if __cplusplus >= 201103L // C++ 11 or later
auto end_it = utf8::find_invalid(line.begin(), line.end());
#else
string::iterator end_it = utf8::find_invalid(line.begin(), line.end());
#endif // C++ 11
if (end_it != line.end()) {
cout << "Invalid UTF-8 encoding detected at line " << line_count << "\n";
cout << "This part is fine: " << string(line.begin(), end_it) << "\n";
}
// Get the line length (at least for the valid part)
ptrdiff_t length = utf8::distance(line.begin(), end_it);
cout << "Length of line " << line_count << " is " << length << "\n";
// Convert it to utf-16
#if __cplusplus >= 201103L // C++ 11 or later
u16string utf16line = utf8::utf8to16(line);
#else
vector<unsigned short> utf16line;
utf8::utf8to16(line.begin(), end_it, back_inserter(utf16line));
#endif // C++ 11
// And back to utf-8;
#if __cplusplus >= 201103L // C++ 11 or later
string utf8line = utf8::utf16to8(utf16line);
#else
string utf8line;
utf8::utf16to8(utf16line.begin(), utf16line.end(), back_inserter(utf8line));
#endif // C++ 11
// Confirm that the conversion went OK:
if (utf8line != string(line.begin(), end_it))
cout << "Error in UTF-16 conversion at line: " << line_count << "\n";
line_count++;
}
return 0;
}

34
external/utfcpp-3.2.5/source/utf8.h vendored Normal file
View File

@ -0,0 +1,34 @@
// 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

@ -0,0 +1,319 @@
// Copyright 2006-2016 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 codepoint) : cp(codepoint) {}
virtual const char* what() const UTF_CPP_NOEXCEPT UTF_CPP_OVERRIDE { 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) {}
invalid_utf8 (char c) : u8(static_cast<uint8_t>(c)) {}
virtual const char* what() const UTF_CPP_NOEXCEPT UTF_CPP_OVERRIDE { 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 UTF_CPP_NOEXCEPT UTF_CPP_OVERRIDE { return "Invalid UTF-16"; }
uint16_t utf16_word() const {return u16;}
};
class not_enough_room : public exception {
public:
virtual const char* what() const UTF_CPP_NOEXCEPT UTF_CPP_OVERRIDE { 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);
return internal::append(cp, 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:
out = utf8::append (replacement, out);
start = end;
break;
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(static_cast<uint8_t>(*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);
}
template <typename octet_iterator, typename distance_type>
void advance (octet_iterator& it, distance_type n, octet_iterator end)
{
const distance_type zero(0);
if (n < zero) {
// backward
for (distance_type i = n; i < zero; ++i)
utf8::prior(it, end);
} else {
// forward
for (distance_type i = zero; 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 {
octet_iterator it;
octet_iterator range_start;
octet_iterator range_end;
public:
typedef uint32_t value_type;
typedef uint32_t* pointer;
typedef uint32_t& reference;
typedef std::ptrdiff_t difference_type;
typedef std::bidirectional_iterator_tag iterator_category;
iterator () {}
explicit iterator (const octet_iterator& octet_it,
const octet_iterator& rangestart,
const octet_iterator& rangeend) :
it(octet_it), range_start(rangestart), range_end(rangeend)
{
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
#if UTF_CPP_CPLUSPLUS >= 201703L // C++ 17 or later
#include "cpp17.h"
#elif UTF_CPP_CPLUSPLUS >= 201103L // C++ 11 or later
#include "cpp11.h"
#endif // C++ 11 or later
#endif //header guard

387
external/utfcpp-3.2.5/source/utf8/core.h vendored Normal file
View File

@ -0,0 +1,387 @@
// 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>
// Determine the C++ standard version.
// If the user defines UTF_CPP_CPLUSPLUS, use that.
// Otherwise, trust the unreliable predefined macro __cplusplus
#if !defined UTF_CPP_CPLUSPLUS
#define UTF_CPP_CPLUSPLUS __cplusplus
#endif
#if UTF_CPP_CPLUSPLUS >= 201103L // C++ 11 or later
#define UTF_CPP_OVERRIDE override
#define UTF_CPP_NOEXCEPT noexcept
#else // C++ 98/03
#define UTF_CPP_OVERRIDE
#define UTF_CPP_NOEXCEPT throw()
#endif // C++ 11 or later
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 = 0xd7c0u; // LEAD_SURROGATE_MIN - (0x10000 >> 10)
const uint32_t SURROGATE_OFFSET = 0xfca02400u; // 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)
{
if (it == end)
return NOT_ENOUGH_ROOM;
// 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);
}
// Internal implementation of both checked and unchecked append() function
// This function will be invoked by the overloads below, as they will know
// the octet_type.
template <typename octet_iterator, typename octet_type>
octet_iterator append(uint32_t cp, octet_iterator result) {
if (cp < 0x80) // one octet
*(result++) = static_cast<octet_type>(cp);
else if (cp < 0x800) { // two octets
*(result++) = static_cast<octet_type>((cp >> 6) | 0xc0);
*(result++) = static_cast<octet_type>((cp & 0x3f) | 0x80);
}
else if (cp < 0x10000) { // three octets
*(result++) = static_cast<octet_type>((cp >> 12) | 0xe0);
*(result++) = static_cast<octet_type>(((cp >> 6) & 0x3f) | 0x80);
*(result++) = static_cast<octet_type>((cp & 0x3f) | 0x80);
}
else { // four octets
*(result++) = static_cast<octet_type>((cp >> 18) | 0xf0);
*(result++) = static_cast<octet_type>(((cp >> 12) & 0x3f)| 0x80);
*(result++) = static_cast<octet_type>(((cp >> 6) & 0x3f) | 0x80);
*(result++) = static_cast<octet_type>((cp & 0x3f) | 0x80);
}
return result;
}
// One of the following overloads will be invoked from the API calls
// A simple (but dangerous) case: the caller appends byte(s) to a char array
inline char* append(uint32_t cp, char* result) {
return append<char*, char>(cp, result);
}
// Hopefully, most common case: the caller uses back_inserter
// i.e. append(cp, std::back_inserter(str));
template<typename container_type>
std::back_insert_iterator<container_type> append
(uint32_t cp, std::back_insert_iterator<container_type> result) {
return append<std::back_insert_iterator<container_type>,
typename container_type::value_type>(cp, result);
}
// The caller uses some other kind of output operator - not covered above
// Note that in this case we are not able to determine octet_type
// so we assume it's uint_8; that can cause a conversion warning if we are wrong.
template <typename octet_iterator>
octet_iterator append(uint32_t cp, octet_iterator result) {
return append<octet_iterator, uint8_t>(cp, result);
}
} // 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])
);
}
} // namespace utf8
#endif // header guard

View File

@ -0,0 +1,103 @@
// Copyright 2018 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_a184c22c_d012_11e8_a8d5_f2801f1b9fd1
#define UTF8_FOR_CPP_a184c22c_d012_11e8_a8d5_f2801f1b9fd1
#include "checked.h"
#include <string>
namespace utf8
{
inline void append(char32_t cp, std::string& s)
{
append(uint32_t(cp), std::back_inserter(s));
}
inline std::string utf16to8(const std::u16string& s)
{
std::string result;
utf16to8(s.begin(), s.end(), std::back_inserter(result));
return result;
}
inline std::u16string utf8to16(const std::string& s)
{
std::u16string result;
utf8to16(s.begin(), s.end(), std::back_inserter(result));
return result;
}
inline std::string utf32to8(const std::u32string& s)
{
std::string result;
utf32to8(s.begin(), s.end(), std::back_inserter(result));
return result;
}
inline std::u32string utf8to32(const std::string& s)
{
std::u32string result;
utf8to32(s.begin(), s.end(), std::back_inserter(result));
return result;
}
inline std::size_t find_invalid(const std::string& s)
{
std::string::const_iterator invalid = find_invalid(s.begin(), s.end());
return (invalid == s.end()) ? std::string::npos : static_cast<std::size_t>(invalid - s.begin());
}
inline bool is_valid(const std::string& s)
{
return is_valid(s.begin(), s.end());
}
inline std::string replace_invalid(const std::string& s, char32_t replacement)
{
std::string result;
replace_invalid(s.begin(), s.end(), std::back_inserter(result), replacement);
return result;
}
inline std::string replace_invalid(const std::string& s)
{
std::string result;
replace_invalid(s.begin(), s.end(), std::back_inserter(result));
return result;
}
inline bool starts_with_bom(const std::string& s)
{
return starts_with_bom(s.begin(), s.end());
}
} // namespace utf8
#endif // header guard

View File

@ -0,0 +1,103 @@
// Copyright 2018 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_7e906c01_03a3_4daf_b420_ea7ea952b3c9
#define UTF8_FOR_CPP_7e906c01_03a3_4daf_b420_ea7ea952b3c9
#include "checked.h"
#include <string>
namespace utf8
{
inline void append(char32_t cp, std::string& s)
{
append(uint32_t(cp), std::back_inserter(s));
}
inline std::string utf16to8(std::u16string_view s)
{
std::string result;
utf16to8(s.begin(), s.end(), std::back_inserter(result));
return result;
}
inline std::u16string utf8to16(std::string_view s)
{
std::u16string result;
utf8to16(s.begin(), s.end(), std::back_inserter(result));
return result;
}
inline std::string utf32to8(std::u32string_view s)
{
std::string result;
utf32to8(s.begin(), s.end(), std::back_inserter(result));
return result;
}
inline std::u32string utf8to32(std::string_view s)
{
std::u32string result;
utf8to32(s.begin(), s.end(), std::back_inserter(result));
return result;
}
inline std::size_t find_invalid(std::string_view s)
{
std::string_view::const_iterator invalid = find_invalid(s.begin(), s.end());
return (invalid == s.end()) ? std::string_view::npos : static_cast<std::size_t>(invalid - s.begin());
}
inline bool is_valid(std::string_view s)
{
return is_valid(s.begin(), s.end());
}
inline std::string replace_invalid(std::string_view s, char32_t replacement)
{
std::string result;
replace_invalid(s.begin(), s.end(), std::back_inserter(result), replacement);
return result;
}
inline std::string replace_invalid(std::string_view s)
{
std::string result;
replace_invalid(s.begin(), s.end(), std::back_inserter(result));
return result;
}
inline bool starts_with_bom(std::string_view s)
{
return starts_with_bom(s.begin(), s.end());
}
} // namespace utf8
#endif // header guard

View File

@ -0,0 +1,259 @@
// 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)
{
return internal::append(cp, 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:
out = utf8::unchecked::append (replacement, out);
start = end;
break;
case internal::INVALID_LEAD:
out = utf8::unchecked::append (replacement, out);
++start;
break;
case internal::INCOMPLETE_SEQUENCE:
case internal::OVERLONG_SEQUENCE:
case internal::INVALID_CODE_POINT:
out = utf8::unchecked::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::unchecked::replace_invalid(start, end, out, replacement_marker);
}
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);
}
template <typename octet_iterator, typename distance_type>
void advance (octet_iterator& it, distance_type n)
{
const distance_type zero(0);
if (n < zero) {
// backward
for (distance_type i = n; i < zero; ++i)
utf8::unchecked::prior(it);
} else {
// forward
for (distance_type i = zero; 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++);
if (start == end)
return result;
// 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 {
octet_iterator it;
public:
typedef uint32_t value_type;
typedef uint32_t* pointer;
typedef uint32_t& reference;
typedef std::ptrdiff_t difference_type;
typedef std::bidirectional_iterator_tag iterator_category;
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

View File

@ -0,0 +1,43 @@
add_executable(negative ${PROJECT_SOURCE_DIR}/tests/negative.cpp)
add_executable(cpp11 ${PROJECT_SOURCE_DIR}/tests/test_cpp11.cpp)
add_executable(cpp17 ${PROJECT_SOURCE_DIR}/tests/test_cpp17.cpp)
add_executable(apitests ${PROJECT_SOURCE_DIR}/tests/apitests.cpp)
add_executable(noexceptionstests ${PROJECT_SOURCE_DIR}/tests/noexceptionstests.cpp)
target_link_libraries(negative PRIVATE utf8::cpp)
target_link_libraries(cpp11 PRIVATE utf8::cpp)
target_link_libraries(cpp17 PRIVATE utf8::cpp)
target_link_libraries(apitests PRIVATE utf8::cpp)
target_link_libraries(noexceptionstests PRIVATE utf8::cpp)
target_compile_options(${PROJECT_NAME} INTERFACE
$<$<CXX_COMPILER_ID:MSVC>:/W4>
$<$<NOT:$<CXX_COMPILER_ID:MSVC>>:-Wall -Wextra -Wpedantic -Wconversion>)
target_compile_options(noexceptionstests PUBLIC -fno-exceptions)
set_target_properties(negative apitests noexceptionstests
PROPERTIES
CXX_STANDARD 98
CXX_STANDARD_REQUIRED YES
CXX_EXTENSIONS NO)
set_target_properties(cpp11
PROPERTIES
CXX_STANDARD 11
CXX_STANDARD_REQUIRED YES
CXX_EXTENSIONS NO)
set_target_properties(cpp17
PROPERTIES
CXX_STANDARD 17
CXX_STANDARD_REQUIRED YES
CXX_EXTENSIONS NO)
add_test(negative_test negative ${PROJECT_SOURCE_DIR}/tests/test_data/utf8_invalid.txt)
add_test(cpp11_test cpp11)
add_test(cpp17_test cpp17)
add_test(api_test apitests)
add_test(noexceptions_test noexceptionstests)

View File

@ -0,0 +1,6 @@
#include "../extern/ftest/ftest.h"
#include "test_checked_api.h"
#include "test_checked_iterator.h"
#include "test_unchecked_api.h"
#include "test_unchecked_iterator.h"

View File

@ -0,0 +1,5 @@
FROM debian:buster-slim
RUN apt-get update \
&& apt-get install -y make g++ cmake git \
&& rm -rf /var/lib/apt/lists/*

View File

@ -0,0 +1,59 @@
#include "utf8.h"
using namespace utf8;
#include <string>
#include <iostream>
#include <fstream>
#include <algorithm>
using namespace std;
const unsigned INVALID_LINES[] = { 75, 76, 83, 84, 85, 93, 102, 103, 105, 106, 107, 108, 109, 110, 114, 115, 116, 117, 124, 125, 130, 135, 140, 145, 153, 154, 155, 156, 157, 158, 159, 160, 161, 162, 169, 175, 176, 177, 207, 208, 209, 210, 211, 220, 221, 222, 223, 224, 232, 233, 234, 235, 236, 247, 248, 249, 250, 251, 252, 253, 257, 258, 259, 260, 261, 262, 263, 264};
const unsigned* INVALID_LINES_END = INVALID_LINES + sizeof(INVALID_LINES)/sizeof(unsigned);
int main(int argc, char** argv)
{
string test_file_path;
if (argc == 2)
test_file_path = argv[1];
else {
cout << "Wrong number of arguments" << endl;
return 1;
}
// Open the test file
ifstream fs8(test_file_path.c_str());
if (!fs8.is_open()) {
cout << "Could not open " << test_file_path << endl;
return 1;
}
// Read it line by line
unsigned int line_count = 0;
char byte;
while (!fs8.eof()) {
string line;
while ((byte = static_cast<char>(fs8.get())) != '\n' && !fs8.eof())
line.push_back(byte);
line_count++;
bool expected_valid = (find(INVALID_LINES, INVALID_LINES_END, line_count) == INVALID_LINES_END);
// Print out lines that contain unexpected invalid UTF-8
if (!is_valid(line.begin(), line.end())) {
if (expected_valid) {
cout << "Unexpected invalid utf-8 at line " << line_count << '\n';
return 1;
}
// try fixing it:
string fixed_line;
replace_invalid(line.begin(), line.end(), back_inserter(fixed_line));
if (!is_valid(fixed_line.begin(), fixed_line.end())) {
cout << "replace_invalid() resulted in an invalid utf-8 at line " << line_count << '\n';
return 1;
}
}
else if (!expected_valid) {
cout << "Invalid utf-8 NOT detected at line " << line_count << '\n';
return 1;
}
}
}

View File

@ -0,0 +1,4 @@
#include "../extern/ftest/ftest.h"
#include "test_unchecked_api.h"
#include "test_unchecked_iterator.h"

View File

@ -0,0 +1,198 @@
#ifndef UTF8_FOR_CPP_TEST_CHECKED_H_2675DCD0_9480_4c0c_B92A_CC14C027B731
#define UTF8_FOR_CPP_TEST_CHECKED_H_2675DCD0_9480_4c0c_B92A_CC14C027B731
#include "utf8.h"
#include <string>
#include <vector>
using namespace utf8;
using namespace std;
TEST(CheckedAPITests, test_append)
{
unsigned char u[5] = {0,0,0,0,0};
append(0x0448, u);
EXPECT_EQ (u[0], 0xd1);
EXPECT_EQ (u[1], 0x88);
EXPECT_EQ (u[2], 0);
EXPECT_EQ (u[3], 0);
EXPECT_EQ (u[4], 0);
append(0x65e5, u);
EXPECT_EQ (u[0], 0xe6);
EXPECT_EQ (u[1], 0x97);
EXPECT_EQ (u[2], 0xa5);
EXPECT_EQ (u[3], 0);
EXPECT_EQ (u[4], 0);
append(0x3044, u);
EXPECT_EQ (u[0], 0xe3);
EXPECT_EQ (u[1], 0x81);
EXPECT_EQ (u[2], 0x84);
EXPECT_EQ (u[3], 0);
EXPECT_EQ (u[4], 0);
append(0x10346, u);
EXPECT_EQ (u[0], 0xf0);
EXPECT_EQ (u[1], 0x90);
EXPECT_EQ (u[2], 0x8d);
EXPECT_EQ (u[3], 0x86);
EXPECT_EQ (u[4], 0);
// Ensure no warnings with plain char
char c[2] = {0,0};
append('a', c);
EXPECT_EQ (c[0], 'a');
EXPECT_EQ (c[1], 0);
}
TEST(CheckedAPITests, test_next)
{
const char* twochars = "\xe6\x97\xa5\xd1\x88";
const char* w = twochars;
unsigned int cp = next(w, twochars + 6);
EXPECT_EQ (cp, 0x65e5);
EXPECT_EQ (w, twochars + 3);
const char* threechars = "\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88";
w = threechars;
cp = next(w, threechars + 9);
EXPECT_EQ (cp, 0x10346);
EXPECT_EQ (w, threechars + 4);
cp = next(w, threechars + 9);
EXPECT_EQ (cp, 0x65e5);
EXPECT_EQ (w, threechars + 7);
cp = next(w, threechars + 9);
EXPECT_EQ (cp, 0x0448);
EXPECT_EQ (w, threechars + 9);
}
TEST(CheckedAPITests, test_peek_next)
{
const char* const cw = "\xe6\x97\xa5\xd1\x88";
unsigned int cp = peek_next(cw, cw + 6);
EXPECT_EQ (cp, 0x65e5);
}
TEST(CheckedAPITests, test_prior)
{
const char* twochars = "\xe6\x97\xa5\xd1\x88";
const char* w = twochars + 3;
unsigned int cp = prior (w, twochars);
EXPECT_EQ (cp, 0x65e5);
EXPECT_EQ (w, twochars);
const char* threechars = "\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88";
w = threechars + 9;
cp = prior(w, threechars);
EXPECT_EQ (cp, 0x0448);
EXPECT_EQ (w, threechars + 7);
cp = prior(w, threechars);
EXPECT_EQ (cp, 0x65e5);
EXPECT_EQ (w, threechars + 4);
cp = prior(w, threechars);
EXPECT_EQ (cp, 0x10346);
EXPECT_EQ (w, threechars);
}
TEST(CheckedAPITests, test_advance)
{
const char* threechars = "\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88";
const char* w = threechars;
advance(w, 2, threechars + 9);
EXPECT_EQ(w, threechars + 7);
advance(w, -2, threechars);
EXPECT_EQ(w, threechars);
advance(w, 3, threechars + 9);
EXPECT_EQ(w, threechars + 9);
advance(w, -2, threechars);
EXPECT_EQ(w, threechars + 4);
advance(w, -1, threechars);
EXPECT_EQ(w, threechars);
}
TEST(CheckedAPITests, test_distance)
{
const char* twochars = "\xe6\x97\xa5\xd1\x88";
size_t dist = static_cast<size_t>(utf8::distance(twochars, twochars + 5));
EXPECT_EQ (dist, 2);
}
TEST(CheckedAPITests, test_utf32to8)
{
unsigned int utf32string[] = {0x448, 0x65E5, 0x10346, 0};
string utf8result;
utf32to8(utf32string, utf32string + 3, back_inserter(utf8result));
EXPECT_EQ (utf8result.size(), 9);
}
TEST(CheckedAPITests, test_utf8to32)
{
const char* twochars = "\xe6\x97\xa5\xd1\x88";
vector<unsigned int> utf32result;
utf8to32(twochars, twochars + 5, back_inserter(utf32result));
EXPECT_EQ (utf32result.size(), 2);
}
TEST(CheckedAPITests, test_utf16to8)
{
unsigned short utf16string[] = {0x41, 0x0448, 0x65e5, 0xd834, 0xdd1e};
string utf8result;
utf16to8(utf16string, utf16string + 5, back_inserter(utf8result));
EXPECT_EQ (utf8result.size(), 10);
}
TEST(CheckedAPITests, test_utf8to16)
{
char utf8_with_surrogates[] = "\xe6\x97\xa5\xd1\x88\xf0\x9d\x84\x9e";
vector <unsigned short> utf16result;
utf8to16(utf8_with_surrogates, utf8_with_surrogates + 9, back_inserter(utf16result));
EXPECT_EQ (utf16result.size(), 4);
EXPECT_EQ (utf16result[2], 0xd834);
EXPECT_EQ (utf16result[3], 0xdd1e);
}
TEST(CheckedAPITests, test_replace_invalid)
{
char invalid_sequence[] = "a\x80\xe0\xa0\xc0\xaf\xed\xa0\x80z";
vector<char> replace_invalid_result;
replace_invalid (invalid_sequence, invalid_sequence + sizeof(invalid_sequence), std::back_inserter(replace_invalid_result), '?');
bool bvalid = is_valid(replace_invalid_result.begin(), replace_invalid_result.end());
EXPECT_TRUE (bvalid);
const char fixed_invalid_sequence[] = "a????z";
EXPECT_EQ (sizeof(fixed_invalid_sequence), replace_invalid_result.size());
EXPECT_TRUE (std::equal(replace_invalid_result.begin(), replace_invalid_result.begin() + sizeof(fixed_invalid_sequence), fixed_invalid_sequence));
}
TEST(CheckedAPITests, test_find_invalid)
{
char utf_invalid[] = "\xe6\x97\xa5\xd1\x88\xfa";
char* invalid = find_invalid(utf_invalid, utf_invalid + 6);
EXPECT_EQ (invalid, utf_invalid + 5);
}
TEST(CheckedAPITests, test_is_valid)
{
char utf_invalid[] = "\xe6\x97\xa5\xd1\x88\xfa";
bool bvalid = is_valid(utf_invalid, utf_invalid + 6);
EXPECT_FALSE (bvalid);
char utf8_with_surrogates[] = "\xe6\x97\xa5\xd1\x88\xf0\x9d\x84\x9e";
bvalid = is_valid(utf8_with_surrogates, utf8_with_surrogates + 9);
EXPECT_TRUE (bvalid);
}
TEST(CheckedAPITests, test_starts_with_bom)
{
unsigned char byte_order_mark[] = {0xef, 0xbb, 0xbf};
bool bbom = starts_with_bom(byte_order_mark, byte_order_mark + sizeof(byte_order_mark));
EXPECT_TRUE (bbom);
const char* threechars = "\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88";
bool no_bbom = starts_with_bom(threechars, threechars + sizeof(threechars));
EXPECT_FALSE (no_bbom);
}
#endif

View File

@ -0,0 +1,35 @@
#ifndef UTF8_FOR_CPP_TEST_CHECKED_ITERATOR_H_2675DCD0_9480_4c0c_B92A_CC14C027B731
#define UTF8_FOR_CPP_TEST_CHECKED_ITERATOR_H_2675DCD0_9480_4c0c_B92A_CC14C027B731
#include "utf8.h"
using namespace utf8;
TEST(CheckedIteratrTests, test_increment)
{
const char* threechars = "\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88";
utf8::iterator<const char*> it(threechars, threechars, threechars + 9);
utf8::iterator<const char*> it2 = it;
EXPECT_EQ (it2, it);
EXPECT_EQ (*it, 0x10346);
EXPECT_EQ (*(++it), 0x65e5);
EXPECT_EQ ((*it++), 0x65e5);
EXPECT_EQ (*it, 0x0448);
EXPECT_NE (it, it2);
utf8::iterator<const char*> endit (threechars + 9, threechars, threechars + 9);
EXPECT_EQ (++it, endit);
}
TEST(CheckedIteratrTests, test_decrement)
{
const char* threechars = "\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88";
utf8::iterator<const char*> it(threechars+9, threechars, threechars + 9);
EXPECT_EQ (*(--it), 0x0448);
EXPECT_EQ ((*it--), 0x0448);
EXPECT_EQ (*it, 0x65e5);
EXPECT_EQ (--it, utf8::iterator<const char*>(threechars, threechars, threechars + 9));
EXPECT_EQ (*it, 0x10346);
}
#endif

View File

@ -0,0 +1,109 @@
#include "../extern/ftest/ftest.h"
#include "utf8.h"
#include <string>
using namespace utf8;
using namespace std;
#if __cplusplus >= 201103L // C++ 11 or later
TEST(CPP11APITests, test_append)
{
string u;
append(0x0448, u);
EXPECT_EQ (u[0], char(0xd1));
EXPECT_EQ (u[1], char(0x88));
EXPECT_EQ (u.length(), 2);
u.clear();
append(0x65e5, u);
EXPECT_EQ (u[0], char(0xe6));
EXPECT_EQ (u[1], char(0x97));
EXPECT_EQ (u[2], char(0xa5));
EXPECT_EQ (u.length(), 3);
u.clear();
append(0x3044, u);
EXPECT_EQ (u[0], char(0xe3));
EXPECT_EQ (u[1], char(0x81));
EXPECT_EQ (u[2], char(0x84));
EXPECT_EQ (u.length(), 3);
u.clear();
append(0x10346, u);
EXPECT_EQ (u[0], char(0xf0));
EXPECT_EQ (u[1], char(0x90));
EXPECT_EQ (u[2], char(0x8d));
EXPECT_EQ (u[3], char(0x86));
EXPECT_EQ (u.length(), 4);
}
TEST(CPP11APITests, test_utf16to8)
{
u16string utf16string = {0x41, 0x0448, 0x65e5, 0xd834, 0xdd1e};
string u = utf16to8(utf16string);
EXPECT_EQ (u.size(), 10);
}
TEST(CPP11APITests, test_utf8to16)
{
string utf8_with_surrogates = "\xe6\x97\xa5\xd1\x88\xf0\x9d\x84\x9e";
u16string utf16result = utf8to16(utf8_with_surrogates);
EXPECT_EQ (utf16result.size(), 4);
EXPECT_EQ (utf16result[2], 0xd834);
EXPECT_EQ (utf16result[3], 0xdd1e);
// Just to make sure it compiles with string literals
utf8to16(u8"simple");
utf8to16("simple");
}
TEST(CPP11APITests, test_utf32to8)
{
u32string utf32string = {0x448, 0x65E5, 0x10346};
string utf8result = utf32to8(utf32string);
EXPECT_EQ (utf8result.size(), 9);
}
TEST(CPP11APITests, test_utf8to32)
{
const char* twochars = "\xe6\x97\xa5\xd1\x88";
u32string utf32result = utf8to32(twochars);
EXPECT_EQ (utf32result.size(), 2);
}
TEST(CPP11APITests, test_find_invalid)
{
string utf_invalid = "\xe6\x97\xa5\xd1\x88\xfa";
auto invalid = find_invalid(utf_invalid);
EXPECT_EQ (invalid, 5);
}
TEST(CPP11APITests, test_is_valid)
{
string utf_invalid = "\xe6\x97\xa5\xd1\x88\xfa";
bool bvalid = is_valid(utf_invalid);
EXPECT_FALSE (bvalid);
string utf8_with_surrogates = "\xe6\x97\xa5\xd1\x88\xf0\x9d\x84\x9e";
bvalid = is_valid(utf8_with_surrogates);
EXPECT_TRUE (bvalid);
}
TEST(CPP11APITests, test_replace_invalid)
{
string invalid_sequence = "a\x80\xe0\xa0\xc0\xaf\xed\xa0\x80z";
string replace_invalid_result = replace_invalid(invalid_sequence, '?');
bool bvalid = is_valid(replace_invalid_result);
EXPECT_TRUE (bvalid);
const string fixed_invalid_sequence = "a????z";
EXPECT_EQ(fixed_invalid_sequence, replace_invalid_result);
}
TEST(CPP11APITests, test_starts_with_bom)
{
string byte_order_mark = {char(0xef), char(0xbb), char(0xbf)};
bool bbom = starts_with_bom(byte_order_mark);
EXPECT_TRUE (bbom);
string threechars = "\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88";
bool no_bbom = starts_with_bom(threechars);
EXPECT_FALSE (no_bbom);
}
#endif // C++ 11 or later

View File

@ -0,0 +1,88 @@
#include "../extern/ftest/ftest.h"
#include "utf8.h"
#include <string>
using namespace utf8;
using namespace std;
#if __cplusplus >= 201703L // C++ 17 or later
TEST(CPP17APITests, test_utf16to8)
{
u16string utf16string = {0x41, 0x0448, 0x65e5, 0xd834, 0xdd1e};
u16string_view utf16stringview(u16string);
string u = utf16to8(utf16string);
EXPECT_EQ (u.size(), 10);
}
TEST(CPP17APITests, test_utf8to16)
{
string_view utf8_with_surrogates = "\xe6\x97\xa5\xd1\x88\xf0\x9d\x84\x9e";
u16string utf16result = utf8to16(utf8_with_surrogates);
EXPECT_EQ (utf16result.size(), 4);
EXPECT_EQ (utf16result[2], 0xd834);
EXPECT_EQ (utf16result[3], 0xdd1e);
}
TEST(CPP17APITests, test_utf32to8)
{
u32string utf32string = {0x448, 0x65E5, 0x10346};
u32string_view utf32stringview(utf32string);
string utf8result = utf32to8(utf32stringview);
EXPECT_EQ (utf8result.size(), 9);
}
TEST(CPP17APITests, test_utf8to32)
{
string_view twochars = "\xe6\x97\xa5\xd1\x88";
u32string utf32result = utf8to32(twochars);
EXPECT_EQ (utf32result.size(), 2);
}
TEST(CPP17APITests, test_find_invalid)
{
string_view utf_invalid = "\xe6\x97\xa5\xd1\x88\xfa";
auto invalid = find_invalid(utf_invalid);
EXPECT_EQ (invalid, 5);
}
TEST(CPP17APITests, test_is_valid)
{
string_view utf_invalid = "\xe6\x97\xa5\xd1\x88\xfa";
bool bvalid = is_valid(utf_invalid);
EXPECT_FALSE (bvalid);
string_view utf8_with_surrogates = "\xe6\x97\xa5\xd1\x88\xf0\x9d\x84\x9e";
bvalid = is_valid(utf8_with_surrogates);
EXPECT_TRUE (bvalid);
}
TEST(CPP17APITests, test_replace_invalid)
{
string_view invalid_sequence = "a\x80\xe0\xa0\xc0\xaf\xed\xa0\x80z";
string replace_invalid_result = replace_invalid(invalid_sequence, '?');
bool bvalid = is_valid(replace_invalid_result);
EXPECT_TRUE (bvalid);
const string fixed_invalid_sequence = "a????z";
EXPECT_EQ(fixed_invalid_sequence, replace_invalid_result);
}
TEST(CPP17APITests, test_starts_with_bom)
{
string byte_order_mark = {char(0xef), char(0xbb), char(0xbf)};
string_view byte_order_mark_view(byte_order_mark);
bool bbom = starts_with_bom(byte_order_mark_view);
EXPECT_TRUE (bbom);
string_view threechars = "\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88";
bool no_bbom = starts_with_bom(threechars);
EXPECT_FALSE (no_bbom);
}
TEST(CPP17APITests, string_class_and_literals)
{
const char* twochars = u8"ab";
EXPECT_TRUE (is_valid(twochars));
const string two_chars_string(twochars);
EXPECT_TRUE (is_valid(two_chars_string));
}
#endif // C++ 11 or later

Binary file not shown.

View File

@ -0,0 +1,169 @@
#ifndef UTF8_FOR_CPP_TEST_UNCHECKED_H_2675DCD0_9480_4c0c_B92A_CC14C027B731
#define UTF8_FOR_CPP_TEST_UNCHECKED_H_2675DCD0_9480_4c0c_B92A_CC14C027B731
#include "utf8/unchecked.h"
#include <string>
#include <vector>
using namespace std;
TEST(UnCheckedAPITests, test_append)
{
unsigned char u[5] = {0,0,0,0,0};
utf8::unchecked::append(0x0448, u);
EXPECT_EQ (u[0], 0xd1);
EXPECT_EQ (u[1], 0x88);
EXPECT_EQ (u[2], 0);
EXPECT_EQ (u[3], 0);
EXPECT_EQ (u[4], 0);
utf8::unchecked::append(0x65e5, u);
EXPECT_EQ (u[0], 0xe6);
EXPECT_EQ (u[1], 0x97);
EXPECT_EQ (u[2], 0xa5);
EXPECT_EQ (u[3], 0);
EXPECT_EQ (u[4], 0);
utf8::unchecked::append(0x3044, u);
EXPECT_EQ (u[0], 0xe3);
EXPECT_EQ (u[1], 0x81);
EXPECT_EQ (u[2], 0x84);
EXPECT_EQ (u[3], 0);
EXPECT_EQ (u[4], 0);
utf8::unchecked::append(0x10346, u);
EXPECT_EQ (u[0], 0xf0);
EXPECT_EQ (u[1], 0x90);
EXPECT_EQ (u[2], 0x8d);
EXPECT_EQ (u[3], 0x86);
EXPECT_EQ (u[4], 0);
}
TEST(UnCheckedAPITests, test_next)
{
const char* twochars = "\xe6\x97\xa5\xd1\x88";
const char* w = twochars;
unsigned int cp = utf8::unchecked::next(w);
EXPECT_EQ (cp, 0x65e5);
EXPECT_EQ (w, twochars + 3);
const char* threechars = "\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88";
w = threechars;
cp = utf8::unchecked::next(w);
EXPECT_EQ (cp, 0x10346);
EXPECT_EQ (w, threechars + 4);
cp = utf8::unchecked::next(w);
EXPECT_EQ (cp, 0x65e5);
EXPECT_EQ (w, threechars + 7);
cp = utf8::unchecked::next(w);
EXPECT_EQ (cp, 0x0448);
EXPECT_EQ (w, threechars + 9);
}
TEST(UnCheckedAPITests, test_peek_next)
{
const char* const cw = "\xe6\x97\xa5\xd1\x88";
unsigned int cp = utf8::unchecked::peek_next(cw);
EXPECT_EQ (cp, 0x65e5);
}
TEST(UnCheckedAPITests, test_prior)
{
const char* twochars = "\xe6\x97\xa5\xd1\x88";
const char* w = twochars + 3;
unsigned int cp = utf8::unchecked::prior (w);
EXPECT_EQ (cp, 0x65e5);
EXPECT_EQ (w, twochars);
const char* threechars = "\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88";
w = threechars + 9;
cp = utf8::unchecked::prior(w);
EXPECT_EQ (cp, 0x0448);
EXPECT_EQ (w, threechars + 7);
cp = utf8::unchecked::prior(w);
EXPECT_EQ (cp, 0x65e5);
EXPECT_EQ (w, threechars + 4);
cp = utf8::unchecked::prior(w);
EXPECT_EQ (cp, 0x10346);
EXPECT_EQ (w, threechars);
}
TEST(UnCheckedAPITests, test_advance)
{
const char* threechars = "\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88";
const char* w = threechars;
utf8::unchecked::advance(w, 2);
EXPECT_EQ(w, threechars + 7);
utf8::unchecked::advance(w, -2);
EXPECT_EQ(w, threechars);
utf8::unchecked::advance(w, 3);
EXPECT_EQ(w, threechars + 9);
utf8::unchecked::advance(w, -2);
EXPECT_EQ(w, threechars + 4);
utf8::unchecked::advance(w, -1);
EXPECT_EQ(w, threechars);
}
TEST(UnCheckedAPITests, test_distance)
{
const char* twochars = "\xe6\x97\xa5\xd1\x88";
size_t dist = static_cast<size_t>(utf8::unchecked::distance(twochars, twochars + 5));
EXPECT_EQ (dist, 2);
}
TEST(UnCheckedAPITests, test_utf32to8)
{
unsigned int utf32string[] = {0x448, 0x65E5, 0x10346, 0};
string utf8result;
utf8::unchecked::utf32to8(utf32string, utf32string + 3, back_inserter(utf8result));
EXPECT_EQ (utf8result.size(), 9);
}
TEST(UnCheckedAPITests, test_utf8to32)
{
const char* twochars = "\xe6\x97\xa5\xd1\x88";
vector<unsigned int> utf32result;
utf8::unchecked::utf8to32(twochars, twochars + 5, back_inserter(utf32result));
EXPECT_EQ (utf32result.size(), 2);
}
TEST(UnCheckedAPITests, test_utf16to8)
{
unsigned short utf16string[] = {0x41, 0x0448, 0x65e5, 0xd834, 0xdd1e};
string utf8result;
utf8::unchecked::utf16to8(utf16string, utf16string + 5, back_inserter(utf8result));
EXPECT_EQ (utf8result.size(), 10);
utf8result.clear();
unsigned short highsurrogateonly[] = {0xd800};
utf8::unchecked::utf16to8(highsurrogateonly, highsurrogateonly + 1, back_inserter(utf8result));
EXPECT_TRUE(true); // we didn't crash
}
TEST(UnCheckedAPITests, test_utf8to16)
{
char utf8_with_surrogates[] = "\xe6\x97\xa5\xd1\x88\xf0\x9d\x84\x9e";
vector <unsigned short> utf16result;
utf8::unchecked::utf8to16(utf8_with_surrogates, utf8_with_surrogates + 9, back_inserter(utf16result));
EXPECT_EQ (utf16result.size(), 4);
EXPECT_EQ (utf16result[2], 0xd834);
EXPECT_EQ (utf16result[3], 0xdd1e);
}
TEST(UnCheckedAPITests, test_replace_invalid)
{
char invalid_sequence[] = "a\x80\xe0\xa0\xc0\xaf\xed\xa0\x80z";
vector<char> replace_invalid_result;
utf8::unchecked::replace_invalid (invalid_sequence, invalid_sequence + sizeof(invalid_sequence), std::back_inserter(replace_invalid_result), '?');
bool bvalid = utf8::is_valid(replace_invalid_result.begin(), replace_invalid_result.end());
EXPECT_TRUE (bvalid);
const char fixed_invalid_sequence[] = "a????z";
EXPECT_EQ (sizeof(fixed_invalid_sequence), replace_invalid_result.size());
EXPECT_TRUE (std::equal(replace_invalid_result.begin(), replace_invalid_result.begin() + sizeof(fixed_invalid_sequence), fixed_invalid_sequence));
}
#endif

View File

@ -0,0 +1,36 @@
#ifndef UTF8_FOR_CPP_TEST_UNCHECKED_ITERATOR_H_2675DCD0_9480_4c0c_B92A_CC14C027B731
#define UTF8_FOR_CPP_TEST_UNCHECKED_ITERATOR_H_2675DCD0_9480_4c0c_B92A_CC14C027B731
#include "utf8/unchecked.h"
using namespace utf8::unchecked;
TEST(UnCheckedIteratrTests, test_increment)
{
const char* threechars = "\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88";
utf8::unchecked::iterator<const char*> it(threechars);
utf8::unchecked::iterator<const char*> it2 = it;
EXPECT_EQ (it2, it);
EXPECT_EQ (*it, 0x10346);
EXPECT_EQ (*(++it), 0x65e5);
EXPECT_EQ ((*it++), 0x65e5);
EXPECT_EQ (*it, 0x0448);
EXPECT_NE (it, it2);
utf8::unchecked::iterator<const char*> endit (threechars + 9);
EXPECT_EQ (++it, endit);
}
TEST(UnCheckedIteratrTests, test_decrement)
{
const char* threechars = "\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88";
utf8::unchecked::iterator<const char*> it(threechars+9);
EXPECT_EQ (*(--it), 0x0448);
EXPECT_EQ ((*it--), 0x0448);
EXPECT_EQ (*it, 0x65e5);
EXPECT_EQ (--it, utf8::unchecked::iterator<const char*>(threechars));
EXPECT_EQ (*it, 0x10346);
}
#endif

View File

@ -0,0 +1,8 @@
@PACKAGE_INIT@
include("${CMAKE_CURRENT_LIST_DIR}/utf8cppTargets.cmake")
check_required_components( "utf8cpp" )
if(NOT TARGET utf8::cpp)
add_library(utf8::cpp ALIAS utf8cpp)
endif()

View File

@ -1,13 +1,15 @@
#include "html_parse.hpp" #include "html_parse.hpp"
#include <cassert> #include <cassert>
#include <charconv>
#include <iostream> #include <iostream>
#include <utf8.h>
namespace html { namespace html {
Tokenizer::Tokenizer(std::u32string source) Tokenizer::Tokenizer(std::string source)
: m_source(std::move(source)) : m_source(std::move(source))
, m_index(0)
{ {
} }
@ -38,95 +40,148 @@ static bool is_newline(char32_t c)
std::vector<Token> Tokenizer::tokenize() std::vector<Token> Tokenizer::tokenize()
{ {
std::u32string buffer; std::string buffer;
std::vector<Token> tokens; std::vector<Token> tokens;
while (peek().has_value()) {
if (is_alpha(peek().value())) { utf8::iterator<std::string::iterator> it(m_source.begin(), m_source.begin(), m_source.end());
utf8::iterator<std::string::iterator> end(m_source.end(), m_source.begin(), m_source.end());
for (; it != end; ++it) {
if (is_alpha(*it)) {
do { do {
buffer.push_back(consume()); utf8::append(*it, std::back_inserter(buffer));
} while (peek().has_value() && is_alpha_num(peek().value())); } while (++it != end && is_alpha_num(*it));
--it;
tokens.push_back({ .type = TokenType::ident, .value = buffer }); tokens.push_back({ .type = TokenType::ident, .value = buffer });
buffer.clear(); buffer.clear();
} }
else if (peek().value() == '<') { else if (*it == '<') {
consume();
tokens.push_back({ .type = TokenType::lt }); tokens.push_back({ .type = TokenType::lt });
} }
else if (peek().value() == '>') { else if (*it == '>') {
consume();
tokens.push_back({ .type = TokenType::gt }); tokens.push_back({ .type = TokenType::gt });
} }
else if (peek().value() == '!') { else if (*it == '!') {
consume();
tokens.push_back({ .type = TokenType::exclaim }); tokens.push_back({ .type = TokenType::exclaim });
} }
else if (peek().value() == '/') { else if (*it == '/') {
consume();
tokens.push_back({ .type = TokenType::fslash }); tokens.push_back({ .type = TokenType::fslash });
} }
else if (peek().value() == '=') { else if (*it == '=') {
consume();
tokens.push_back({ .type = TokenType::eq }); tokens.push_back({ .type = TokenType::eq });
} }
else if (peek().value() == '"') { else if (*it == '-') {
tokens.push_back({ .type = TokenType::minus });
}
else if (*it == '{') {
tokens.push_back({ .type = TokenType::left_curly });
}
else if (*it == ':') {
tokens.push_back({ .type = TokenType::colon });
}
else if (*it == '#') {
tokens.push_back({ .type = TokenType::hash });
}
else if (*it == ';') {
tokens.push_back({ .type = TokenType::semi });
}
else if (is_num(*it)) {
do { do {
buffer.push_back(consume()); utf8::append(*it, std::back_inserter(buffer));
} while (peek().has_value() && peek().value() != '"'); } while (++it != end && is_num(*it));
--it;
tokens.push_back({ .type = TokenType::num, .value = buffer });
buffer.clear();
}
else if (*it == ',') {
tokens.push_back({ .type = TokenType::comma });
}
else if (*it == '{') {
tokens.push_back({ .type = TokenType::left_curly });
}
else if (*it == '}') {
tokens.push_back({ .type = TokenType::right_curly });
}
else if (*it == '(') {
tokens.push_back({ .type = TokenType::left_paren });
}
else if (*it == ')') {
tokens.push_back({ .type = TokenType::right_paren });
}
else if (*it == '.') {
tokens.push_back({ .type = TokenType::dot });
}
else if (*it == '@') {
tokens.push_back({ .type = TokenType::at });
}
else if (*it == '"') {
++it;
while (it != end && *it != '"') {
utf8::append(*it, std::back_inserter(buffer));
++it;
}
tokens.push_back({ .type = TokenType::str, .value = buffer }); tokens.push_back({ .type = TokenType::str, .value = buffer });
buffer.clear(); buffer.clear();
} }
else if (is_space(peek().value()) || is_newline(peek().value())) { else if (is_space(*it) || is_newline(*it)) {
consume();
} }
else { else {
std::cout << "[WARN] Unexpected token: " << std::to_string(peek().value()) << std::endl; utf8::append(*it, std::back_inserter(buffer));
consume(); std::cout << "[WARN] Unexpected token: " << buffer << std::endl;
buffer.clear();
} }
} }
return tokens; return tokens;
} }
std::optional<char32_t> Tokenizer::peek(size_t ahead)
{
if (m_index + ahead >= m_source.size()) {
return {};
}
return m_source.at(m_index + ahead);
}
char32_t Tokenizer::consume() std::string Token::to_string()
{ {
return m_source.at(m_index++);
}
std::u32string Token::to_string()
{
std::u32string buffer;
switch (type) { switch (type) {
case TokenType::lt: case TokenType::lt:
buffer.push_back('<'); return "<";
return buffer;
case TokenType::gt: case TokenType::gt:
buffer.push_back('>'); return ">";
return buffer;
case TokenType::ident: case TokenType::ident:
assert(value.has_value()); assert(value.has_value());
return value.value(); return value.value();
case TokenType::fslash: case TokenType::fslash:
buffer.push_back('/'); return "/";
return buffer;
case TokenType::str: case TokenType::str:
assert(value.has_value()); assert(value.has_value());
return value.value(); return value.value();
case TokenType::exclaim: case TokenType::exclaim:
buffer.push_back('!'); return "!";
return buffer;
case TokenType::eq: case TokenType::eq:
buffer.push_back('='); return "=";
return buffer; case TokenType::minus:
return "-";
case TokenType::left_curly:
return "{";
case TokenType::right_curly:
return "}";
case TokenType::left_paren:
return "(";
case TokenType::right_paren:
return ")";
case TokenType::colon:
return ":";
case TokenType::dot:
return ".";
case TokenType::comma:
return ",";
case TokenType::at:
return "@";
case TokenType::hash:
return "#";
case TokenType::semi:
return ";";
case TokenType::num:
assert(value.has_value());
return value.value();
default: default:
assert(false && "Unimplemented"); assert(false && "Unimplemented");
return buffer; return "";
} }
} }

View File

@ -4,15 +4,37 @@
#include <string> #include <string>
#include <vector> #include <vector>
#include <utf8.h>
namespace html { namespace html {
enum class TokenType { lt, gt, ident, fslash, str, exclaim, eq }; enum class TokenType {
lt,
gt,
ident,
fslash,
str,
exclaim,
eq,
minus,
left_curly,
right_curly,
colon,
hash,
semi,
num,
comma,
left_paren,
right_paren,
at,
dot,
};
struct Token { struct Token {
TokenType type; TokenType type;
std::optional<std::u32string> value = {}; std::optional<std::string> value = {};
std::u32string to_string(); std::string to_string();
}; };
enum class NodeType { enum class NodeType {
@ -23,17 +45,12 @@ struct Node { };
class Tokenizer { class Tokenizer {
public: public:
explicit Tokenizer(std::u32string source); explicit Tokenizer(std::string source);
std::vector<Token> tokenize(); std::vector<Token> tokenize();
private: private:
std::optional<char32_t> peek(size_t ahead = 1); std::string m_source;
char32_t consume();
std::u32string m_source;
size_t m_index;
}; };
} }

View File

@ -32,12 +32,10 @@ int main()
float scroll_pos = 0.0f; float scroll_pos = 0.0f;
if (page_data.has_value()) { if (page_data.has_value()) {
std::u32string page_data_unicode(page_data.value().begin(), page_data.value().end()); html::Tokenizer tokenizer(page_data.value());
html::Tokenizer tokenizer(page_data_unicode);
std::vector<html::Token> tokens = tokenizer.tokenize(); std::vector<html::Token> tokens = tokenizer.tokenize();
std::wstring_convert<std::codecvt_utf8<char32_t>, char32_t> converter;
for (html::Token token : tokens) { for (html::Token token : tokens) {
std::cout << converter.to_bytes(token.to_string()) << std::endl; std::cout << token.to_string() << std::endl;
} }
} }