Skip to content

L
libcifpp
Commit a855f880 by Maarten L. Hekkelman
Options

Getting rid of boost/algorithm/string

parent cfa2acd6
Showing with 949 additions and 630 deletions
CMakeLists.txt
...@@ -57,6 +57,7 @@ set(CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS ON) ...@@ -57,6 +57,7 @@ set(CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS ON)
# Optionally build a version to be installed inside CCP4 # Optionally build a version to be installed inside CCP4
option(BUILD_FOR_CCP4 "Build a version to be installed in CCP4" OFF) option(BUILD_FOR_CCP4 "Build a version to be installed in CCP4" OFF)
if(BUILD_FOR_CCP4) if(BUILD_FOR_CCP4)
if("$ENV{CCP4}" STREQUAL "" OR NOT EXISTS $ENV{CCP4}) if("$ENV{CCP4}" STREQUAL "" OR NOT EXISTS $ENV{CCP4})
message(FATAL_ERROR "A CCP4 built was requested but CCP4 was not sourced") message(FATAL_ERROR "A CCP4 built was requested but CCP4 was not sourced")
...@@ -79,6 +80,7 @@ if(EXISTS "$ENV{CCP4}") ...@@ -79,6 +80,7 @@ if(EXISTS "$ENV{CCP4}")
set(CCP4 $ENV{CCP4}) set(CCP4 $ENV{CCP4})
set(CLIBD ${CCP4}/lib/data) set(CLIBD ${CCP4}/lib/data)
endif() endif()
if(CCP4 AND NOT CLIBD) if(CCP4 AND NOT CLIBD)
set(CLIBD ${CCP4}/lib/data) set(CLIBD ${CCP4}/lib/data)
endif() endif()
...@@ -97,13 +99,12 @@ else() ...@@ -97,13 +99,12 @@ else()
endif() endif()
# set(CMAKE_DEBUG_POSTFIX d) # set(CMAKE_DEBUG_POSTFIX d)
if(MSVC) if(MSVC)
# make msvc standards compliant... # make msvc standards compliant...
add_compile_options(/permissive-) add_compile_options(/permissive-)
macro(get_WIN32_WINNT version) macro(get_WIN32_WINNT version)
if (WIN32 AND CMAKE_SYSTEM_VERSION) if(WIN32 AND CMAKE_SYSTEM_VERSION)
set(ver ${CMAKE_SYSTEM_VERSION}) set(ver ${CMAKE_SYSTEM_VERSION})
string(REPLACE "." "" ver ${ver}) string(REPLACE "." "" ver ${ver})
string(REGEX REPLACE "([0-9])" "0\\1" ver ${ver}) string(REGEX REPLACE "([0-9])" "0\\1" ver ${ver})
...@@ -129,7 +130,6 @@ if(UNIX AND NOT APPLE AND NOT BUILD_FOR_CCP4 AND CMAKE_INSTALL_PREFIX_INITIALIZE ...@@ -129,7 +130,6 @@ if(UNIX AND NOT APPLE AND NOT BUILD_FOR_CCP4 AND CMAKE_INSTALL_PREFIX_INITIALIZE
endif() endif()
# Optionally use mrc to create resources # Optionally use mrc to create resources
if(WIN32 AND BUILD_SHARED_LIBS) if(WIN32 AND BUILD_SHARED_LIBS)
message("Not using resources when building shared libraries for Windows") message("Not using resources when building shared libraries for Windows")
else() else()
...@@ -150,17 +150,12 @@ else() ...@@ -150,17 +150,12 @@ else()
endif() endif()
# Libraries # Libraries
set(CMAKE_THREAD_PREFER_PTHREAD) set(CMAKE_THREAD_PREFER_PTHREAD)
set(THREADS_PREFER_PTHREAD_FLAG) set(THREADS_PREFER_PTHREAD_FLAG)
find_package(Threads) find_package(Threads)
find_package(Boost 1.70.0 REQUIRED COMPONENTS system iostreams regex program_options) find_package(Boost 1.70.0 REQUIRED COMPONENTS system regex program_options)
find_package(gzstream REQUIRED)
if(NOT MSVC AND Boost_USE_STATIC_LIBS)
find_package(ZLIB REQUIRED)
list(APPEND CIFPP_REQUIRED_LIBRARIES ZLIB::ZLIB)
endif()
include(FindFilesystem) include(FindFilesystem)
list(APPEND CIFPP_REQUIRED_LIBRARIES ${STDCPPFS_LIBRARY}) list(APPEND CIFPP_REQUIRED_LIBRARIES ${STDCPPFS_LIBRARY})
...@@ -175,10 +170,10 @@ write_version_header("LibCIFPP") ...@@ -175,10 +170,10 @@ write_version_header("LibCIFPP")
# SymOp data table # SymOp data table
if(CIFPP_RECREATE_SYMOP_DATA) if(CIFPP_RECREATE_SYMOP_DATA)
# The tool to create the table # The tool to create the table
add_executable(symop-map-generator "${CMAKE_SOURCE_DIR}/tools/symop-map-generator.cpp") add_executable(symop-map-generator "${CMAKE_SOURCE_DIR}/tools/symop-map-generator.cpp")
target_link_libraries(symop-map-generator Threads::Threads ${Boost_LIBRARIES} ${CIFPP_REQUIRED_LIBRARIES}) target_link_libraries(symop-map-generator Threads::Threads ${Boost_LIBRARIES} ${CIFPP_REQUIRED_LIBRARIES})
if(Boost_INCLUDE_DIR) if(Boost_INCLUDE_DIR)
target_include_directories(symop-map-generator PUBLIC ${Boost_INCLUDE_DIR}) target_include_directories(symop-map-generator PUBLIC ${Boost_INCLUDE_DIR})
endif() endif()
...@@ -197,7 +192,6 @@ if(CIFPP_RECREATE_SYMOP_DATA) ...@@ -197,7 +192,6 @@ if(CIFPP_RECREATE_SYMOP_DATA)
endif() endif()
# Sources # Sources
set(project_sources set(project_sources
${PROJECT_SOURCE_DIR}/src/AtomType.cpp ${PROJECT_SOURCE_DIR}/src/AtomType.cpp
${PROJECT_SOURCE_DIR}/src/BondMap.cpp ${PROJECT_SOURCE_DIR}/src/BondMap.cpp
...@@ -249,7 +243,7 @@ target_include_directories(cifpp ...@@ -249,7 +243,7 @@ target_include_directories(cifpp
PUBLIC PUBLIC
"$<BUILD_INTERFACE:${PROJECT_SOURCE_DIR}/include>" "$<BUILD_INTERFACE:${PROJECT_SOURCE_DIR}/include>"
"$<INSTALL_INTERFACE:${CMAKE_INSTALL_INCLUDEDIR}>" "$<INSTALL_INTERFACE:${CMAKE_INSTALL_INCLUDEDIR}>"
${Boost_INCLUDE_DIR} ${Boost_INCLUDE_DIR} ${gzstream_INCLUDE_DIR}
) )
target_include_directories(cifpp target_include_directories(cifpp
...@@ -257,21 +251,21 @@ target_include_directories(cifpp ...@@ -257,21 +251,21 @@ target_include_directories(cifpp
${CMAKE_BINARY_DIR} ${CMAKE_BINARY_DIR}
) )
target_link_libraries(cifpp PUBLIC Threads::Threads Boost::regex Boost::iostreams ${CIFPP_REQUIRED_LIBRARIES}) target_link_libraries(cifpp PUBLIC Threads::Threads Boost::regex gzstream::gzstream ${CIFPP_REQUIRED_LIBRARIES})
# target_link_libraries(cifpp PRIVATE)
if (CMAKE_CXX_COMPILER_ID STREQUAL "AppleClang") # target_link_libraries(cifpp PRIVATE)
if(CMAKE_CXX_COMPILER_ID STREQUAL "AppleClang")
target_link_options(cifpp PRIVATE -undefined dynamic_lookup) target_link_options(cifpp PRIVATE -undefined dynamic_lookup)
endif (CMAKE_CXX_COMPILER_ID STREQUAL "AppleClang") endif(CMAKE_CXX_COMPILER_ID STREQUAL "AppleClang")
option(CIFPP_DOWNLOAD_CCD "Download the CCD file components.cif during installation" OFF) option(CIFPP_DOWNLOAD_CCD "Download the CCD file components.cif during installation" OFF)
if(CIFPP_DOWNLOAD_CCD) if(CIFPP_DOWNLOAD_CCD)
# download the components.cif file from CCD # download the components.cif file from CCD
set(COMPONENTS_CIF ${PROJECT_SOURCE_DIR}/data/components.cif) set(COMPONENTS_CIF ${PROJECT_SOURCE_DIR}/data/components.cif)
if (NOT EXISTS ${COMPONENTS_CIF}) if(NOT EXISTS ${COMPONENTS_CIF})
if(NOT EXISTS ${PROJECT_SOURCE_DIR}/data)
if (NOT EXISTS ${PROJECT_SOURCE_DIR}/data)
file(MAKE_DIRECTORY ${PROJECT_SOURCE_DIR}/data/) file(MAKE_DIRECTORY ${PROJECT_SOURCE_DIR}/data/)
endif() endif()
...@@ -301,8 +295,8 @@ endif() ...@@ -301,8 +295,8 @@ endif()
generate_export_header(cifpp generate_export_header(cifpp
EXPORT_FILE_NAME cif++/Cif++Export.hpp) EXPORT_FILE_NAME cif++/Cif++Export.hpp)
set(INCLUDE_INSTALL_DIR ${CMAKE_INSTALL_INCLUDEDIR} ) set(INCLUDE_INSTALL_DIR ${CMAKE_INSTALL_INCLUDEDIR})
set(LIBRARY_INSTALL_DIR ${CMAKE_INSTALL_LIBDIR} ) set(LIBRARY_INSTALL_DIR ${CMAKE_INSTALL_LIBDIR})
set(SHARE_INSTALL_DIR ${CMAKE_INSTALL_DATADIR}/libcifpp) set(SHARE_INSTALL_DIR ${CMAKE_INSTALL_DATADIR}/libcifpp)
set(CIFPP_DATA_DIR "${CMAKE_INSTALL_PREFIX}/${SHARE_INSTALL_DIR}" CACHE STRING "The directory containing the provided data files") set(CIFPP_DATA_DIR "${CMAKE_INSTALL_PREFIX}/${SHARE_INSTALL_DIR}" CACHE STRING "The directory containing the provided data files")
...@@ -310,7 +304,6 @@ set(CIFPP_DATA_DIR "${CMAKE_INSTALL_PREFIX}/${SHARE_INSTALL_DIR}" CACHE STRING " ...@@ -310,7 +304,6 @@ set(CIFPP_DATA_DIR "${CMAKE_INSTALL_PREFIX}/${SHARE_INSTALL_DIR}" CACHE STRING "
target_compile_definitions(cifpp PUBLIC DATA_DIR="${CIFPP_DATA_DIR}") target_compile_definitions(cifpp PUBLIC DATA_DIR="${CIFPP_DATA_DIR}")
# Install rules # Install rules
install(TARGETS cifpp install(TARGETS cifpp
EXPORT cifppTargets EXPORT cifppTargets
ARCHIVE DESTINATION ${CMAKE_INSTALL_LIBDIR} ARCHIVE DESTINATION ${CMAKE_INSTALL_LIBDIR}
...@@ -380,7 +373,6 @@ write_basic_package_version_file( ...@@ -380,7 +373,6 @@ write_basic_package_version_file(
) )
# pkgconfig support # pkgconfig support
set(prefix ${CMAKE_INSTALL_PREFIX}) set(prefix ${CMAKE_INSTALL_PREFIX})
set(exec_prefix ${CMAKE_INSTALL_PREFIX}) set(exec_prefix ${CMAKE_INSTALL_PREFIX})
set(libdir ${CMAKE_INSTALL_PREFIX}/${CMAKE_INSTALL_LIBDIR}) set(libdir ${CMAKE_INSTALL_PREFIX}/${CMAKE_INSTALL_LIBDIR})
...@@ -393,12 +385,11 @@ file(GENERATE OUTPUT ${CMAKE_CURRENT_BINARY_DIR}/libcifpp.pc ...@@ -393,12 +385,11 @@ file(GENERATE OUTPUT ${CMAKE_CURRENT_BINARY_DIR}/libcifpp.pc
install(FILES ${CMAKE_CURRENT_BINARY_DIR}/libcifpp.pc DESTINATION ${CMAKE_INSTALL_LIBDIR}/pkgconfig) install(FILES ${CMAKE_CURRENT_BINARY_DIR}/libcifpp.pc DESTINATION ${CMAKE_INSTALL_LIBDIR}/pkgconfig)
# Unit tests # Unit tests
option(CIFPP_BUILD_TESTS "Build test exectuables" OFF) option(CIFPP_BUILD_TESTS "Build test exectuables" OFF)
if(CIFPP_BUILD_TESTS) if(CIFPP_BUILD_TESTS)
list(APPEND CIFPP_tests list(APPEND CIFPP_tests
# pdb2cif # pdb2cif
rename-compound rename-compound
structure structure
...@@ -417,7 +408,7 @@ if(CIFPP_BUILD_TESTS) ...@@ -417,7 +408,7 @@ if(CIFPP_BUILD_TESTS)
${CMAKE_CURRENT_BINARY_DIR} # for config.h ${CMAKE_CURRENT_BINARY_DIR} # for config.h
) )
target_link_libraries(${CIFPP_TEST} PRIVATE Threads::Threads cifpp ) target_link_libraries(${CIFPP_TEST} PRIVATE Threads::Threads cifpp)
if(CIFPP_USE_RSRC) if(CIFPP_USE_RSRC)
mrc_target_resources(${CIFPP_TEST} ${CMAKE_SOURCE_DIR}/rsrc/mmcif_pdbx_v50.dic) mrc_target_resources(${CIFPP_TEST} ${CMAKE_SOURCE_DIR}/rsrc/mmcif_pdbx_v50.dic)
...@@ -436,14 +427,12 @@ if(CIFPP_BUILD_TESTS) ...@@ -436,14 +427,12 @@ if(CIFPP_BUILD_TESTS)
add_test(NAME ${CIFPP_TEST} add_test(NAME ${CIFPP_TEST}
COMMAND $<TARGET_FILE:${CIFPP_TEST}> -- ${CMAKE_SOURCE_DIR}/test) COMMAND $<TARGET_FILE:${CIFPP_TEST}> -- ${CMAKE_SOURCE_DIR}/test)
endforeach() endforeach()
endif() endif()
message("Will install in ${CMAKE_INSTALL_PREFIX}") message("Will install in ${CMAKE_INSTALL_PREFIX}")
# Optionally install the update scripts for CCD and dictionary files # Optionally install the update scripts for CCD and dictionary files
if(CIFPP_INSTALL_UPDATE_SCRIPT) if(CIFPP_INSTALL_UPDATE_SCRIPT)
set(CIFPP_CRON_DIR "$ENV{DESTDIR}/etc/cron.weekly") set(CIFPP_CRON_DIR "$ENV{DESTDIR}/etc/cron.weekly")
...@@ -468,4 +457,3 @@ if(CIFPP_INSTALL_UPDATE_SCRIPT) ...@@ -468,4 +457,3 @@ if(CIFPP_INSTALL_UPDATE_SCRIPT)
target_compile_definitions(cifpp PUBLIC CACHE_DIR="${CIFPP_CACHE_DIR}") target_compile_definitions(cifpp PUBLIC CACHE_DIR="${CIFPP_CACHE_DIR}")
endif() endif()
Config.cmake.in
...@@ -2,10 +2,8 @@ ...@@ -2,10 +2,8 @@
include(CMakeFindDependencyMacro) include(CMakeFindDependencyMacro)
find_dependency(Threads) find_dependency(Threads)
find_dependency(Boost 1.70.0 REQUIRED COMPONENTS system iostreams regex) find_dependency(Boost 1.70.0 REQUIRED COMPONENTS system regex)
if(NOT WIN32) find_dependency(gzstream)
find_dependency(ZLIB)
endif()
INCLUDE("${CMAKE_CURRENT_LIST_DIR}/cifppTargets.cmake") INCLUDE("${CMAKE_CURRENT_LIST_DIR}/cifppTargets.cmake")
......
include/cif++/CifUtils.hpp
...@@ -72,7 +72,124 @@ bool iequals(const char *a, const char *b); ...@@ -72,7 +72,124 @@ bool iequals(const char *a, const char *b);
int icompare(const char *a, const char *b); int icompare(const char *a, const char *b);
void toLower(std::string &s); void toLower(std::string &s);
std::string toLowerCopy(const std::string &s); std::string toLowerCopy(std::string_view s);
void toUpper(std::string &s);
// std::string toUpperCopy(const std::string &s);
template <typename IterType>
std::string join(IterType b, IterType e, std::string_view sep)
{
std::ostringstream s;
if (b != e)
{
auto ai = b;
auto ni = std::next(ai);
for (;;)
{
s << *ai;
ai = ni;
ni = std::next(ai);
if (ni == e)
break;
s << sep;
}
}
return s.str();
}
template <typename V>
std::string join(const V &arr, std::string_view sep)
{
return join(arr.begin(), arr.end(), sep);
}
template<typename StringType = std::string_view>
std::vector<StringType> split(std::string_view s, std::string_view separators, bool suppress_empty = false)
{
std::vector<StringType> result;
auto b = s.begin();
auto e = b;
while (e != s.end())
{
if (separators.find(*e) != std::string_view::npos)
{
if (e > b or not suppress_empty)
result.emplace_back(b, e - b);
b = e = e + 1;
continue;
}
++e;
}
if (e > b or not suppress_empty)
result.emplace_back(b, e - b);
return result;
}
void replace_all(std::string &s, std::string_view what, std::string_view with = {});
#if defined(__cpp_lib_starts_ends_with)
inline bool starts_with(std::string s, std::string_view with)
{
return s.starts_with(with);
}
inline bool ends_with(std::string_view s, std::string_view with)
{
return s.ends_with(with);
}
#else
inline bool starts_with(std::string s, std::string_view with)
{
return s.compare(0, with.length(), with) == 0;
}
inline bool ends_with(std::string_view s, std::string_view with)
{
return s.length() >= with.length() and s.compare(s.length() - with.length(), with.length(), with) == 0;
}
#endif
#if defined(__cpp_lib_string_contains)
inline bool contains(std::string_view s, std::string_view q)
{
return s.contains(q);
}
#else
inline bool contains(std::string_view s, std::string_view q)
{
return s.find(q) != std::string_view::npos;
}
#endif
bool icontains(std::string_view s, std::string_view q);
void trim_left(std::string &s);
void trim_right(std::string &s);
void trim(std::string &s);
std::string trim_left_copy(std::string_view s);
std::string trim_right_copy(std::string_view s);
std::string trim_copy(std::string_view s);
// To make life easier, we also define iless and iset using iequals // To make life easier, we also define iless and iset using iequals
......
include/cif++/Secondary.hpp
...@@ -28,6 +28,8 @@ ...@@ -28,6 +28,8 @@
#pragma once #pragma once
#include <vector>
namespace mmcif namespace mmcif
{ {
......
include/cif++/Structure.hpp
...@@ -599,8 +599,6 @@ class File : public cif::File ...@@ -599,8 +599,6 @@ class File : public cif::File
void load(const std::filesystem::path &p) override; void load(const std::filesystem::path &p) override;
void save(const std::filesystem::path &p) override; void save(const std::filesystem::path &p) override;
void load(std::istream &is) override;
using cif::File::load; using cif::File::load;
using cif::File::save; using cif::File::save;
......
include/cif++/v2/category.hpp
...@@ -394,6 +394,34 @@ class category ...@@ -394,6 +394,34 @@ class category
} }
// -------------------------------------------------------------------- // --------------------------------------------------------------------
/// \brief generate a new, unique ID. Pass it an ID generating function
/// based on a sequence number. This function will be called until the
/// result is unique in the context of this category
std::string get_unique_id(std::function<std::string(int)> generator = cif::cifIdForNumber);
std::string get_unique_id(const std::string &prefix)
{
return get_unique_id([prefix](int nr)
{ return prefix + std::to_string(nr + 1); });
}
// --------------------------------------------------------------------
/// \brief Rename a single column in the rows that match \a cond to value \a value
/// making sure the linked categories are updated according to the link.
/// That means, child categories are updated if the links are absolute
/// and unique. If they are not, the child category rows are split.
void update_value(condition &&cond, std::string_view tag, std::string_view value)
{
auto rs = find(std::move(cond));
std::vector<row_handle> rows;
std::copy(rs.begin(), rs.end(), std::back_inserter(rows));
update_value(rows, tag, value);
}
void update_value(const std::vector<row_handle> &rows, std::string_view tag, std::string_view value);
// --------------------------------------------------------------------
/// \brief Return the index number for \a column_name /// \brief Return the index number for \a column_name
uint16_t get_column_ix(std::string_view column_name) const uint16_t get_column_ix(std::string_view column_name) const
...@@ -573,6 +601,8 @@ class category ...@@ -573,6 +601,8 @@ class category
} }
} }
row_handle create_copy(row_handle r);
struct item_column struct item_column
{ {
std::string m_name; std::string m_name;
...@@ -607,6 +637,7 @@ class category ...@@ -607,6 +637,7 @@ class category
const category_validator *m_cat_validator = nullptr; const category_validator *m_cat_validator = nullptr;
std::vector<link> m_parent_links, m_child_links; std::vector<link> m_parent_links, m_child_links;
bool m_cascade = true; bool m_cascade = true;
uint32_t m_last_unique_num = 0;
class category_index* m_index = nullptr; class category_index* m_index = nullptr;
row *m_head = nullptr, *m_tail = nullptr; row *m_head = nullptr, *m_tail = nullptr;
}; };
......
include/cif++/v2/item.hpp
...@@ -452,8 +452,9 @@ struct item_handle::item_value_as<T, std::enable_if_t<std::is_same_v<T, std::str ...@@ -452,8 +452,9 @@ struct item_handle::item_value_as<T, std::enable_if_t<std::is_same_v<T, std::str
{ {
static std::string convert(const item_handle &ref) static std::string convert(const item_handle &ref)
{ {
std::string_view txt = ref.text(); if (ref.empty())
return {txt.data(), txt.size()}; return {};
return {ref.text().data(), ref.text().size()};
} }
static int compare(const item_handle &ref, const std::string &value, bool icase) static int compare(const item_handle &ref, const std::string &value, bool icase)
......
include/cif++/v2/validate.hpp
...@@ -31,16 +31,10 @@ ...@@ -31,16 +31,10 @@
// duh.. https://gcc.gnu.org/bugzilla/show_bug.cgi?id=86164 // duh.. https://gcc.gnu.org/bugzilla/show_bug.cgi?id=86164
// #include <regex> // #include <regex>
// TODO: get rid of boost::iostreams
#include <boost/iostreams/filter/gzip.hpp>
#include <boost/iostreams/filtering_stream.hpp>
#include <boost/regex.hpp> #include <boost/regex.hpp>
#include <cif++/CifUtils.hpp> #include <cif++/CifUtils.hpp>
namespace io = boost::iostreams;
namespace cif::v2 namespace cif::v2
{ {
......
src/Cif++.cpp
...@@ -38,9 +38,8 @@ ...@@ -38,9 +38,8 @@
#include <filesystem> #include <filesystem>
#include <boost/algorithm/string.hpp> #include <gzstream/gzstream.hpp>
#include <boost/iostreams/filter/gzip.hpp>
#include <boost/iostreams/filtering_stream.hpp>
#include <boost/logic/tribool.hpp> #include <boost/logic/tribool.hpp>
#include <cif++/Cif++.hpp> #include <cif++/Cif++.hpp>
...@@ -48,8 +47,6 @@ ...@@ -48,8 +47,6 @@
#include <cif++/CifUtils.hpp> #include <cif++/CifUtils.hpp>
#include <cif++/CifValidator.hpp> #include <cif++/CifValidator.hpp>
namespace ba = boost::algorithm;
namespace io = boost::iostreams;
namespace fs = std::filesystem; namespace fs = std::filesystem;
namespace cif namespace cif
...@@ -622,10 +619,10 @@ bool operator==(const cif::Datablock &dbA, const cif::Datablock &dbB) ...@@ -622,10 +619,10 @@ bool operator==(const cif::Datablock &dbA, const cif::Datablock &dbB)
while (catA_i != catA.end() and catB_i != catB.end()) while (catA_i != catA.end() and catB_i != catB.end())
{ {
std::string nA = *catA_i; std::string nA = *catA_i;
ba::to_lower(nA); toLower(nA);
std::string nB = *catB_i; std::string nB = *catB_i;
ba::to_lower(nB); toLower(nB);
int d = nA.compare(nB); int d = nA.compare(nB);
if (d > 0) if (d > 0)
...@@ -654,11 +651,11 @@ bool operator==(const cif::Datablock &dbA, const cif::Datablock &dbB) ...@@ -654,11 +651,11 @@ bool operator==(const cif::Datablock &dbA, const cif::Datablock &dbB)
{ {
std::cerr << "compare of datablocks failed" << std::endl; std::cerr << "compare of datablocks failed" << std::endl;
if (not missingA.empty()) if (not missingA.empty())
std::cerr << "Categories missing in A: " << ba::join(missingA, ", ") << std::endl std::cerr << "Categories missing in A: " << cif::join(missingA, ", ") << std::endl
<< std::endl; << std::endl;
if (not missingB.empty()) if (not missingB.empty())
std::cerr << "Categories missing in B: " << ba::join(missingB, ", ") << std::endl std::cerr << "Categories missing in B: " << cif::join(missingB, ", ") << std::endl
<< std::endl; << std::endl;
result = false; result = false;
...@@ -673,10 +670,10 @@ bool operator==(const cif::Datablock &dbA, const cif::Datablock &dbB) ...@@ -673,10 +670,10 @@ bool operator==(const cif::Datablock &dbA, const cif::Datablock &dbB)
while (catA_i != catA.end() and catB_i != catB.end()) while (catA_i != catA.end() and catB_i != catB.end())
{ {
std::string nA = *catA_i; std::string nA = *catA_i;
ba::to_lower(nA); toLower(nA);
std::string nB = *catB_i; std::string nB = *catB_i;
ba::to_lower(nB); toLower(nB);
int d = nA.compare(nB); int d = nA.compare(nB);
if (d > 0) if (d > 0)
...@@ -2156,7 +2153,7 @@ bool Category::isValid() ...@@ -2156,7 +2153,7 @@ bool Category::isValid()
if (not mandatory.empty()) if (not mandatory.empty())
{ {
mValidator->reportError("In Category " + mName + " the following mandatory fields are missing: " + ba::join(mandatory, ", "), false); mValidator->reportError("In Category " + mName + " the following mandatory fields are missing: " + cif::join(mandatory, ", "), false);
result = false; result = false;
} }
...@@ -2447,12 +2444,12 @@ namespace detail ...@@ -2447,12 +2444,12 @@ namespace detail
{ {
if (value.find('\n') != std::string::npos or width == 0 or value.length() > 132) // write as text field if (value.find('\n') != std::string::npos or width == 0 or value.length() > 132) // write as text field
{ {
ba::replace_all(value, "\n;", "\n\\;"); cif::replace_all(value, "\n;", "\n\\;");
if (offset > 0) if (offset > 0)
os << std::endl; os << std::endl;
os << ';' << value; os << ';' << value;
if (not ba::ends_with(value, "\n")) if (not cif::ends_with(value, "\n"))
os << std::endl; os << std::endl;
os << ';' << std::endl; os << ';' << std::endl;
offset = 0; offset = 0;
...@@ -3451,20 +3448,9 @@ void File::load(const std::filesystem::path &p) ...@@ -3451,20 +3448,9 @@ void File::load(const std::filesystem::path &p)
{ {
fs::path path(p); fs::path path(p);
std::ifstream inFile(p, std::ios_base::in | std::ios_base::binary);
if (not inFile.is_open())
throw std::runtime_error("Could not open file: " + path.string());
io::filtering_stream<io::input> in;
std::string ext;
if (path.extension() == ".gz") if (path.extension() == ".gz")
{ {
in.push(io::gzip_decompressor()); gzstream::ifstream in(p);
ext = path.stem().extension().string();
}
in.push(inFile);
try try
{ {
...@@ -3476,23 +3462,36 @@ void File::load(const std::filesystem::path &p) ...@@ -3476,23 +3462,36 @@ void File::load(const std::filesystem::path &p)
std::cerr << "Error loading file " << path << std::endl; std::cerr << "Error loading file " << path << std::endl;
throw; throw;
} }
}
else
{
std::ifstream inFile(p, std::ios_base::in | std::ios_base::binary);
try
{
load(inFile);
}
catch (const std::exception &ex)
{
if (cif::VERBOSE >= 0)
std::cerr << "Error loading file " << path << std::endl;
throw;
}
}
} }
void File::save(const std::filesystem::path &p) void File::save(const std::filesystem::path &p)
{ {
fs::path path(p); if (p.extension() == ".gz")
std::ofstream outFile(p, std::ios_base::out | std::ios_base::binary);
io::filtering_stream<io::output> out;
if (path.extension() == ".gz")
{ {
out.push(io::gzip_compressor()); gzstream::ofstream outFile(p);
path = path.stem(); save(outFile);
}
else
{
std::ofstream outFile(p, std::ios_base::out | std::ios_base::binary);
save(outFile);
} }
out.push(outFile);
save(out);
} }
void File::load(std::istream &is) void File::load(std::istream &is)
...@@ -3534,14 +3533,16 @@ void File::load(const char *data, std::size_t length) ...@@ -3534,14 +3533,16 @@ void File::load(const char *data, std::size_t length)
membuf(char *data, size_t length) { this->setg(data, data, data + length); } membuf(char *data, size_t length) { this->setg(data, data, data + length); }
} buffer(const_cast<char *>(data), length); } buffer(const_cast<char *>(data), length);
std::istream is(&buffer);
io::filtering_stream<io::input> in;
if (gzipped) if (gzipped)
in.push(io::gzip_decompressor()); {
in.push(is); gzstream::istream is(&buffer);
load(is);
}
else
{
std::istream is(&buffer);
load(is); load(is);
}
} }
void File::save(std::ostream &os) void File::save(std::ostream &os)
......
src/Cif2PDB.cpp
...@@ -30,51 +30,55 @@ ...@@ -30,51 +30,55 @@
#include <cmath> #include <cmath>
#include <iomanip> #include <iomanip>
#include <boost/algorithm/string.hpp>
#include <boost/format.hpp> #include <boost/format.hpp>
#include <boost/iostreams/filtering_stream.hpp>
#include <boost/iostreams/concepts.hpp> // output_filter
#include <boost/iostreams/operations.hpp> // put
#include <cif++/Cif2PDB.hpp> #include <cif++/Cif2PDB.hpp>
#include <cif++/AtomType.hpp> #include <cif++/AtomType.hpp>
#include <cif++/Compound.hpp> #include <cif++/Compound.hpp>
namespace ba = boost::algorithm;
namespace io = boost::iostreams;
using cif::Datablock; using cif::Datablock;
using cif::Category; using cif::Category;
using cif::Row; using cif::Row;
// -------------------------------------------------------------------- // --------------------------------------------------------------------
// FillOutLineFilter is used to make sure all lines in PDB files class FillOutStreamBuf : public std::streambuf
// are at filled out with spaces to be as much as 80 characters wide.
class FillOutLineFilter : public io::output_filter
{ {
public: public:
FillOutLineFilter() using base_type = std::streambuf;
: mLineCount(0), mColumnCount(0) {} using int_type = base_type::int_type;
using char_type = base_type::char_type;
using traits_type = base_type::traits_type;
FillOutStreamBuf(std::ostream &os)
: mOS(os)
, mUpstream(os.rdbuf())
{
}
template<typename Sink> ~FillOutStreamBuf()
bool put(Sink& dest, int c)
{ {
bool result = true; mOS.rdbuf(mUpstream);
}
virtual int_type
overflow(int_type ic = traits_type::eof())
{
char ch = traits_type::to_char_type(ic);
int_type result = ic;
if (c == '\n') if (ch == '\n')
{ {
for (int i = mColumnCount; result and i < 80; ++i) for (int i = mColumnCount; result != traits_type::eof() and i < 80; ++i)
result = io::put(dest, ' '); result = mUpstream->sputc(' ');
} }
if (result) if (result != traits_type::eof())
result = io::put(dest, c); result = mUpstream->sputc(ch);
if (result) if (result != traits_type::eof())
{ {
if (c == '\n') if (ch == '\n')
{ {
mColumnCount = 0; mColumnCount = 0;
++mLineCount; ++mLineCount;
...@@ -86,18 +90,15 @@ class FillOutLineFilter : public io::output_filter ...@@ -86,18 +90,15 @@ class FillOutLineFilter : public io::output_filter
return result; return result;
} }
template<typename Sink> std::streambuf *getUpstream() const { return mUpstream; }
void close(Sink&)
{
mLineCount = 0;
mColumnCount = 0;
}
int GetLineCount() const { return mLineCount; } int GetLineCount() const { return mLineCount; }
private: private:
int mLineCount; std::ostream &mOS;
int mColumnCount; std::streambuf *mUpstream;
int mLineCount = 0;
int mColumnCount = 0;
}; };
// -------------------------------------------------------------------- // --------------------------------------------------------------------
...@@ -198,8 +199,8 @@ std::string cifSoftware(const Datablock& db, SoftwareType sw) ...@@ -198,8 +199,8 @@ std::string cifSoftware(const Datablock& db, SoftwareType sw)
result = r["name"].as<std::string>() + " " + r["version"].as<std::string>(); result = r["name"].as<std::string>() + " " + r["version"].as<std::string>();
} }
ba::trim(result); cif::trim(result);
ba::to_upper(result); cif::toUpper(result);
if (result.empty()) if (result.empty())
result = "NULL"; result = "NULL";
...@@ -249,7 +250,7 @@ size_t WriteContinuedLine(std::ostream& pdbFile, std::string header, int& count, ...@@ -249,7 +250,7 @@ size_t WriteContinuedLine(std::ostream& pdbFile, std::string header, int& count,
for (auto& line: lines) for (auto& line: lines)
{ {
// ba::to_upper(line); // cif::toUpper(line);
pdbFile << header; pdbFile << header;
...@@ -302,13 +303,13 @@ size_t WriteCitation(std::ostream& pdbFile, const Datablock& db, Row r, int refe ...@@ -302,13 +303,13 @@ size_t WriteCitation(std::ostream& pdbFile, const Datablock& db, Row r, int refe
authors.push_back(cif2pdbAuth(r1["name"].as<std::string>())); authors.push_back(cif2pdbAuth(r1["name"].as<std::string>()));
if (not authors.empty()) if (not authors.empty())
result += WriteOneContinuedLine(pdbFile, s1 + "AUTH", 2, ba::join(authors, ","), 19); result += WriteOneContinuedLine(pdbFile, s1 + "AUTH", 2, cif::join(authors, ","), 19);
result += WriteOneContinuedLine(pdbFile, s1 + "TITL", 2, title, 19); result += WriteOneContinuedLine(pdbFile, s1 + "TITL", 2, title, 19);
if (not pubname.empty()) if (not pubname.empty())
{ {
ba::to_upper(pubname); cif::toUpper(pubname);
const std::string kRefHeader = s1 + "REF %2.2d %-28.28s %2.2s%4.4d %5.5d %4.4d"; const std::string kRefHeader = s1 + "REF %2.2d %-28.28s %2.2s%4.4d %5.5d %4.4d";
pdbFile << (boost::format(kRefHeader) pdbFile << (boost::format(kRefHeader)
...@@ -410,7 +411,7 @@ void WriteHeaderLines(std::ostream& pdbFile, const Datablock& db) ...@@ -410,7 +411,7 @@ void WriteHeaderLines(std::ostream& pdbFile, const Datablock& db)
for (auto r: db["struct"]) for (auto r: db["struct"])
{ {
std::string title = r["title"].as<std::string>(); std::string title = r["title"].as<std::string>();
ba::trim(title); cif::trim(title);
WriteOneContinuedLine(pdbFile, "TITLE ", 2, title); WriteOneContinuedLine(pdbFile, "TITLE ", 2, title);
break; break;
} }
...@@ -438,7 +439,7 @@ void WriteHeaderLines(std::ostream& pdbFile, const Datablock& db) ...@@ -438,7 +439,7 @@ void WriteHeaderLines(std::ostream& pdbFile, const Datablock& db)
if (not poly.empty()) if (not poly.empty())
{ {
std::string chains = poly.front()["pdbx_strand_id"].as<std::string>(); std::string chains = poly.front()["pdbx_strand_id"].as<std::string>();
ba::replace_all(chains, ",", ", "); cif::replace_all(chains, ",", ", ");
cmpnd.push_back("CHAIN: " + chains); cmpnd.push_back("CHAIN: " + chains);
} }
...@@ -469,7 +470,7 @@ void WriteHeaderLines(std::ostream& pdbFile, const Datablock& db) ...@@ -469,7 +470,7 @@ void WriteHeaderLines(std::ostream& pdbFile, const Datablock& db)
cmpnd.push_back("OTHER_DETAILS: " + details); cmpnd.push_back("OTHER_DETAILS: " + details);
} }
WriteOneContinuedLine(pdbFile, "COMPND ", 3, ba::join(cmpnd, ";\n")); WriteOneContinuedLine(pdbFile, "COMPND ", 3, cif::join(cmpnd, ";\n"));
// SOURCE // SOURCE
...@@ -550,7 +551,7 @@ void WriteHeaderLines(std::ostream& pdbFile, const Datablock& db) ...@@ -550,7 +551,7 @@ void WriteHeaderLines(std::ostream& pdbFile, const Datablock& db)
} }
} }
WriteOneContinuedLine(pdbFile, "SOURCE ", 3, ba::join(source, ";\n")); WriteOneContinuedLine(pdbFile, "SOURCE ", 3, cif::join(source, ";\n"));
// KEYWDS // KEYWDS
...@@ -575,7 +576,7 @@ void WriteHeaderLines(std::ostream& pdbFile, const Datablock& db) ...@@ -575,7 +576,7 @@ void WriteHeaderLines(std::ostream& pdbFile, const Datablock& db)
for (auto r: dbexpt) for (auto r: dbexpt)
method.push_back(r["method"].as<std::string>()); method.push_back(r["method"].as<std::string>());
if (not method.empty()) if (not method.empty())
WriteOneContinuedLine(pdbFile, "EXPDTA ", 2, ba::join(method, "; ")); WriteOneContinuedLine(pdbFile, "EXPDTA ", 2, cif::join(method, "; "));
} }
// NUMMDL // NUMMDL
...@@ -589,7 +590,7 @@ void WriteHeaderLines(std::ostream& pdbFile, const Datablock& db) ...@@ -589,7 +590,7 @@ void WriteHeaderLines(std::ostream& pdbFile, const Datablock& db)
for (auto r: db["audit_author"]) for (auto r: db["audit_author"])
authors.push_back(cif2pdbAuth(r["name"].as<std::string>())); authors.push_back(cif2pdbAuth(r["name"].as<std::string>()));
if (not authors.empty()) if (not authors.empty())
WriteOneContinuedLine(pdbFile, "AUTHOR ", 2, ba::join(authors, ",")); WriteOneContinuedLine(pdbFile, "AUTHOR ", 2, cif::join(authors, ","));
} }
void WriteTitle(std::ostream& pdbFile, const Datablock& db) void WriteTitle(std::ostream& pdbFile, const Datablock& db)
...@@ -1378,7 +1379,7 @@ void WriteRemark3Refmac(std::ostream& pdbFile, const Datablock& db) ...@@ -1378,7 +1379,7 @@ void WriteRemark3Refmac(std::ostream& pdbFile, const Datablock& db)
pdbFile << RM3("") << std::endl pdbFile << RM3("") << std::endl
<< RM3(" NCS GROUP NUMBER : ") << ens_id << std::endl << RM3(" NCS GROUP NUMBER : ") << ens_id << std::endl
<< RM3(" CHAIN NAMES : ") << ba::join(chains, " ") << std::endl << RM3(" CHAIN NAMES : ") << cif::join(chains, " ") << std::endl
<< RM3(" NUMBER OF COMPONENTS NCS GROUP : ") << component_ids.size() << std::endl << RM3(" NUMBER OF COMPONENTS NCS GROUP : ") << component_ids.size() << std::endl
<< RM3(" COMPONENT C SSSEQI TO C SSSEQI CODE") << std::endl; << RM3(" COMPONENT C SSSEQI TO C SSSEQI CODE") << std::endl;
...@@ -1397,12 +1398,12 @@ void WriteRemark3Refmac(std::ostream& pdbFile, const Datablock& db) ...@@ -1397,12 +1398,12 @@ void WriteRemark3Refmac(std::ostream& pdbFile, const Datablock& db)
for (auto l: db["refine_ls_restr_ncs"].find(cif::Key("pdbx_ens_id") == ens_id)) for (auto l: db["refine_ls_restr_ncs"].find(cif::Key("pdbx_ens_id") == ens_id))
{ {
std::string type = l["pdbx_type"].as<std::string>(); std::string type = l["pdbx_type"].as<std::string>();
ba::to_upper(type); cif::toUpper(type);
std::string unit; std::string unit;
if (ba::ends_with(type, "POSITIONAL")) if (cif::ends_with(type, "POSITIONAL"))
unit = " (A): "; unit = " (A): ";
else if (ba::ends_with(type, "THERMAL")) else if (cif::ends_with(type, "THERMAL"))
unit = " (A**2): "; unit = " (A**2): ";
else else
unit = " : "; unit = " : ";
...@@ -1729,7 +1730,7 @@ void WriteRemark3Phenix(std::ostream& pdbFile, const Datablock& db) ...@@ -1729,7 +1730,7 @@ void WriteRemark3Phenix(std::ostream& pdbFile, const Datablock& db)
// //
// pdbFile << RM3("") << std::endl // pdbFile << RM3("") << std::endl
// << RM3(" NCS GROUP NUMBER : ") << ens_id << std::endl // << RM3(" NCS GROUP NUMBER : ") << ens_id << std::endl
// << RM3(" CHAIN NAMES : ") << ba::join(chains, " ") << std::endl // << RM3(" CHAIN NAMES : ") << cif::join(chains, " ") << std::endl
// << RM3(" NUMBER OF COMPONENTS NCS GROUP : ") << component_ids.size() << std::endl // << RM3(" NUMBER OF COMPONENTS NCS GROUP : ") << component_ids.size() << std::endl
// << RM3(" COMPONENT C SSSEQI TO C SSSEQI CODE") << std::endl; // << RM3(" COMPONENT C SSSEQI TO C SSSEQI CODE") << std::endl;
// //
...@@ -1748,12 +1749,12 @@ void WriteRemark3Phenix(std::ostream& pdbFile, const Datablock& db) ...@@ -1748,12 +1749,12 @@ void WriteRemark3Phenix(std::ostream& pdbFile, const Datablock& db)
// for (auto l: db["refine_ls_restr_ncs"].find(cif::Key("pdbx_ens_id") == ens_id)) // for (auto l: db["refine_ls_restr_ncs"].find(cif::Key("pdbx_ens_id") == ens_id))
// { // {
// std::string type = l["pdbx_type"]; // std::string type = l["pdbx_type"];
// ba::to_upper(type); // cif::toUpper(type);
// //
// std::string unit; // std::string unit;
// if (ba::ends_with(type, "POSITIONAL")) // if (cif::ends_with(type, "POSITIONAL"))
// unit = " (A): "; // unit = " (A): ";
// else if (ba::ends_with(type, "THERMAL")) // else if (cif::ends_with(type, "THERMAL"))
// unit = " (A**2): "; // unit = " (A**2): ";
// else // else
// unit = " : "; // unit = " : ";
...@@ -2369,7 +2370,7 @@ void WriteRemark280(std::ostream& pdbFile, const Datablock& db) ...@@ -2369,7 +2370,7 @@ void WriteRemark280(std::ostream& pdbFile, const Datablock& db)
std::string v = exptl_crystal_grow[c].as<std::string>(); std::string v = exptl_crystal_grow[c].as<std::string>();
if (not v.empty()) if (not v.empty())
{ {
ba::to_upper(v); cif::toUpper(v);
switch (i) switch (i)
{ {
...@@ -2385,7 +2386,7 @@ void WriteRemark280(std::ostream& pdbFile, const Datablock& db) ...@@ -2385,7 +2386,7 @@ void WriteRemark280(std::ostream& pdbFile, const Datablock& db)
} }
} }
WriteOneContinuedLine(pdbFile, "REMARK 280", 0, "CRYSTALLIZATION CONDITIONS: " + (conditions.empty() ? "NULL" : ba::join(conditions, ", "))); WriteOneContinuedLine(pdbFile, "REMARK 280", 0, "CRYSTALLIZATION CONDITIONS: " + (conditions.empty() ? "NULL" : cif::join(conditions, ", ")));
break; break;
} }
...@@ -2420,7 +2421,7 @@ void WriteRemark350(std::ostream& pdbFile, const Datablock& db) ...@@ -2420,7 +2421,7 @@ void WriteRemark350(std::ostream& pdbFile, const Datablock& db)
// write out the mandatory REMARK 300 first // write out the mandatory REMARK 300 first
pdbFile << RM<300>("") << std::endl pdbFile << RM<300>("") << std::endl
<< RM<300>("BIOMOLECULE: ") << ba::join(biomolecules, ", ") << std::endl << RM<300>("BIOMOLECULE: ") << cif::join(biomolecules, ", ") << std::endl
<< RM<300>("SEE REMARK 350 FOR THE AUTHOR PROVIDED AND/OR PROGRAM") << std::endl << RM<300>("SEE REMARK 350 FOR THE AUTHOR PROVIDED AND/OR PROGRAM") << std::endl
<< RM<300>("GENERATED ASSEMBLY INFORMATION FOR THE STRUCTURE IN") << std::endl << RM<300>("GENERATED ASSEMBLY INFORMATION FOR THE STRUCTURE IN") << std::endl
<< RM<300>("THIS ENTRY. THE REMARK MAY ALSO PROVIDE INFORMATION ON") << std::endl << RM<300>("THIS ENTRY. THE REMARK MAY ALSO PROVIDE INFORMATION ON") << std::endl
...@@ -2451,7 +2452,7 @@ void WriteRemark350(std::ostream& pdbFile, const Datablock& db) ...@@ -2451,7 +2452,7 @@ void WriteRemark350(std::ostream& pdbFile, const Datablock& db)
pdbFile << RM("") << std::endl pdbFile << RM("") << std::endl
<< RM("BIOMOLECULE: ") << id << std::endl; << RM("BIOMOLECULE: ") << id << std::endl;
ba::to_upper(oligomer); cif::toUpper(oligomer);
if (detail == "author_defined_assembly" or detail == "author_and_software_defined_assembly") if (detail == "author_defined_assembly" or detail == "author_and_software_defined_assembly")
pdbFile << RM("AUTHOR DETERMINED BIOLOGICAL UNIT: ") << oligomer << std::endl; pdbFile << RM("AUTHOR DETERMINED BIOLOGICAL UNIT: ") << oligomer << std::endl;
...@@ -2479,20 +2480,16 @@ void WriteRemark350(std::ostream& pdbFile, const Datablock& db) ...@@ -2479,20 +2480,16 @@ void WriteRemark350(std::ostream& pdbFile, const Datablock& db)
auto gen = db["pdbx_struct_assembly_gen"][cif::Key("assembly_id") == id]; auto gen = db["pdbx_struct_assembly_gen"][cif::Key("assembly_id") == id];
std::vector<std::string> asyms;
std::string asym_id_list, oper_id_list; std::string asym_id_list, oper_id_list;
cif::tie(asym_id_list, oper_id_list) = gen.get("asym_id_list", "oper_expression"); cif::tie(asym_id_list, oper_id_list) = gen.get("asym_id_list", "oper_expression");
ba::split(asyms, asym_id_list, ba::is_any_of(",")); auto asyms = cif::split<std::string>(asym_id_list, ",");
std::vector<std::string> chains = MapAsymIDs2ChainIDs(asyms, db); std::vector<std::string> chains = MapAsymIDs2ChainIDs(asyms, db);
pdbFile << RM("APPLY THE FOLLOWING TO CHAINS: ") << ba::join(chains, ", ") << std::endl; pdbFile << RM("APPLY THE FOLLOWING TO CHAINS: ") << cif::join(chains, ", ") << std::endl;
for (auto oper_id : cif::split<std::string>(oper_id_list, ",", true))
for (auto i = make_split_iterator(oper_id_list, ba::token_finder(ba::is_any_of(","), ba::token_compress_on)); not i.eof(); ++i)
{ {
std::string oper_id{ i->begin(), i->end() };
auto r = db["pdbx_struct_oper_list"][cif::Key("id") == oper_id]; auto r = db["pdbx_struct_oper_list"][cif::Key("id") == oper_id];
pdbFile << RM(" BIOMT1 ", -3) << Fs(r, "id") pdbFile << RM(" BIOMT1 ", -3) << Fs(r, "id")
...@@ -2666,7 +2663,7 @@ void WriteRemark800(std::ostream& pdbFile, const Datablock& db) ...@@ -2666,7 +2663,7 @@ void WriteRemark800(std::ostream& pdbFile, const Datablock& db)
std::string ident, code, desc; std::string ident, code, desc;
cif::tie(ident, code, desc) = r.get("id", "pdbx_evidence_code", "details"); cif::tie(ident, code, desc) = r.get("id", "pdbx_evidence_code", "details");
ba::to_upper(code); cif::toUpper(code);
for (auto l: { "SITE_IDENTIFIER: " + ident, "EVIDENCE_CODE: " + code, "SITE_DESCRIPTION: " + desc }) for (auto l: { "SITE_IDENTIFIER: " + ident, "EVIDENCE_CODE: " + code, "SITE_DESCRIPTION: " + desc })
{ {
...@@ -2780,7 +2777,7 @@ int WritePrimaryStructure(std::ostream& pdbFile, const Datablock& db) ...@@ -2780,7 +2777,7 @@ int WritePrimaryStructure(std::ostream& pdbFile, const Datablock& db)
"pdbx_seq_db_name", "pdbx_seq_db_accession_code", "db_mon_id", "pdbx_seq_db_seq_num", "pdbx_seq_db_name", "pdbx_seq_db_accession_code", "db_mon_id", "pdbx_seq_db_seq_num",
"details"); "details");
ba::to_upper(conflict); cif::toUpper(conflict);
pdbFile << (boost::format( pdbFile << (boost::format(
"SEQADV %4.4s %3.3s %1.1s %4.4s%1.1s %-4.4s %-9.9s %3.3s %5.5s %-21.21s") "SEQADV %4.4s %3.3s %1.1s %4.4s%1.1s %-4.4s %-9.9s %3.3s %5.5s %-21.21s")
...@@ -2823,14 +2820,12 @@ int WritePrimaryStructure(std::ostream& pdbFile, const Datablock& db) ...@@ -2823,14 +2820,12 @@ int WritePrimaryStructure(std::ostream& pdbFile, const Datablock& db)
if (t > 13) if (t > 13)
t = 13; t = 13;
auto r = boost::make_iterator_range(seq.begin(), seq.begin() + t);
pdbFile << (boost::format( pdbFile << (boost::format(
"SEQRES %3.3d %c %4.4d %-51.51s ") "SEQRES %3.3d %c %4.4d %-51.51s ")
% n++ % n++
% chainID % chainID
% seqresl[chainID] % seqresl[chainID]
% ba::join(r, " ")).str() % cif::join(seq.begin(), seq.begin() + t, " ")).str()
<< std::endl; << std::endl;
++numSeq; ++numSeq;
...@@ -2966,7 +2961,7 @@ int WriteHeterogen(std::ostream& pdbFile, const Datablock& db) ...@@ -2966,7 +2961,7 @@ int WriteHeterogen(std::ostream& pdbFile, const Datablock& db)
} }
if (cif::VERBOSE > 1 and not missingHetNames.empty()) if (cif::VERBOSE > 1 and not missingHetNames.empty())
std::cerr << "Missing het name(s) for " << ba::join(missingHetNames, ", ") << std::endl; std::cerr << "Missing het name(s) for " << cif::join(missingHetNames, ", ") << std::endl;
boost::format kHET("HET %3.3s %1.1s%4.4d%1.1s %5.5d"); boost::format kHET("HET %3.3s %1.1s%4.4d%1.1s %5.5d");
for (auto h: hets) for (auto h: hets)
...@@ -2985,7 +2980,7 @@ int WriteHeterogen(std::ostream& pdbFile, const Datablock& db) ...@@ -2985,7 +2980,7 @@ int WriteHeterogen(std::ostream& pdbFile, const Datablock& db)
if (id == water_comp_id) if (id == water_comp_id)
continue; continue;
ba::to_upper(name); cif::toUpper(name);
int c = 1; int c = 1;
...@@ -3723,46 +3718,35 @@ std::tuple<int,int> WriteCoordinate(std::ostream& pdbFile, const Datablock& db) ...@@ -3723,46 +3718,35 @@ std::tuple<int,int> WriteCoordinate(std::ostream& pdbFile, const Datablock& db)
void WritePDBFile(std::ostream& pdbFile, const Datablock &db) void WritePDBFile(std::ostream& pdbFile, const Datablock &db)
{ {
io::filtering_ostream out; FillOutStreamBuf fb(pdbFile);
out.push(FillOutLineFilter());
out.push(pdbFile);
auto filter = out.component<FillOutLineFilter>(0);
assert(filter);
int numRemark = 0, numHet = 0, numHelix = 0, numSheet = 0, numTurn = 0, numSite = 0, numXform = 0, numCoord = 0, numTer = 0, numConect = 0, numSeq = 0; int numRemark = 0, numHet = 0, numHelix = 0, numSheet = 0, numTurn = 0, numSite = 0, numXform = 0, numCoord = 0, numTer = 0, numConect = 0, numSeq = 0;
WriteTitle(out, db); WriteTitle(pdbFile, db);
int savedLineCount = filter->GetLineCount(); int savedLineCount = fb.GetLineCount();
// numRemark = WriteRemarks(out, db); // numRemark = WriteRemarks(pdbFile, db);
WriteRemarks(out, db); WriteRemarks(pdbFile, db);
numRemark = filter->GetLineCount() - savedLineCount; numRemark = fb.GetLineCount() - savedLineCount;
numSeq = WritePrimaryStructure(out, db); numSeq = WritePrimaryStructure(pdbFile, db);
numHet = WriteHeterogen(out, db); numHet = WriteHeterogen(pdbFile, db);
std::tie(numHelix, numSheet) = WriteSecondaryStructure(out, db); std::tie(numHelix, numSheet) = WriteSecondaryStructure(pdbFile, db);
WriteConnectivity(out, db); WriteConnectivity(pdbFile, db);
numSite = WriteMiscellaneousFeatures(out, db); numSite = WriteMiscellaneousFeatures(pdbFile, db);
WriteCrystallographic(out, db); WriteCrystallographic(pdbFile, db);
numXform = WriteCoordinateTransformation(out, db); numXform = WriteCoordinateTransformation(pdbFile, db);
std::tie(numCoord, numTer) = WriteCoordinate(out, db); std::tie(numCoord, numTer) = WriteCoordinate(pdbFile, db);
boost::format kMASTER("MASTER %5.5d 0%5.5d%5.5d%5.5d%5.5d%5.5d%5.5d%5.5d%5.5d%5.5d%5.5d"); boost::format kMASTER("MASTER %5.5d 0%5.5d%5.5d%5.5d%5.5d%5.5d%5.5d%5.5d%5.5d%5.5d%5.5d");
out << (kMASTER % numRemark % numHet % numHelix % numSheet % numTurn % numSite % numXform % numCoord % numTer % numConect % numSeq) << std::endl pdbFile << (kMASTER % numRemark % numHet % numHelix % numSheet % numTurn % numSite % numXform % numCoord % numTer % numConect % numSeq) << std::endl
<< "END" << std::endl; << "END" << std::endl;
} }
void WritePDBHeaderLines(std::ostream& os, const Datablock &db) void WritePDBHeaderLines(std::ostream& os, const Datablock &db)
{ {
// io::filtering_ostream out; FillOutStreamBuf fb(os);
// out.push(FillOutLineFilter());
// out.push(os);
// auto filter = out.component<FillOutLineFilter>(0);
// assert(filter);
WriteHeaderLines(os, db); WriteHeaderLines(os, db);
} }
...@@ -3847,7 +3831,7 @@ std::string GetPDBCOMPNDLine(const Datablock &db, std::string::size_type truncat ...@@ -3847,7 +3831,7 @@ std::string GetPDBCOMPNDLine(const Datablock &db, std::string::size_type truncat
if (not poly.empty()) if (not poly.empty())
{ {
std::string chains = poly.front()["pdbx_strand_id"].as<std::string>(); std::string chains = poly.front()["pdbx_strand_id"].as<std::string>();
ba::replace_all(chains, ",", ", "); cif::replace_all(chains, ",", ", ");
cmpnd.push_back("CHAIN: " + chains); cmpnd.push_back("CHAIN: " + chains);
} }
...@@ -3878,7 +3862,7 @@ std::string GetPDBCOMPNDLine(const Datablock &db, std::string::size_type truncat ...@@ -3878,7 +3862,7 @@ std::string GetPDBCOMPNDLine(const Datablock &db, std::string::size_type truncat
cmpnd.push_back("OTHER_DETAILS: " + details); cmpnd.push_back("OTHER_DETAILS: " + details);
} }
return FixStringLength("COMPND " + ba::join(cmpnd, "; "), truncate_at); return FixStringLength("COMPND " + cif::join(cmpnd, "; "), truncate_at);
} }
std::string GetPDBSOURCELine(const Datablock &db, std::string::size_type truncate_at) std::string GetPDBSOURCELine(const Datablock &db, std::string::size_type truncate_at)
...@@ -3961,7 +3945,7 @@ std::string GetPDBSOURCELine(const Datablock &db, std::string::size_type truncat ...@@ -3961,7 +3945,7 @@ std::string GetPDBSOURCELine(const Datablock &db, std::string::size_type truncat
} }
} }
return FixStringLength("SOURCE " + ba::join(source, "; "), truncate_at); return FixStringLength("SOURCE " + cif::join(source, "; "), truncate_at);
} }
std::string GetPDBAUTHORLine(const Datablock &db, std::string::size_type truncate_at) std::string GetPDBAUTHORLine(const Datablock &db, std::string::size_type truncate_at)
...@@ -3971,5 +3955,5 @@ std::string GetPDBAUTHORLine(const Datablock &db, std::string::size_type truncat ...@@ -3971,5 +3955,5 @@ std::string GetPDBAUTHORLine(const Datablock &db, std::string::size_type truncat
for (auto r: db["audit_author"]) for (auto r: db["audit_author"])
author.push_back(cif2pdbAuth(r["name"].as<std::string>())); author.push_back(cif2pdbAuth(r["name"].as<std::string>()));
return FixStringLength("AUTHOR " + ba::join(author, "; "), truncate_at); return FixStringLength("AUTHOR " + cif::join(author, "; "), truncate_at);
} }
src/CifParser.cpp
...@@ -26,14 +26,10 @@ ...@@ -26,14 +26,10 @@
#include <set> #include <set>
#include <boost/algorithm/string.hpp>
#include <cif++/Cif++.hpp> #include <cif++/Cif++.hpp>
#include <cif++/CifParser.hpp> #include <cif++/CifParser.hpp>
#include <cif++/CifValidator.hpp> #include <cif++/CifValidator.hpp>
namespace ba = boost::algorithm;
extern int VERBOSE; extern int VERBOSE;
namespace cif namespace cif
...@@ -1300,9 +1296,9 @@ bool DictParser::collectItemTypes() ...@@ -1300,9 +1296,9 @@ bool DictParser::collectItemTypes()
std::string code, primitiveCode, construct; std::string code, primitiveCode, construct;
cif::tie(code, primitiveCode, construct) = t.get("code", "primitive_code", "construct"); cif::tie(code, primitiveCode, construct) = t.get("code", "primitive_code", "construct");
ba::replace_all(construct, "\\n", "\n"); cif::replace_all(construct, "\\n", "\n");
ba::replace_all(construct, "\\t", "\t"); cif::replace_all(construct, "\\t", "\t");
ba::replace_all(construct, "\\\n", ""); cif::replace_all(construct, "\\\n", "");
try try
{ {
......
src/CifUtils.cpp
...@@ -25,6 +25,7 @@ ...@@ -25,6 +25,7 @@
*/ */
#include <atomic> #include <atomic>
#include <cassert>
#include <cmath> #include <cmath>
#include <fstream> #include <fstream>
#include <iomanip> #include <iomanip>
...@@ -42,13 +43,10 @@ ...@@ -42,13 +43,10 @@
#include <termios.h> #include <termios.h>
#endif #endif
#include <boost/algorithm/string.hpp>
#include <cif++/CifUtils.hpp> #include <cif++/CifUtils.hpp>
#include "revision.hpp" #include "revision.hpp"
namespace ba = boost::algorithm;
namespace fs = std::filesystem; namespace fs = std::filesystem;
// -------------------------------------------------------------------- // --------------------------------------------------------------------
...@@ -152,7 +150,7 @@ void toLower(std::string &s) ...@@ -152,7 +150,7 @@ void toLower(std::string &s)
c = tolower(c); c = tolower(c);
} }
std::string toLowerCopy(const std::string &s) std::string toLowerCopy(std::string_view s)
{ {
std::string result(s); std::string result(s);
for (auto &c : result) for (auto &c : result)
...@@ -160,6 +158,91 @@ std::string toLowerCopy(const std::string &s) ...@@ -160,6 +158,91 @@ std::string toLowerCopy(const std::string &s)
return result; return result;
} }
void toUpper(std::string &s)
{
for (auto &c : s)
c = toupper(c);
}
void replace_all(std::string &s, std::string_view what, std::string_view with)
{
for (std::string::size_type p = s.find(what); p != std::string::npos; p = s.find(what, p))
s.replace(p, what.length(), with);
}
bool icontains(std::string_view s, std::string_view q)
{
return contains(toLowerCopy(s), toLowerCopy(q));
}
void trim_right(std::string &s)
{
auto e = s.end();
while (e != s.begin())
{
auto pe = std::prev(e);
if (not std::isspace(*pe))
break;
e = pe;
}
if (e != s.end())
s.erase(e, s.end());
}
std::string trim_right_copy(std::string_view s)
{
auto e = s.end();
while (e != s.begin())
{
auto pe = std::prev(e);
if (not std::isspace(*pe))
break;
e = pe;
}
return {s.begin(), e};
}
std::string trim_left_copy(std::string_view s)
{
auto b = s.begin();
while (b != s.end())
{
if (not std::isspace(*b))
break;
b = std::next(b);
}
return {b, s.end()};
}
void trim_left(std::string &s)
{
auto b = s.begin();
while (b != s.end())
{
if (not std::isspace(*b))
break;
b = std::next(b);
}
s.erase(s.begin(), b);
}
void trim(std::string &s)
{
trim_right(s);
trim_left(s);
}
std::string trim_copy(std::string_view s)
{
return trim_left_copy(trim_right_copy(s));
}
// -------------------------------------------------------------------- // --------------------------------------------------------------------
std::tuple<std::string, std::string> splitTagName(std::string_view tag) std::tuple<std::string, std::string> splitTagName(std::string_view tag)
...@@ -433,11 +516,8 @@ std::vector<std::string> wrapLine(const std::string &text, size_t width) ...@@ -433,11 +516,8 @@ std::vector<std::string> wrapLine(const std::string &text, size_t width)
std::vector<std::string> wordWrap(const std::string &text, size_t width) std::vector<std::string> wordWrap(const std::string &text, size_t width)
{ {
std::vector<std::string> paragraphs;
ba::split(paragraphs, text, ba::is_any_of("\n"));
std::vector<std::string> result; std::vector<std::string> result;
for (auto &p : paragraphs) for (auto p : cif::split<std::string>(text, "\n"))
{ {
if (p.empty()) if (p.empty())
{ {
...@@ -488,6 +568,9 @@ std::string GetExecutablePath() ...@@ -488,6 +568,9 @@ std::string GetExecutablePath()
} }
#else #else
#include <limits.h>
uint32_t get_terminal_width() uint32_t get_terminal_width()
{ {
uint32_t result = 80; uint32_t result = 80;
...@@ -786,9 +869,9 @@ struct rsrc_imp ...@@ -786,9 +869,9 @@ struct rsrc_imp
#if _MSC_VER #if _MSC_VER
extern "C" const mrsrc::rsrc_imp* gResourceIndexDefault[1] = {}; extern "C" const mrsrc::rsrc_imp *gResourceIndexDefault[1] = {};
extern "C" const char* gResourceDataDefault[1] = {}; extern "C" const char *gResourceDataDefault[1] = {};
extern "C" const char* gResourceNameDefault[1] = {}; extern "C" const char *gResourceNameDefault[1] = {};
extern "C" const mrsrc::rsrc_imp gResourceIndex[]; extern "C" const mrsrc::rsrc_imp gResourceIndex[];
extern "C" const char gResourceData[]; extern "C" const char gResourceData[];
...@@ -1250,12 +1333,14 @@ class ResourcePool ...@@ -1250,12 +1333,14 @@ class ResourcePool
result.reset(file.release()); result.reset(file.release());
} }
} }
catch (...) {} catch (...)
{
}
return result; return result;
} }
std::map<std::string,std::filesystem::path> mLocalResources; std::map<std::string, std::filesystem::path> mLocalResources;
std::deque<fs::path> mDirs; std::deque<fs::path> mDirs;
}; };
......
src/CifValidator.cpp
...@@ -27,17 +27,13 @@ ...@@ -27,17 +27,13 @@
#include <fstream> #include <fstream>
#include <filesystem> #include <filesystem>
#include <boost/algorithm/string.hpp> #include <gzstream/gzstream.hpp>
#include <boost/iostreams/filtering_stream.hpp>
#include <boost/iostreams/filter/gzip.hpp>
#include <cif++/Cif++.hpp> #include <cif++/Cif++.hpp>
#include <cif++/CifParser.hpp> #include <cif++/CifParser.hpp>
#include <cif++/CifValidator.hpp> #include <cif++/CifValidator.hpp>
namespace ba = boost::algorithm;
namespace fs = std::filesystem; namespace fs = std::filesystem;
namespace io = boost::iostreams;
extern int VERBOSE; extern int VERBOSE;
...@@ -416,15 +412,11 @@ const Validator &ValidatorFactory::operator[](std::string_view dictionary) ...@@ -416,15 +412,11 @@ const Validator &ValidatorFactory::operator[](std::string_view dictionary)
if (fs::exists(p, ec) and not ec) if (fs::exists(p, ec) and not ec)
{ {
std::ifstream file(p, std::ios::binary); gzstream::ifstream file(p);
if (not file.is_open()) if (not file.is_open())
throw std::runtime_error("Could not open dictionary (" + p.string() + ")"); throw std::runtime_error("Could not open dictionary (" + p.string() + ")");
io::filtering_stream<io::input> in; mValidators.emplace_back(dictionary, file);
in.push(io::gzip_decompressor());
in.push(file);
mValidators.emplace_back(dictionary, in);
} }
else else
throw std::runtime_error("Dictionary not found or defined (" + dict_name.string() + ")"); throw std::runtime_error("Dictionary not found or defined (" + dict_name.string() + ")");
......
src/Compound.cpp
...@@ -29,8 +29,6 @@ ...@@ -29,8 +29,6 @@
#include <numeric> #include <numeric>
#include <shared_mutex> #include <shared_mutex>
#include <boost/algorithm/string.hpp>
#include <filesystem> #include <filesystem>
#include <fstream> #include <fstream>
...@@ -40,7 +38,6 @@ ...@@ -40,7 +38,6 @@
#include <cif++/Compound.hpp> #include <cif++/Compound.hpp>
#include <cif++/Point.hpp> #include <cif++/Point.hpp>
namespace ba = boost::algorithm;
namespace fs = std::filesystem; namespace fs = std::filesystem;
namespace mmcif namespace mmcif
...@@ -126,7 +123,7 @@ Compound::Compound(cif::Datablock &db) ...@@ -126,7 +123,7 @@ Compound::Compound(cif::Datablock &db)
chemComp.front().get("id", "name", "type", "formula", "formula_weight", "pdbx_formal_charge"); chemComp.front().get("id", "name", "type", "formula", "formula_weight", "pdbx_formal_charge");
// The name should not contain newline characters since that triggers validation errors later on // The name should not contain newline characters since that triggers validation errors later on
ba::replace_all(mName, "\n", ""); cif::replace_all(mName, "\n", "");
mGroup = "non-polymer"; mGroup = "non-polymer";
...@@ -286,7 +283,7 @@ class CompoundFactoryImpl : public std::enable_shared_from_this<CompoundFactoryI ...@@ -286,7 +283,7 @@ class CompoundFactoryImpl : public std::enable_shared_from_this<CompoundFactoryI
{ {
std::shared_lock lock(mMutex); std::shared_lock lock(mMutex);
ba::to_upper(id); cif::toUpper(id);
Compound *result = nullptr; Compound *result = nullptr;
...@@ -554,7 +551,7 @@ CCP4CompoundFactoryImpl::CCP4CompoundFactoryImpl(const fs::path &clibd_mon, std: ...@@ -554,7 +551,7 @@ CCP4CompoundFactoryImpl::CCP4CompoundFactoryImpl(const fs::path &clibd_mon, std:
{ {
if (std::regex_match(group, peptideRx)) if (std::regex_match(group, peptideRx))
mKnownPeptides.insert(threeLetterCode); mKnownPeptides.insert(threeLetterCode);
else if (ba::iequals(group, "DNA") or ba::iequals(group, "RNA")) else if (cif::iequals(group, "DNA") or cif::iequals(group, "RNA"))
mKnownBases.insert(threeLetterCode); mKnownBases.insert(threeLetterCode);
} }
} }
...@@ -576,10 +573,10 @@ Compound *CCP4CompoundFactoryImpl::create(const std::string &id) ...@@ -576,10 +573,10 @@ Compound *CCP4CompoundFactoryImpl::create(const std::string &id)
cif::tie(name, group, numberAtomsAll, numberAtomsNh) = cif::tie(name, group, numberAtomsAll, numberAtomsNh) =
row.get("name", "group", "number_atoms_all", "number_atoms_nh"); row.get("name", "group", "number_atoms_all", "number_atoms_nh");
fs::path resFile = mCLIBD_MON / ba::to_lower_copy(id.substr(0, 1)) / (id + ".cif"); fs::path resFile = mCLIBD_MON / cif::toLowerCopy(id.substr(0, 1)) / (id + ".cif");
if (not fs::exists(resFile) and (id == "COM" or id == "CON" or "PRN")) // seriously... if (not fs::exists(resFile) and (id == "COM" or id == "CON" or "PRN")) // seriously...
resFile = mCLIBD_MON / ba::to_lower_copy(id.substr(0, 1)) / (id + '_' + id + ".cif"); resFile = mCLIBD_MON / cif::toLowerCopy(id.substr(0, 1)) / (id + '_' + id + ".cif");
if (fs::exists(resFile)) if (fs::exists(resFile))
{ {
......
src/PDB2Cif.cpp
...@@ -30,7 +30,6 @@ ...@@ -30,7 +30,6 @@
#include <system_error> #include <system_error>
#include <iomanip> #include <iomanip>
#include <boost/algorithm/string.hpp>
#include <boost/format.hpp> #include <boost/format.hpp>
#include <boost/numeric/ublas/matrix.hpp> #include <boost/numeric/ublas/matrix.hpp>
...@@ -42,13 +41,13 @@ ...@@ -42,13 +41,13 @@
#include <cif++/Point.hpp> #include <cif++/Point.hpp>
#include <cif++/Symmetry.hpp> #include <cif++/Symmetry.hpp>
namespace ba = boost::algorithm;
using cif::Category; using cif::Category;
using cif::Datablock; using cif::Datablock;
using cif::iequals; using cif::iequals;
using cif::Key; using cif::Key;
using cif::Row; using cif::Row;
using cif::toLower;
using cif::toLowerCopy;
using mmcif::CompoundFactory; using mmcif::CompoundFactory;
// -------------------------------------------------------------------- // --------------------------------------------------------------------
...@@ -205,7 +204,7 @@ std::string PDBRecord::vS(size_t columnFirst, size_t columnLast) ...@@ -205,7 +204,7 @@ std::string PDBRecord::vS(size_t columnFirst, size_t columnLast)
if (columnFirst < mVlen + 7) if (columnFirst < mVlen + 7)
{ {
result = std::string{mValue + columnFirst - 7, mValue + columnLast - 7 + 1}; result = std::string{mValue + columnFirst - 7, mValue + columnLast - 7 + 1};
ba::trim(result); cif::trim(result);
} }
return result; return result;
...@@ -429,7 +428,7 @@ std::tuple<std::string, std::string> SpecificationListParser::GetNextSpecificati ...@@ -429,7 +428,7 @@ std::tuple<std::string, std::string> SpecificationListParser::GetNextSpecificati
} }
} }
ba::trim(value); cif::trim(value);
return std::make_tuple(id, value); return std::make_tuple(id, value);
} }
...@@ -949,7 +948,7 @@ class PDBFileParser ...@@ -949,7 +948,7 @@ class PDBFileParser
std::string pdb2cifAuth(std::string author) std::string pdb2cifAuth(std::string author)
{ {
ba::trim(author); cif::trim(author);
const std::regex rx(R"(((?:[A-Z]+\.)+)(.+))"); const std::regex rx(R"(((?:[A-Z]+\.)+)(.+))");
std::smatch m; std::smatch m;
...@@ -1135,13 +1134,13 @@ void PDBFileParser::PreParseInput(std::istream &is) ...@@ -1135,13 +1134,13 @@ void PDBFileParser::PreParseInput(std::istream &is)
if (lookahead.back() == '\r') if (lookahead.back() == '\r')
lookahead.pop_back(); lookahead.pop_back();
// if (ba::starts_with(lookahead, "HEADER") == false) // if (cif::starts_with(lookahead, "HEADER") == false)
// throw std::runtime_error("This does not look like a PDB file, should start with a HEADER line"); // throw std::runtime_error("This does not look like a PDB file, should start with a HEADER line");
auto contNr = [&lookahead](int offset, int len) -> int auto contNr = [&lookahead](int offset, int len) -> int
{ {
std::string cs = lookahead.substr(offset, len); std::string cs = lookahead.substr(offset, len);
ba::trim(cs); cif::trim(cs);
int result; int result;
try try
...@@ -1177,7 +1176,7 @@ void PDBFileParser::PreParseInput(std::istream &is) ...@@ -1177,7 +1176,7 @@ void PDBFileParser::PreParseInput(std::istream &is)
std::string type = lookahead.substr(0, 6); std::string type = lookahead.substr(0, 6);
std::string value; std::string value;
if (lookahead.length() > 6) if (lookahead.length() > 6)
value = ba::trim_right_copy(lookahead.substr(6)); value = cif::trim_right_copy(lookahead.substr(6));
uint32_t curLineNr = lineNr; uint32_t curLineNr = lineNr;
getline(is, lookahead); getline(is, lookahead);
...@@ -1185,7 +1184,7 @@ void PDBFileParser::PreParseInput(std::istream &is) ...@@ -1185,7 +1184,7 @@ void PDBFileParser::PreParseInput(std::istream &is)
if (kSupportedRecords.count(type) == 0) if (kSupportedRecords.count(type) == 0)
{ {
ba::trim(type); cif::trim(type);
if (type != "END") // special case if (type != "END") // special case
dropped.insert(type); dropped.insert(type);
...@@ -1207,7 +1206,7 @@ void PDBFileParser::PreParseInput(std::istream &is) ...@@ -1207,7 +1206,7 @@ void PDBFileParser::PreParseInput(std::istream &is)
int n = 2; int n = 2;
while (lookahead.substr(0, 6) == type and contNr(7, 3) == n) while (lookahead.substr(0, 6) == type and contNr(7, 3) == n)
{ {
value += ba::trim_right_copy(lookahead.substr(10)); value += cif::trim_right_copy(lookahead.substr(10));
getline(is, lookahead); getline(is, lookahead);
++lineNr; ++lineNr;
++n; ++n;
...@@ -1219,7 +1218,7 @@ void PDBFileParser::PreParseInput(std::istream &is) ...@@ -1219,7 +1218,7 @@ void PDBFileParser::PreParseInput(std::istream &is)
value += '\n'; value += '\n';
while (lookahead.substr(0, 6) == type and contNr(7, 3) == n) while (lookahead.substr(0, 6) == type and contNr(7, 3) == n)
{ {
value += ba::trim_right_copy(lookahead.substr(10)); value += cif::trim_right_copy(lookahead.substr(10));
value += '\n'; value += '\n';
getline(is, lookahead); getline(is, lookahead);
++lineNr; ++lineNr;
...@@ -1245,7 +1244,7 @@ void PDBFileParser::PreParseInput(std::istream &is) ...@@ -1245,7 +1244,7 @@ void PDBFileParser::PreParseInput(std::istream &is)
int n = 2; int n = 2;
while (lookahead.substr(0, 6) == type and contNr(7, 3) == n) while (lookahead.substr(0, 6) == type and contNr(7, 3) == n)
{ {
value += ba::trim_right_copy(lookahead.substr(13)); value += cif::trim_right_copy(lookahead.substr(13));
getline(is, lookahead); getline(is, lookahead);
++lineNr; ++lineNr;
++n; ++n;
...@@ -1266,7 +1265,7 @@ void PDBFileParser::PreParseInput(std::istream &is) ...@@ -1266,7 +1265,7 @@ void PDBFileParser::PreParseInput(std::istream &is)
int n = 2; int n = 2;
while (lookahead.substr(0, 6) == type and contNr(7, 3) == n) while (lookahead.substr(0, 6) == type and contNr(7, 3) == n)
{ {
value += ba::trim_copy(lookahead.substr(10)); value += cif::trim_copy(lookahead.substr(10));
value += '\n'; value += '\n';
getline(is, lookahead); getline(is, lookahead);
++lineNr; ++lineNr;
...@@ -1297,7 +1296,7 @@ void PDBFileParser::PreParseInput(std::istream &is) ...@@ -1297,7 +1296,7 @@ void PDBFileParser::PreParseInput(std::istream &is)
stoi(lookahead.substr(7, 3)) == compNr and stoi(lookahead.substr(7, 3)) == compNr and
contNr(16, 2) == n) contNr(16, 2) == n)
{ {
value += ba::trim_right_copy(lookahead.substr(19)); value += cif::trim_right_copy(lookahead.substr(19));
; ;
getline(is, lookahead); getline(is, lookahead);
++lineNr; ++lineNr;
...@@ -1323,7 +1322,7 @@ void PDBFileParser::PreParseInput(std::istream &is) ...@@ -1323,7 +1322,7 @@ void PDBFileParser::PreParseInput(std::istream &is)
int n = 2; int n = 2;
while (lookahead.substr(0, 6) == type and contNr(8, 2) == n) while (lookahead.substr(0, 6) == type and contNr(8, 2) == n)
{ {
value += ba::trim_right_copy(lookahead.substr(16)); value += cif::trim_right_copy(lookahead.substr(16));
; ;
getline(is, lookahead); getline(is, lookahead);
++lineNr; ++lineNr;
...@@ -1333,19 +1332,19 @@ void PDBFileParser::PreParseInput(std::istream &is) ...@@ -1333,19 +1332,19 @@ void PDBFileParser::PreParseInput(std::istream &is)
else if (type == "SITE ") else if (type == "SITE ")
{ {
std::string siteName = value.substr(5, 3); std::string siteName = value.substr(5, 3);
ba::trim_right(value); cif::trim_right(value);
size_t n = value.length() - 12; size_t n = value.length() - 12;
value += std::string(11 - (n % 11), ' '); value += std::string(11 - (n % 11), ' ');
while (lookahead.substr(0, 6) == type and lookahead.substr(11, 3) == siteName) while (lookahead.substr(0, 6) == type and lookahead.substr(11, 3) == siteName)
{ {
std::string s = lookahead.substr(18); std::string s = lookahead.substr(18);
ba::trim_right(s); cif::trim_right(s);
s += std::string(11 - (s.length() % 11), ' '); s += std::string(11 - (s.length() % 11), ' ');
value += s; value += s;
// TODO: improve this... either use numRes or don't lump together all text // TODO: improve this... either use numRes or don't lump together all text
// value += " " + ba::trim_right_copy(); // value += " " + cif::trim_right_copy();
getline(is, lookahead); getline(is, lookahead);
++lineNr; ++lineNr;
} }
...@@ -1364,10 +1363,10 @@ void PDBFileParser::PreParseInput(std::istream &is) ...@@ -1364,10 +1363,10 @@ void PDBFileParser::PreParseInput(std::istream &is)
std::string k = value.substr(4, i - 4); std::string k = value.substr(4, i - 4);
std::string v = value.substr(i + 1); std::string v = value.substr(i + 1);
ba::trim(k); cif::trim(k);
while (k.find(" ") != std::string::npos) while (k.find(" ") != std::string::npos)
ba::replace_all(k, " ", " "); cif::replace_all(k, " ", " ");
ba::trim(v); cif::trim(v);
if (iequals(v, "NONE") or iequals(v, "N/A") or iequals(v, "NAN")) if (iequals(v, "NONE") or iequals(v, "N/A") or iequals(v, "NAN"))
mRemark200[k] = "."; mRemark200[k] = ".";
...@@ -1386,7 +1385,7 @@ void PDBFileParser::PreParseInput(std::istream &is) ...@@ -1386,7 +1385,7 @@ void PDBFileParser::PreParseInput(std::istream &is)
last = cur; last = cur;
ba::trim(type); cif::trim(type);
if (type == "LINK" or type == "LINKR") if (type == "LINK" or type == "LINKR")
{ {
...@@ -1421,7 +1420,7 @@ void PDBFileParser::PreParseInput(std::istream &is) ...@@ -1421,7 +1420,7 @@ void PDBFileParser::PreParseInput(std::istream &is)
if (not dropped.empty()) if (not dropped.empty())
{ {
if (cif::VERBOSE >= 0) if (cif::VERBOSE >= 0)
std::cerr << "Dropped unsupported records: " << ba::join(dropped, ", ") << std::endl; std::cerr << "Dropped unsupported records: " << cif::join(dropped, ", ") << std::endl;
} }
if (mData == nullptr) if (mData == nullptr)
...@@ -1456,10 +1455,9 @@ void PDBFileParser::Match(const std::string &expected, bool throwIfMissing) ...@@ -1456,10 +1455,9 @@ void PDBFileParser::Match(const std::string &expected, bool throwIfMissing)
std::vector<std::string> PDBFileParser::SplitCSV(const std::string &value) std::vector<std::string> PDBFileParser::SplitCSV(const std::string &value)
{ {
std::vector<std::string> vs; auto vs = cif::split<std::string>(value, ",");
ba::split(vs, value, ba::is_any_of(","));
for (auto &v : vs) for (auto &v : vs)
ba::trim(v); cif::trim(v);
return vs; return vs;
} }
...@@ -1484,12 +1482,12 @@ void PDBFileParser::ParseTitle() ...@@ -1484,12 +1482,12 @@ void PDBFileParser::ParseTitle()
keywords = vS(11, 50); keywords = vS(11, 50);
mOriginalDate = pdb2cifDate(vS(51, 59)); mOriginalDate = pdb2cifDate(vS(51, 59));
ba::trim(keywords); cif::trim(keywords);
GetNextRecord(); GetNextRecord();
} }
ba::trim(mStructureID); cif::trim(mStructureID);
if (mStructureID.empty()) if (mStructureID.empty())
mStructureID = "nohd"; mStructureID = "nohd";
...@@ -1514,12 +1512,12 @@ void PDBFileParser::ParseTitle() ...@@ -1514,12 +1512,12 @@ void PDBFileParser::ParseTitle()
cat = getCategory("pdbx_database_PDB_obs"); cat = getCategory("pdbx_database_PDB_obs");
std::string value = mRec->vS(32); std::string value = mRec->vS(32);
for (auto i = make_split_iterator(value, ba::token_finder(ba::is_any_of(" "), ba::token_compress_on)); not i.eof(); ++i) for (auto i : cif::split<std::string>(value, " ", true))
{ {
cat->emplace({{"id", "OBSLTE"}, cat->emplace({{"id", "OBSLTE"},
{"date", date}, {"date", date},
{"replace_pdb_id", old}, {"replace_pdb_id", old},
{"pdb_id", std::string(i->begin(), i->end())}}); {"pdb_id", i}});
} }
GetNextRecord(); GetNextRecord();
...@@ -1596,12 +1594,9 @@ void PDBFileParser::ParseTitle() ...@@ -1596,12 +1594,9 @@ void PDBFileParser::ParseTitle()
} }
else if (key == "CHAIN") else if (key == "CHAIN")
{ {
std::vector<std::string> chains; for (auto c : cif::split<std::string>(val, ","))
ba::split(chains, val, ba::is_any_of(","));
for (auto &c : chains)
{ {
ba::trim(c); cif::trim(c);
mCompounds.back().mChains.insert(c[0]); mCompounds.back().mChains.insert(c[0]);
} }
} }
...@@ -1698,16 +1693,14 @@ void PDBFileParser::ParseTitle() ...@@ -1698,16 +1693,14 @@ void PDBFileParser::ParseTitle()
cat = getCategory("exptl"); cat = getCategory("exptl");
std::vector<std::string> crystals; auto crystals = cif::split<std::string>(mRemark200["NUMBER OF CRYSTALS USED"], "; ");
ba::split(crystals, mRemark200["NUMBER OF CRYSTALS USED"], ba::is_any_of("; "));
if (crystals.empty()) if (crystals.empty())
crystals.push_back(""); crystals.push_back("");
auto ci = crystals.begin(); auto ci = crystals.begin();
for (auto si = ba::make_split_iterator(mExpMethod, ba::token_finder(ba::is_any_of(";"), ba::token_compress_on)); not si.eof(); ++si, ++ci) for (auto expMethod : cif::split<std::string>(mExpMethod, ";"))
{ {
std::string expMethod(si->begin(), si->end()); cif::trim(expMethod);
ba::trim(expMethod);
if (expMethod.empty()) if (expMethod.empty())
continue; continue;
...@@ -1743,10 +1736,8 @@ void PDBFileParser::ParseTitle() ...@@ -1743,10 +1736,8 @@ void PDBFileParser::ParseTitle()
cat = getCategory("audit_author"); cat = getCategory("audit_author");
value = {mRec->vS(11)}; value = {mRec->vS(11)};
for (auto si = ba::make_split_iterator(value, ba::token_finder(ba::is_any_of(","), ba::token_compress_on)); not si.eof(); ++si) for (auto author : cif::split<std::string>(value, ",", true))
{ {
std::string author(si->begin(), si->end());
cat->emplace({{"name", pdb2cifAuth(author)}, cat->emplace({{"name", pdb2cifAuth(author)},
{"pdbx_ordinal", n}}); {"pdbx_ordinal", n}});
++n; ++n;
...@@ -1788,7 +1779,7 @@ void PDBFileParser::ParseTitle() ...@@ -1788,7 +1779,7 @@ void PDBFileParser::ParseTitle()
revdats.push_back({revNum, date, modType == 0 ? mOriginalDate : "", modID, modType}); revdats.push_back({revNum, date, modType == 0 ? mOriginalDate : "", modID, modType});
ba::split(revdats.back().types, detail, ba::is_any_of(" ")); revdats.back().types = cif::split<std::string>(detail, " ");
if (firstRevDat) if (firstRevDat)
{ {
...@@ -1849,7 +1840,7 @@ void PDBFileParser::ParseCitation(const std::string &id) ...@@ -1849,7 +1840,7 @@ void PDBFileParser::ParseCitation(const std::string &id)
{ {
if (not s.empty()) if (not s.empty())
s += ' '; s += ' ';
s += ba::trim_copy(p); s += cif::trim_copy(p);
}; };
while (mRec->is(rec) and (id == "primary" or vC(12) == ' ')) while (mRec->is(rec) and (id == "primary" or vC(12) == ' '))
...@@ -1867,7 +1858,7 @@ void PDBFileParser::ParseCitation(const std::string &id) ...@@ -1867,7 +1858,7 @@ void PDBFileParser::ParseCitation(const std::string &id)
{ {
extend(pubname, vS(20, 47)); extend(pubname, vS(20, 47));
if (vS(50, 51) == "V.") if (vS(50, 51) == "V.")
volume = ba::trim_copy(vS(52, 55)); volume = cif::trim_copy(vS(52, 55));
pageFirst = vS(57, 61); pageFirst = vS(57, 61);
year = vI(63, 66); year = vI(63, 66);
} }
...@@ -1910,10 +1901,8 @@ void PDBFileParser::ParseCitation(const std::string &id) ...@@ -1910,10 +1901,8 @@ void PDBFileParser::ParseCitation(const std::string &id)
if (not auth.empty()) if (not auth.empty())
{ {
cat = getCategory("citation_author"); cat = getCategory("citation_author");
for (auto si = ba::make_split_iterator(auth, ba::token_finder(ba::is_any_of(","), ba::token_compress_on)); not si.eof(); ++si) for (auto author : cif::split<std::string>(auth, ",", true))
{ {
std::string author(si->begin(), si->end());
cat->emplace({{"citation_id", id}, cat->emplace({{"citation_id", id},
{"name", pdb2cifAuth(author)}, {"name", pdb2cifAuth(author)},
{"ordinal", mCitationAuthorNr}}); {"ordinal", mCitationAuthorNr}});
...@@ -1925,10 +1914,8 @@ void PDBFileParser::ParseCitation(const std::string &id) ...@@ -1925,10 +1914,8 @@ void PDBFileParser::ParseCitation(const std::string &id)
if (not edit.empty()) if (not edit.empty())
{ {
cat = getCategory("citation_editor"); cat = getCategory("citation_editor");
for (auto si = ba::make_split_iterator(edit, ba::token_finder(ba::is_any_of(","), ba::token_compress_on)); not si.eof(); ++si) for (auto editor : cif::split<std::string>(edit, ",", true))
{ {
std::string editor(si->begin(), si->end());
cat->emplace({{"citation_id", id}, cat->emplace({{"citation_id", id},
{"name", pdb2cifAuth(editor)}, {"name", pdb2cifAuth(editor)},
{"ordinal", mCitationEditorNr}}); {"ordinal", mCitationEditorNr}});
...@@ -1942,7 +1929,7 @@ void PDBFileParser::ParseRemarks() ...@@ -1942,7 +1929,7 @@ void PDBFileParser::ParseRemarks()
{ {
std::string sequenceDetails, compoundDetails, sourceDetails; std::string sequenceDetails, compoundDetails, sourceDetails;
while (ba::starts_with(mRec->mName, "REMARK")) while (cif::starts_with(mRec->mName, "REMARK"))
{ {
int remarkNr = vI(8, 10); int remarkNr = vI(8, 10);
...@@ -2004,7 +1991,7 @@ void PDBFileParser::ParseRemarks() ...@@ -2004,7 +1991,7 @@ void PDBFileParser::ParseRemarks()
{ {
std::string r = mRec->vS(12); std::string r = mRec->vS(12);
if (ba::starts_with(r, "REMARK: ")) if (cif::starts_with(r, "REMARK: "))
{ {
mRemark200["REMARK"] = r.substr(8); mRemark200["REMARK"] = r.substr(8);
remark = true; remark = true;
...@@ -2041,7 +2028,7 @@ void PDBFileParser::ParseRemarks() ...@@ -2041,7 +2028,7 @@ void PDBFileParser::ParseRemarks()
densityPercentSol = m[1].str(); densityPercentSol = m[1].str();
else if (std::regex_match(r, m, rx2)) else if (std::regex_match(r, m, rx2))
density_Matthews = m[1].str(); density_Matthews = m[1].str();
else if (ba::starts_with(r, "CRYSTALLIZATION CONDITIONS: ")) else if (cif::starts_with(r, "CRYSTALLIZATION CONDITIONS: "))
conditions = r.substr(28); conditions = r.substr(28);
} }
else else
...@@ -2064,18 +2051,16 @@ void PDBFileParser::ParseRemarks() ...@@ -2064,18 +2051,16 @@ void PDBFileParser::ParseRemarks()
std::string temp, ph, method; std::string temp, ph, method;
for (auto i = make_split_iterator(conditions, ba::token_finder(ba::is_any_of(","), ba::token_compress_on)); not i.eof(); ++i) for (auto s : cif::split<std::string>(conditions, ",", true))
{ {
std::string s(i->begin(), i->end()); cif::trim(s);
ba::trim(s);
if (std::regex_search(s, m, rx3)) if (std::regex_search(s, m, rx3))
temp = m[1].str(); temp = m[1].str();
if (std::regex_search(s, m, rx4)) if (std::regex_search(s, m, rx4))
ph = m[1].str(); ph = m[1].str();
if (s.length() < 60 and if (s.length() < 60 and
(ba::icontains(s, "drop") or ba::icontains(s, "vapor") or ba::icontains(s, "batch"))) (cif::icontains(s, "drop") or cif::icontains(s, "vapor") or cif::icontains(s, "batch")))
{ {
if (not method.empty()) if (not method.empty())
method = method + ", " + s; method = method + ", " + s;
...@@ -2159,7 +2144,7 @@ void PDBFileParser::ParseRemarks() ...@@ -2159,7 +2144,7 @@ void PDBFileParser::ParseRemarks()
models[1] = stoi(m[2].str()); models[1] = stoi(m[2].str());
} }
else else
headerSeen = ba::contains(line, "RES C SSSEQI"); headerSeen = cif::contains(line, "RES C SSSEQI");
continue; continue;
} }
...@@ -2197,7 +2182,7 @@ void PDBFileParser::ParseRemarks() ...@@ -2197,7 +2182,7 @@ void PDBFileParser::ParseRemarks()
models[1] = stoi(m[2].str()); models[1] = stoi(m[2].str());
} }
else else
headerSeen = ba::contains(line, "RES CSSEQI ATOMS"); headerSeen = cif::contains(line, "RES CSSEQI ATOMS");
continue; continue;
} }
...@@ -2209,10 +2194,8 @@ void PDBFileParser::ParseRemarks() ...@@ -2209,10 +2194,8 @@ void PDBFileParser::ParseRemarks()
int seq = vI(21, 24); int seq = vI(21, 24);
char iCode = vC(25); char iCode = vC(25);
std::vector<std::string> atoms;
std::string atomStr = mRec->vS(29); std::string atomStr = mRec->vS(29);
for (auto i = make_split_iterator(atomStr, ba::token_finder(ba::is_any_of(" "), ba::token_compress_on)); not i.eof(); ++i) auto atoms = cif::split<std::string>(atomStr, " ", true);
atoms.push_back({i->begin(), i->end()});
for (int modelNr = models[0]; modelNr <= models[1]; ++modelNr) for (int modelNr = models[0]; modelNr <= models[1]; ++modelNr)
mUnobs.push_back({modelNr, res, chain, seq, iCode, atoms}); mUnobs.push_back({modelNr, res, chain, seq, iCode, atoms});
...@@ -2252,7 +2235,7 @@ void PDBFileParser::ParseRemarks() ...@@ -2252,7 +2235,7 @@ void PDBFileParser::ParseRemarks()
{ {
case eStart: case eStart:
{ {
if (line.empty() or not ba::starts_with(line, "SUBTOPIC: ")) if (line.empty() or not cif::starts_with(line, "SUBTOPIC: "))
continue; continue;
std::string subtopic = line.substr(10); std::string subtopic = line.substr(10);
...@@ -2384,7 +2367,7 @@ void PDBFileParser::ParseRemarks() ...@@ -2384,7 +2367,7 @@ void PDBFileParser::ParseRemarks()
{ {
if (not headerSeen) if (not headerSeen)
{ {
if (ba::starts_with(line, "FORMAT: ") and line != "FORMAT: (10X,I3,1X,2(A3,1X,A1,I4,A1,1X,A4,3X),1X,F6.3)") if (cif::starts_with(line, "FORMAT: ") and line != "FORMAT: (10X,I3,1X,2(A3,1X,A1,I4,A1,1X,A4,3X),1X,F6.3)")
throw std::runtime_error("Unexpected format in REMARK 500"); throw std::runtime_error("Unexpected format in REMARK 500");
headerSeen = line == "M RES CSSEQI ATM1 RES CSSEQI ATM2 DEVIATION"; headerSeen = line == "M RES CSSEQI ATM1 RES CSSEQI ATM2 DEVIATION";
...@@ -2438,7 +2421,7 @@ void PDBFileParser::ParseRemarks() ...@@ -2438,7 +2421,7 @@ void PDBFileParser::ParseRemarks()
case eCBA: case eCBA:
if (not headerSeen) if (not headerSeen)
{ {
if (ba::starts_with(line, "FORMAT: ") and line != "FORMAT: (10X,I3,1X,A3,1X,A1,I4,A1,3(1X,A4,2X),12X,F5.1)") if (cif::starts_with(line, "FORMAT: ") and line != "FORMAT: (10X,I3,1X,A3,1X,A1,I4,A1,3(1X,A4,2X),12X,F5.1)")
throw std::runtime_error("Unexpected format in REMARK 500"); throw std::runtime_error("Unexpected format in REMARK 500");
headerSeen = line == "M RES CSSEQI ATM1 ATM2 ATM3"; headerSeen = line == "M RES CSSEQI ATM1 ATM2 ATM3";
...@@ -2486,7 +2469,7 @@ void PDBFileParser::ParseRemarks() ...@@ -2486,7 +2469,7 @@ void PDBFileParser::ParseRemarks()
case eTA: case eTA:
if (not headerSeen) if (not headerSeen)
{ {
if (ba::starts_with(line, "FORMAT: ") and line != "FORMAT:(10X,I3,1X,A3,1X,A1,I4,A1,4X,F7.2,3X,F7.2)") if (cif::starts_with(line, "FORMAT: ") and line != "FORMAT:(10X,I3,1X,A3,1X,A1,I4,A1,4X,F7.2,3X,F7.2)")
throw std::runtime_error("Unexpected format in REMARK 500"); throw std::runtime_error("Unexpected format in REMARK 500");
headerSeen = line == "M RES CSSEQI PSI PHI"; headerSeen = line == "M RES CSSEQI PSI PHI";
...@@ -2607,7 +2590,7 @@ void PDBFileParser::ParseRemarks() ...@@ -2607,7 +2590,7 @@ void PDBFileParser::ParseRemarks()
if (not headerSeen) if (not headerSeen)
{ {
std::string line = vS(12); std::string line = vS(12);
headerSeen = ba::contains(line, "RES C SSEQI"); headerSeen = cif::contains(line, "RES C SSEQI");
continue; continue;
} }
...@@ -2818,20 +2801,17 @@ void PDBFileParser::ParseRemark200() ...@@ -2818,20 +2801,17 @@ void PDBFileParser::ParseRemark200()
int nr = 0; int nr = 0;
std::string result; std::string result;
for (auto i = make_split_iterator(mRemark200[name], for (auto s : cif::split<std::string>(mRemark200[name], ";"))
ba::token_finder(ba::is_any_of(";"), ba::token_compress_off));
not i.eof(); ++i)
{ {
if (++nr != diffrnNr) if (++nr != diffrnNr)
continue; continue;
result.assign(i->begin(), i->end()); cif::trim(s);
;
ba::trim(result);
if (result == "NULL") if (s == "NULL")
result.clear(); s.clear();
result = std::move(s);
break; break;
} }
...@@ -2903,7 +2883,7 @@ void PDBFileParser::ParseRemark200() ...@@ -2903,7 +2883,7 @@ void PDBFileParser::ParseRemark200()
if (ambientTemp.empty()) if (ambientTemp.empty())
break; break;
if (ba::ends_with(ambientTemp, "K")) if (cif::ends_with(ambientTemp, "K"))
ambientTemp.erase(ambientTemp.length() - 1, 1); ambientTemp.erase(ambientTemp.length() - 1, 1);
getCategory("diffrn")->emplace({{"id", diffrnNr}, getCategory("diffrn")->emplace({{"id", diffrnNr},
...@@ -2938,9 +2918,8 @@ void PDBFileParser::ParseRemark200() ...@@ -2938,9 +2918,8 @@ void PDBFileParser::ParseRemark200()
{"pdbx_diffrn_protocol", rm200("DIFFRACTION PROTOCOL", diffrnNr)}, {"pdbx_diffrn_protocol", rm200("DIFFRACTION PROTOCOL", diffrnNr)},
{"pdbx_scattering_type", scatteringType}}); {"pdbx_scattering_type", scatteringType}});
std::vector<std::string> wavelengths;
std::string wl = rm200("WAVELENGTH OR RANGE (A)", diffrnNr); std::string wl = rm200("WAVELENGTH OR RANGE (A)", diffrnNr);
ba::split(wavelengths, wl, ba::is_any_of(", -"), ba::token_compress_on); auto wavelengths = cif::split<std::string>(wl, ", -", true);
diffrnWaveLengths.insert(wavelengths.begin(), wavelengths.end()); diffrnWaveLengths.insert(wavelengths.begin(), wavelengths.end());
...@@ -2955,7 +2934,7 @@ void PDBFileParser::ParseRemark200() ...@@ -2955,7 +2934,7 @@ void PDBFileParser::ParseRemark200()
{"pdbx_synchrotron_beamline", rm200("BEAMLINE", diffrnNr)}, {"pdbx_synchrotron_beamline", rm200("BEAMLINE", diffrnNr)},
{"pdbx_wavelength", wavelengths.size() == 1 ? wavelengths[0] : ""}, {"pdbx_wavelength", wavelengths.size() == 1 ? wavelengths[0] : ""},
{"pdbx_wavelength_list", wavelengths.size() == 1 ? "" : ba::join(wavelengths, ", ")}, {"pdbx_wavelength_list", wavelengths.size() == 1 ? "" : cif::join(wavelengths, ", ")},
}); });
} }
else if (inRM200({"X-RAY GENERATOR MODEL", "RADIATION SOURCE", "BEAMLINE", "WAVELENGTH OR RANGE (A)"})) else if (inRM200({"X-RAY GENERATOR MODEL", "RADIATION SOURCE", "BEAMLINE", "WAVELENGTH OR RANGE (A)"}))
...@@ -2966,7 +2945,7 @@ void PDBFileParser::ParseRemark200() ...@@ -2966,7 +2945,7 @@ void PDBFileParser::ParseRemark200()
{"type", rm200("X-RAY GENERATOR MODEL", diffrnNr)}, {"type", rm200("X-RAY GENERATOR MODEL", diffrnNr)},
{"pdbx_wavelength", wavelengths.size() == 1 ? wavelengths[0] : ""}, {"pdbx_wavelength", wavelengths.size() == 1 ? wavelengths[0] : ""},
{"pdbx_wavelength_list", wavelengths.size() == 1 ? "" : ba::join(wavelengths, ", ")}, {"pdbx_wavelength_list", wavelengths.size() == 1 ? "" : cif::join(wavelengths, ", ")},
}); });
} }
} }
...@@ -2974,7 +2953,7 @@ void PDBFileParser::ParseRemark200() ...@@ -2974,7 +2953,7 @@ void PDBFileParser::ParseRemark200()
int wavelengthNr = 1; int wavelengthNr = 1;
for (auto wl : diffrnWaveLengths) for (auto wl : diffrnWaveLengths)
{ {
if (ba::ends_with(wl, "A")) if (cif::ends_with(wl, "A"))
wl.erase(wl.length() - 1, 1); wl.erase(wl.length() - 1, 1);
getCategory("diffrn_radiation_wavelength")->emplace({{"id", wavelengthNr++}, getCategory("diffrn_radiation_wavelength")->emplace({{"id", wavelengthNr++},
...@@ -3090,12 +3069,8 @@ void PDBFileParser::ParseRemark350() ...@@ -3090,12 +3069,8 @@ void PDBFileParser::ParseRemark350()
std::string value = m[1].str(); std::string value = m[1].str();
for (auto i = make_split_iterator(value, for (auto chain : cif::split<std::string>(value, ", ", true))
ba::token_finder(ba::is_any_of(", "), ba::token_compress_on));
not i.eof(); ++i)
{ {
std::string chain = boost::copy_range<std::string>(*i);
if (chain.empty()) // happens when we have a AND CHAIN line if (chain.empty()) // happens when we have a AND CHAIN line
{ {
state = eAnd; state = eAnd;
...@@ -3118,12 +3093,9 @@ void PDBFileParser::ParseRemark350() ...@@ -3118,12 +3093,9 @@ void PDBFileParser::ParseRemark350()
state = eApply; state = eApply;
std::string value = m[1].str(); std::string value = m[1].str();
for (auto i = make_split_iterator(value,
ba::token_finder(ba::is_any_of(", "), ba::token_compress_on));
not i.eof(); ++i)
{
std::string chain = boost::copy_range<std::string>(*i);
for (auto chain : cif::split<std::string>(value, ", ", true))
{
if (chain.empty()) // happens when we have another AND CHAIN line if (chain.empty()) // happens when we have another AND CHAIN line
{ {
state = eAnd; state = eAnd;
...@@ -3183,7 +3155,7 @@ void PDBFileParser::ParseRemark350() ...@@ -3183,7 +3155,7 @@ void PDBFileParser::ParseRemark350()
std::string oligomer = values["AUTHOR DETERMINED BIOLOGICAL UNIT"]; std::string oligomer = values["AUTHOR DETERMINED BIOLOGICAL UNIT"];
if (oligomer.empty()) if (oligomer.empty())
oligomer = values["SOFTWARE DETERMINED QUATERNARY STRUCTURE"]; oligomer = values["SOFTWARE DETERMINED QUATERNARY STRUCTURE"];
ba::to_lower(oligomer); toLower(oligomer);
int count = 0; int count = 0;
std::smatch m2; std::smatch m2;
...@@ -3192,7 +3164,7 @@ void PDBFileParser::ParseRemark350() ...@@ -3192,7 +3164,7 @@ void PDBFileParser::ParseRemark350()
{ {
count = stoi(m2[1].str()); count = stoi(m2[1].str());
} }
else if (ba::ends_with(oligomer, "meric")) else if (cif::ends_with(oligomer, "meric"))
{ {
std::string cs = oligomer.substr(0, oligomer.length() - 5); std::string cs = oligomer.substr(0, oligomer.length() - 5);
if (cs == "mono") if (cs == "mono")
...@@ -3278,8 +3250,8 @@ void PDBFileParser::ParseRemark350() ...@@ -3278,8 +3250,8 @@ void PDBFileParser::ParseRemark350()
throw std::runtime_error("Invalid REMARK 350"); throw std::runtime_error("Invalid REMARK 350");
getCategory("pdbx_struct_assembly_gen")->emplace({{"assembly_id", biomolecule}, getCategory("pdbx_struct_assembly_gen")->emplace({{"assembly_id", biomolecule},
{"oper_expression", ba::join(operExpression, ",")}, {"oper_expression", cif::join(operExpression, ",")},
{"asym_id_list", ba::join(asymIdList, ",")}}); {"asym_id_list", cif::join(asymIdList, ",")}});
biomolecule = stoi(m[1].str()); biomolecule = stoi(m[1].str());
asymIdList.clear(); asymIdList.clear();
...@@ -3294,8 +3266,8 @@ void PDBFileParser::ParseRemark350() ...@@ -3294,8 +3266,8 @@ void PDBFileParser::ParseRemark350()
if (not operExpression.empty()) if (not operExpression.empty())
{ {
getCategory("pdbx_struct_assembly_gen")->emplace({{"assembly_id", biomolecule}, getCategory("pdbx_struct_assembly_gen")->emplace({{"assembly_id", biomolecule},
{"oper_expression", ba::join(operExpression, ",")}, {"oper_expression", cif::join(operExpression, ",")},
{"asym_id_list", ba::join(asymIdList, ",")}}); {"asym_id_list", cif::join(asymIdList, ",")}});
} }
mRec = saved; mRec = saved;
...@@ -3306,7 +3278,7 @@ void PDBFileParser::ParsePrimaryStructure() ...@@ -3306,7 +3278,7 @@ void PDBFileParser::ParsePrimaryStructure()
// First locate the DBREF record. Might be missing // First locate the DBREF record. Might be missing
DBREF cur = {mStructureID}; DBREF cur = {mStructureID};
while (ba::starts_with(mRec->mName, "DBREF")) while (cif::starts_with(mRec->mName, "DBREF"))
{ {
if (mRec->is("DBREF ")) // 1 - 6 Record name "DBREF " if (mRec->is("DBREF ")) // 1 - 6 Record name "DBREF "
{ {
...@@ -3405,9 +3377,8 @@ void PDBFileParser::ParsePrimaryStructure() ...@@ -3405,9 +3377,8 @@ void PDBFileParser::ParsePrimaryStructure()
auto &chain = GetChainForID(chainID, numRes); auto &chain = GetChainForID(chainID, numRes);
for (auto si = ba::make_split_iterator(monomers, ba::token_finder(ba::is_any_of(" "), ba::token_compress_on)); not si.eof(); ++si) for (auto monID : cif::split<std::string>(monomers, " ", true))
{ {
std::string monID(si->begin(), si->end());
if (monID.empty()) if (monID.empty())
continue; continue;
...@@ -4159,7 +4130,7 @@ void PDBFileParser::ConstructEntities() ...@@ -4159,7 +4130,7 @@ void PDBFileParser::ConstructEntities()
{"pdbx_seq_one_letter_code", seq}, {"pdbx_seq_one_letter_code", seq},
{"pdbx_seq_one_letter_code_can", seqCan}, {"pdbx_seq_one_letter_code_can", seqCan},
{"nstd_monomer", (nstdMonomer ? "yes" : "no")}, {"nstd_monomer", (nstdMonomer ? "yes" : "no")},
{"pdbx_strand_id", ba::join(chains, ",")}, {"pdbx_strand_id", cif::join(chains, ",")},
{"nstd_linkage", nonstandardLinkage ? "yes" : "no"}, {"nstd_linkage", nonstandardLinkage ? "yes" : "no"},
{"type", type}}); {"type", type}});
} }
...@@ -4168,8 +4139,8 @@ void PDBFileParser::ConstructEntities() ...@@ -4168,8 +4139,8 @@ void PDBFileParser::ConstructEntities()
{ {
getCategory("struct")->emplace({ getCategory("struct")->emplace({
{"entry_id", mStructureID}, {"entry_id", mStructureID},
{"title", ba::join(structTitle, ", ")}, {"title", cif::join(structTitle, ", ")},
{"pdbx_descriptor", ba::join(structDescription, ", ")}, {"pdbx_descriptor", cif::join(structDescription, ", ")},
{"pdbx_model_type_details", mModelTypeDetails} {"pdbx_model_type_details", mModelTypeDetails}
}); });
} }
...@@ -4308,7 +4279,7 @@ void PDBFileParser::ConstructEntities() ...@@ -4308,7 +4279,7 @@ void PDBFileParser::ConstructEntities()
int seqNr = ++ndbSeqNum[std::make_tuple(hetID, asymID)]; int seqNr = ++ndbSeqNum[std::make_tuple(hetID, asymID)];
std::string iCode{het.iCode}; std::string iCode{het.iCode};
ba::trim(iCode); cif::trim(iCode);
if (iCode.empty()) if (iCode.empty())
iCode = {'.'}; iCode = {'.'};
...@@ -4622,7 +4593,7 @@ void PDBFileParser::ConstructSugarTrees(int &asymNr) ...@@ -4622,7 +4593,7 @@ void PDBFileParser::ConstructSugarTrees(int &asymNr)
}); });
std::string iCode{si->iCode}; std::string iCode{si->iCode};
ba::trim(iCode); cif::trim(iCode);
if (iCode.empty()) if (iCode.empty())
iCode = {'.'}; iCode = {'.'};
...@@ -4793,7 +4764,7 @@ void PDBFileParser::ParseSecondaryStructure() ...@@ -4793,7 +4764,7 @@ void PDBFileParser::ParseSecondaryStructure()
// 70 AChar prevICode Registration. Insertion code in // 70 AChar prevICode Registration. Insertion code in
// previous strand. // previous strand.
std::string sheetID = ba::trim_copy(vS(12, 14)); std::string sheetID = cif::trim_copy(vS(12, 14));
if (sheetsSeen.count(sheetID) == 0) if (sheetsSeen.count(sheetID) == 0)
{ {
sheetsSeen.insert(sheetID); sheetsSeen.insert(sheetID);
...@@ -5317,7 +5288,7 @@ void PDBFileParser::ParseCoordinateTransformation() ...@@ -5317,7 +5288,7 @@ void PDBFileParser::ParseCoordinateTransformation()
{ {
std::string m[3][3], v[3]; std::string m[3][3], v[3];
if (ba::starts_with(mRec->mName, "ORIGX")) if (cif::starts_with(mRec->mName, "ORIGX"))
{ {
for (std::string n : {"1", "2", "3"}) for (std::string n : {"1", "2", "3"})
{ {
...@@ -5349,7 +5320,7 @@ void PDBFileParser::ParseCoordinateTransformation() ...@@ -5349,7 +5320,7 @@ void PDBFileParser::ParseCoordinateTransformation()
}); });
} }
if (ba::starts_with(mRec->mName, "SCALE")) if (cif::starts_with(mRec->mName, "SCALE"))
{ {
for (std::string n : {"1", "2", "3"}) for (std::string n : {"1", "2", "3"})
{ {
...@@ -5381,7 +5352,7 @@ void PDBFileParser::ParseCoordinateTransformation() ...@@ -5381,7 +5352,7 @@ void PDBFileParser::ParseCoordinateTransformation()
}); });
} }
while (ba::starts_with(mRec->mName, "MTRIX1")) while (cif::starts_with(mRec->mName, "MTRIX1"))
{ {
int serial = 0, igiven = 0; int serial = 0, igiven = 0;
......
src/PDB2CifRemark3.cpp
...@@ -29,7 +29,6 @@ ...@@ -29,7 +29,6 @@
#include <map> #include <map>
#include <set> #include <set>
#include <boost/algorithm/string.hpp>
#include <boost/format.hpp> #include <boost/format.hpp>
#include <cif++/AtomType.hpp> #include <cif++/AtomType.hpp>
...@@ -37,8 +36,6 @@ ...@@ -37,8 +36,6 @@
#include <cif++/PDB2CifRemark3.hpp> #include <cif++/PDB2CifRemark3.hpp>
#include <cif++/CifUtils.hpp> #include <cif++/CifUtils.hpp>
namespace ba = boost::algorithm;
using cif::Datablock; using cif::Datablock;
using cif::Category; using cif::Category;
using cif::Row; using cif::Row;
...@@ -992,7 +989,7 @@ std::string Remark3Parser::nextLine() ...@@ -992,7 +989,7 @@ std::string Remark3Parser::nextLine()
while (mRec->is("REMARK 3") and mRec->mVlen > valueIndent) while (mRec->is("REMARK 3") and mRec->mVlen > valueIndent)
{ {
std::string v(mRec->mValue + 4, mRec->mValue + mRec->mVlen); std::string v(mRec->mValue + 4, mRec->mValue + mRec->mVlen);
if (not ba::starts_with(v, indent)) if (not cif::starts_with(v, indent))
break; break;
mLine += ' '; mLine += ' ';
...@@ -1146,7 +1143,7 @@ void Remark3Parser::storeCapture(const char* category, std::initializer_list<con ...@@ -1146,7 +1143,7 @@ void Remark3Parser::storeCapture(const char* category, std::initializer_list<con
++capture; ++capture;
std::string value = mM[capture].str(); std::string value = mM[capture].str();
ba::trim(value); cif::trim(value);
if (iequals(value, "NULL") or iequals(value, "NONE") or iequals(value, "Inf") or iequals(value, "+Inf") or iequals(value, std::string(value.length(), '*'))) if (iequals(value, "NULL") or iequals(value, "NONE") or iequals(value, "Inf") or iequals(value, "+Inf") or iequals(value, std::string(value.length(), '*')))
continue; continue;
...@@ -1253,7 +1250,7 @@ void Remark3Parser::storeRefineLsRestr(const char* type, std::initializer_list<c ...@@ -1253,7 +1250,7 @@ void Remark3Parser::storeRefineLsRestr(const char* type, std::initializer_list<c
++capture; ++capture;
std::string value = mM[capture].str(); std::string value = mM[capture].str();
ba::trim(value); cif::trim(value);
if (value.empty() or iequals(value, "NULL") or iequals(value, "Inf") or iequals(value, "+Inf") or iequals(value, std::string(value.length(), '*'))) if (value.empty() or iequals(value, "NULL") or iequals(value, "Inf") or iequals(value, "+Inf") or iequals(value, std::string(value.length(), '*')))
continue; continue;
...@@ -1284,7 +1281,7 @@ void Remark3Parser::updateRefineLsRestr(const char* type, std::initializer_list< ...@@ -1284,7 +1281,7 @@ void Remark3Parser::updateRefineLsRestr(const char* type, std::initializer_list<
++capture; ++capture;
std::string value = mM[capture].str(); std::string value = mM[capture].str();
ba::trim(value); cif::trim(value);
if (iequals(value, "NULL") or iequals(value, std::string(value.length(), '*'))) if (iequals(value, "NULL") or iequals(value, std::string(value.length(), '*')))
value.clear(); value.clear();
...@@ -1385,32 +1382,29 @@ bool Remark3Parser::parse(const std::string& expMethod, PDBRecord* r, cif::Datab ...@@ -1385,32 +1382,29 @@ bool Remark3Parser::parse(const std::string& expMethod, PDBRecord* r, cif::Datab
} }
}; };
for (auto p = make_split_iterator(line, ba::first_finder(", ")); for (auto program : cif::split<std::string>(line, ", ", true))
not p.eof(); ++p)
{ {
std::string program(p->begin(), p->end()); if (cif::starts_with(program, "BUSTER"))
if (ba::starts_with(program, "BUSTER"))
tryParser(new BUSTER_TNT_Remark3Parser(program, expMethod, r, db)); tryParser(new BUSTER_TNT_Remark3Parser(program, expMethod, r, db));
else if (ba::starts_with(program, "CNS") or ba::starts_with(program, "CNX")) else if (cif::starts_with(program, "CNS") or cif::starts_with(program, "CNX"))
tryParser(new CNS_Remark3Parser(program, expMethod, r, db)); tryParser(new CNS_Remark3Parser(program, expMethod, r, db));
else if (ba::starts_with(program, "PHENIX")) else if (cif::starts_with(program, "PHENIX"))
tryParser(new PHENIX_Remark3Parser(program, expMethod, r, db)); tryParser(new PHENIX_Remark3Parser(program, expMethod, r, db));
else if (ba::starts_with(program, "NUCLSQ")) else if (cif::starts_with(program, "NUCLSQ"))
tryParser(new NUCLSQ_Remark3Parser(program, expMethod, r, db)); tryParser(new NUCLSQ_Remark3Parser(program, expMethod, r, db));
else if (ba::starts_with(program, "PROLSQ")) else if (cif::starts_with(program, "PROLSQ"))
tryParser(new PROLSQ_Remark3Parser(program, expMethod, r, db)); tryParser(new PROLSQ_Remark3Parser(program, expMethod, r, db));
else if (ba::starts_with(program, "REFMAC")) else if (cif::starts_with(program, "REFMAC"))
{ {
// simply try both and take the best // simply try both and take the best
tryParser(new REFMAC_Remark3Parser(program, expMethod, r, db)); tryParser(new REFMAC_Remark3Parser(program, expMethod, r, db));
tryParser(new REFMAC5_Remark3Parser(program, expMethod, r, db)); tryParser(new REFMAC5_Remark3Parser(program, expMethod, r, db));
} }
else if (ba::starts_with(program, "SHELXL")) else if (cif::starts_with(program, "SHELXL"))
tryParser(new SHELXL_Remark3Parser(program, expMethod, r, db)); tryParser(new SHELXL_Remark3Parser(program, expMethod, r, db));
else if (ba::starts_with(program, "TNT")) else if (cif::starts_with(program, "TNT"))
tryParser(new TNT_Remark3Parser(program, expMethod, r, db)); tryParser(new TNT_Remark3Parser(program, expMethod, r, db));
else if (ba::starts_with(program, "X-PLOR")) else if (cif::starts_with(program, "X-PLOR"))
tryParser(new XPLOR_Remark3Parser(program, expMethod, r, db)); tryParser(new XPLOR_Remark3Parser(program, expMethod, r, db));
else if (cif::VERBOSE > 0) else if (cif::VERBOSE > 0)
std::cerr << "Skipping unknown program (" << program << ") in REMARK 3" << std::endl; std::cerr << "Skipping unknown program (" << program << ") in REMARK 3" << std::endl;
......
src/Secondary.cpp
...@@ -30,13 +30,9 @@ ...@@ -30,13 +30,9 @@
#include <numeric> #include <numeric>
#include <thread> #include <thread>
#include <boost/algorithm/string.hpp>
#include <cif++/Secondary.hpp> #include <cif++/Secondary.hpp>
#include <cif++/Structure.hpp> #include <cif++/Structure.hpp>
namespace ba = boost::algorithm;
// -------------------------------------------------------------------- // --------------------------------------------------------------------
namespace mmcif namespace mmcif
...@@ -106,7 +102,7 @@ const ResidueInfo kResidueInfo[] = { ...@@ -106,7 +102,7 @@ const ResidueInfo kResidueInfo[] = {
ResidueType MapResidue(std::string inName) ResidueType MapResidue(std::string inName)
{ {
ba::trim(inName); cif::trim(inName);
ResidueType result = kUnknownResidue; ResidueType result = kUnknownResidue;
......
src/Structure.cpp
...@@ -31,9 +31,7 @@ ...@@ -31,9 +31,7 @@
#include <iomanip> #include <iomanip>
#include <numeric> #include <numeric>
#include <boost/algorithm/string.hpp> #include <gzstream/gzstream.hpp>
#include <boost/iostreams/filter/gzip.hpp>
#include <boost/iostreams/filtering_stream.hpp>
#if __cpp_lib_format #if __cpp_lib_format
#include <format> #include <format>
...@@ -47,8 +45,6 @@ ...@@ -47,8 +45,6 @@
// #include <cif++/AtomShape.hpp> // #include <cif++/AtomShape.hpp>
namespace fs = std::filesystem; namespace fs = std::filesystem;
namespace ba = boost::algorithm;
namespace io = boost::iostreams;
extern int cif::VERBOSE; extern int cif::VERBOSE;
...@@ -1289,81 +1285,27 @@ float Branch::weight() const ...@@ -1289,81 +1285,27 @@ float Branch::weight() const
void File::load(const std::filesystem::path &path) void File::load(const std::filesystem::path &path)
{ {
std::ifstream inFile(path, std::ios_base::in | std::ios_base::binary);
if (not inFile.is_open())
throw std::runtime_error("No such file: " + path.string());
io::filtering_stream<io::input> in;
std::string ext = path.extension().string(); std::string ext = path.extension().string();
if (path.extension() == ".gz") if (ext == ".gz")
{ {
in.push(io::gzip_decompressor()); gzstream::ifstream in(path);
ext = path.stem().extension().string();
}
in.push(inFile); ext = path.stem().extension().string();
try if (ext == ".pdb" or ext == ".ent")
{
// OK, we've got the file, now create a protein
if (ext == ".cif")
load(in);
else if (ext == ".pdb" or ext == ".ent")
ReadPDBFile(in, *this); ReadPDBFile(in, *this);
else else
{
try
{
if (cif::VERBOSE > 0)
std::cerr << "unrecognized file extension, trying cif" << std::endl;
cif::File::load(in); cif::File::load(in);
} }
catch (const cif::CifParserError &e)
{
if (cif::VERBOSE > 0)
std::cerr << "Not cif, trying plain old PDB" << std::endl;
// pffft...
in.reset();
if (inFile.is_open())
inFile.seekg(0);
else else
inFile.open(path, std::ios_base::in | std::ios::binary);
if (path.extension() == ".gz")
in.push(io::gzip_decompressor());
in.push(inFile);
ReadPDBFile(in, *this);
}
}
}
catch (const std::exception &ex)
{ {
if (cif::VERBOSE >= 0) std::ifstream in(path, std::ios_base::binary);
std::cerr << "Error trying to load file " << path << std::endl;
throw;
}
// validate, otherwise lots of functionality won't work
loadDictionary("mmcif_pdbx_v50");
if (not isValid() and cif::VERBOSE >= 0)
std::cerr << "Invalid mmCIF file" << (cif::VERBOSE > 0 ? "." : " use --verbose option to see errors") << std::endl;
}
void File::load(std::istream &is) if (ext == ".pdb" or ext == ".ent")
{ ReadPDBFile(in, *this);
try else
{ cif::File::load(in);
cif::File::load(is);
}
catch (const cif::CifParserError &e)
{
ReadPDBFile(is, *this);
} }
// validate, otherwise lots of functionality won't work // validate, otherwise lots of functionality won't work
...@@ -1376,21 +1318,20 @@ void File::save(const std::filesystem::path &path) ...@@ -1376,21 +1318,20 @@ void File::save(const std::filesystem::path &path)
{ {
fs::path file = path.filename(); fs::path file = path.filename();
std::ofstream outFile(path, std::ios_base::out | std::ios_base::binary); std::unique_ptr<std::ostream> outFile;
io::filtering_stream<io::output> out;
if (file.extension() == ".gz") if (file.extension() == ".gz")
{ {
out.push(io::gzip_compressor()); outFile.reset(new gzstream::ofstream(path));
file.replace_extension(""); file.replace_extension("");
} }
else
out.push(outFile); outFile.reset(new std::ofstream(path, std::ios_base::out | std::ios_base::binary));
if (file.extension() == ".pdb") if (file.extension() == ".pdb")
WritePDBFile(out, data()); WritePDBFile(*outFile, data());
else else
cif::File::save(out); cif::File::save(*outFile);
} }
// -------------------------------------------------------------------- // --------------------------------------------------------------------
......
src/TlsParser.cpp
...@@ -24,12 +24,8 @@ ...@@ -24,12 +24,8 @@
* SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/ */
#include <boost/algorithm/string.hpp>
#include <cif++/TlsParser.hpp> #include <cif++/TlsParser.hpp>
namespace ba = boost::algorithm;
namespace cif namespace cif
{ {
...@@ -1830,7 +1826,7 @@ TLSSelectionPtr ParseSelectionDetails(const std::string& program, const std::str ...@@ -1830,7 +1826,7 @@ TLSSelectionPtr ParseSelectionDetails(const std::string& program, const std::str
TLSSelectionPtr result; TLSSelectionPtr result;
if (ba::icontains(program, "buster")) if (cif::icontains(program, "buster"))
{ {
result = buster.Parse(selection); result = buster.Parse(selection);
...@@ -1848,7 +1844,7 @@ TLSSelectionPtr ParseSelectionDetails(const std::string& program, const std::str ...@@ -1848,7 +1844,7 @@ TLSSelectionPtr ParseSelectionDetails(const std::string& program, const std::str
result = phenix.Parse(selection); result = phenix.Parse(selection);
} }
} }
else if (ba::icontains(program, "phenix")) else if (cif::icontains(program, "phenix"))
{ {
result = phenix.Parse(selection); result = phenix.Parse(selection);
......
src/parser.cpp
...@@ -1294,9 +1294,9 @@ bool DictParser::collectItemTypes() ...@@ -1294,9 +1294,9 @@ bool DictParser::collectItemTypes()
std::string code, primitiveCode, construct; std::string code, primitiveCode, construct;
cif::tie(code, primitiveCode, construct) = t.get("code", "primitive_code", "construct"); cif::tie(code, primitiveCode, construct) = t.get("code", "primitive_code", "construct");
ba::replace_all(construct, "\\n", "\n"); cif::replace_all(construct, "\\n", "\n");
ba::replace_all(construct, "\\t", "\t"); cif::replace_all(construct, "\\t", "\t");
ba::replace_all(construct, "\\\n", ""); cif::replace_all(construct, "\\\n", "");
try try
{ {
......
src/v2/category.cpp
...@@ -34,32 +34,6 @@ ...@@ -34,32 +34,6 @@
namespace cif::v2 namespace cif::v2
{ {
template <typename V>
std::string join(const V &arr, std::string_view sep)
{
std::ostringstream s;
if (not arr.empty())
{
auto ai = arr.begin();
auto ni = std::next(ai);
for (;;)
{
s << *ai;
ai = ni;
ni = std::next(ai);
if (ni == arr.end())
break;
s << sep;
}
}
return s.str();
}
// -------------------------------------------------------------------- // --------------------------------------------------------------------
class row_comparator class row_comparator
...@@ -1013,8 +987,13 @@ category::iterator category::erase(iterator pos) ...@@ -1013,8 +987,13 @@ category::iterator category::erase(iterator pos)
for (size_t ix = 0; ix < link->m_parent_keys.size(); ++ix) for (size_t ix = 0; ix < link->m_parent_keys.size(); ++ix)
{ {
std::string_view value = rh[link->m_parent_keys[ix]].text(); std::string_view value = rh[link->m_parent_keys[ix]].text();
// cond = std::move(cond) and (key(link->m_child_keys[ix]) == value or key(link->m_child_keys[ix]) == null);
cond = std::move(cond) and (key(link->m_child_keys[ix]) == value); auto childKey = link->m_child_keys[ix];
if (childCat->m_cat_validator and childCat->m_cat_validator->m_mandatory_fields.contains(childKey))
cond = std::move(cond) and key(childKey) == value;
else
cond = std::move(cond) and (key(childKey) == value or key(childKey) == null);
} }
childCat->erase_orphans(std::move(cond)); childCat->erase_orphans(std::move(cond));
...@@ -1133,6 +1112,164 @@ void category::erase_orphans(condition &&cond) ...@@ -1133,6 +1112,164 @@ void category::erase_orphans(condition &&cond)
erase(iterator(*this, r)); erase(iterator(*this, r));
} }
std::string category::get_unique_id(std::function<std::string(int)> generator)
{
using namespace cif::v2::literals;
std::string id_tag = "id";
if (m_cat_validator != nullptr and m_cat_validator->m_keys.size() == 1)
id_tag = m_cat_validator->m_keys.front();
// calling size() often is a waste of resources
if (m_last_unique_num == 0)
m_last_unique_num = size();
for (;;)
{
std::string result = generator(static_cast<int>(m_last_unique_num++));
if (exists(key(id_tag) == result))
continue;
return result;
}
}
void category::update_value(const std::vector<row_handle> &rows, std::string_view tag, std::string_view value)
{
using namespace std::literals;
if (rows.empty())
return;
auto colIx = get_column_ix(tag);
if (colIx >= m_columns.size())
throw std::runtime_error("Invalid column " + std::string{ value } + " for " + m_name);
auto &col = m_columns[colIx];
// check the value
if (col.m_validator)
(*col.m_validator)(value);
// first some sanity checks, what was the old value and is it the same for all rows?
std::string_view oldValue = rows.front()[tag].text();
for (auto row : rows)
{
if (oldValue != row[tag].text())
throw std::runtime_error("Inconsistent old values in update_value");
}
if (oldValue == value) // no need to do anything
return;
// update rows, but do not cascade
for (auto row : rows)
row.assign(colIx, value, false);
// see if we need to update any child categories that depend on this value
for (auto parent : rows)
{
for (auto &&[childCat, linked] : m_child_links)
{
if (std::find(linked->m_parent_keys.begin(), linked->m_parent_keys.end(), tag) == linked->m_parent_keys.end())
continue;
condition cond;
std::string childTag;
for (size_t ix = 0; ix < linked->m_parent_keys.size(); ++ix)
{
std::string pk = linked->m_parent_keys[ix];
std::string ck = linked->m_child_keys[ix];
// TODO: add code to *NOT* test mandatory fields for Empty
if (pk == tag)
{
childTag = ck;
cond = std::move(cond) && key(ck) == oldValue;
}
else
cond = std::move(cond) && key(ck) == parent[pk].text();
}
auto children = childCat->find(std::move(cond));
if (children.empty())
continue;
std::vector<row_handle> child_rows;
std::copy(children.begin(), children.end(), std::back_inserter(child_rows));
// now be careful. If we search back from child to parent and still find a valid parent row
// we cannot simply rename the child but will have to create a new child. Unless that new
// child already exists of course.
std::vector<row_handle> process;
for (auto child : child_rows)
{
condition cond_c;
for (size_t ix = 0; ix < linked->m_parent_keys.size(); ++ix)
{
std::string pk = linked->m_parent_keys[ix];
std::string ck = linked->m_child_keys[ix];
// TODO: add code to *NOT* test mandatory fields for Empty
cond_c = std::move(cond_c) && key(pk) == child[ck].text();
}
auto parents = find(std::move(cond_c));
if (parents.empty())
{
process.push_back(child);
continue;
}
// oops, we need to split this child, unless a row already exists for the new value
condition check;
for (size_t ix = 0; ix < linked->m_parent_keys.size(); ++ix)
{
std::string pk = linked->m_parent_keys[ix];
std::string ck = linked->m_child_keys[ix];
// TODO: add code to *NOT* test mandatory fields for Empty
if (pk == tag)
check = std::move(check) && key(ck) == value;
else
check = std::move(check) && key(ck) == parent[pk].text();
}
if (childCat->exists(std::move(check))) // phew..., narrow escape
continue;
// create the actual copy, if we can...
if (childCat->m_cat_validator != nullptr and childCat->m_cat_validator->m_keys.size() == 1)
{
auto copy = childCat->create_copy(child);
if (copy != child)
{
process.push_back(child);
continue;
}
}
// cannot update this...
if (cif::VERBOSE > 0)
std::cerr << "Cannot update child " << childCat->m_name << "." << childTag << " with value " << value << std::endl;
}
// finally, update the children
if (not process.empty())
childCat->update_value(std::move(process), childTag, value);
}
}
}
void category::update_value(row *row, size_t column, std::string_view value, bool updateLinked, bool validate) void category::update_value(row *row, size_t column, std::string_view value, bool updateLinked, bool validate)
{ {
auto &col = m_columns[column]; auto &col = m_columns[column];
...@@ -1235,7 +1372,7 @@ void category::update_value(row *row, size_t column, std::string_view value, boo ...@@ -1235,7 +1372,7 @@ void category::update_value(row *row, size_t column, std::string_view value, boo
std::string pk = linked->m_parent_keys[ix]; std::string pk = linked->m_parent_keys[ix];
std::string ck = linked->m_child_keys[ix]; std::string ck = linked->m_child_keys[ix];
// TODO add code to *NOT* test mandatory fields for Empty // TODO: add code to *NOT* test mandatory fields for Empty
if (pk == iv->m_tag) if (pk == iv->m_tag)
{ {
...@@ -1272,7 +1409,7 @@ void category::update_value(row *row, size_t column, std::string_view value, boo ...@@ -1272,7 +1409,7 @@ void category::update_value(row *row, size_t column, std::string_view value, boo
std::string pk = linked->m_parent_keys[ix]; std::string pk = linked->m_parent_keys[ix];
std::string ck = linked->m_child_keys[ix]; std::string ck = linked->m_child_keys[ix];
// TODO add code to *NOT* test mandatory fields for Empty // TODO: add code to *NOT* test mandatory fields for Empty
if (pk == iv->m_tag) if (pk == iv->m_tag)
cond_n = std::move(cond_n) and key(ck) == value; cond_n = std::move(cond_n) and key(ck) == value;
...@@ -1301,6 +1438,40 @@ void category::update_value(row *row, size_t column, std::string_view value, boo ...@@ -1301,6 +1438,40 @@ void category::update_value(row *row, size_t column, std::string_view value, boo
} }
} }
row_handle category::create_copy(row_handle r)
{
// copy the values
std::vector<item> items;
for (item_value *iv = r.m_row->m_head; iv != nullptr; iv = iv->m_next)
items.emplace_back(m_columns[iv->m_column_ix].m_name, iv->text());
if (m_cat_validator and m_cat_validator->m_keys.size() == 1)
{
auto key = m_cat_validator->m_keys.front();
auto kv = m_cat_validator->get_validator_for_item(key);
for (auto &item : items)
{
if (item.name() != key)
continue;
if (kv->m_type->m_primitive_type == DDL_PrimitiveType::Numb)
item.value(get_unique_id(""));
else
item.value(get_unique_id(m_name + "_id_"));
break;
}
}
return emplace(items.begin(), items.end());
// auto &&[result, inserted] = emplace(items.begin(), items.end());
// // assert(inserted);
// return result;
}
// proxy methods for every insertion // proxy methods for every insertion
category::iterator category::insert_impl(const_iterator pos, row *n) category::iterator category::insert_impl(const_iterator pos, row *n)
{ {
......
src/v2/validate.cpp
...@@ -28,6 +28,8 @@ ...@@ -28,6 +28,8 @@
#include <fstream> #include <fstream>
#include <iostream> #include <iostream>
#include <gzstream/gzstream.hpp>
#include <cif++/v2/dictionary_parser.hpp> #include <cif++/v2/dictionary_parser.hpp>
#include <cif++/v2/validate.hpp> #include <cif++/v2/validate.hpp>
...@@ -407,13 +409,10 @@ const validator &validator_factory::operator[](std::string_view dictionary_name) ...@@ -407,13 +409,10 @@ const validator &validator_factory::operator[](std::string_view dictionary_name)
if (std::filesystem::exists(p, ec) and not ec) if (std::filesystem::exists(p, ec) and not ec)
{ {
std::ifstream file(p, std::ios::binary); gzstream::ifstream in(p);
if (not file.is_open())
throw std::runtime_error("Could not open dictionary (" + p.string() + ")");
io::filtering_stream<io::input> in; if (not in.is_open())
in.push(io::gzip_decompressor()); throw std::runtime_error("Could not open dictionary (" + p.string() + ")");
in.push(file);
construct_validator(dictionary_name, in); construct_validator(dictionary_name, in);
} }
......
test/unit-v2-test.cpp
...@@ -287,7 +287,7 @@ BOOST_AUTO_TEST_CASE(c_3) ...@@ -287,7 +287,7 @@ BOOST_AUTO_TEST_CASE(c_3)
for (auto r : c) for (auto r : c)
c2.emplace(r); c2.emplace(r);
BOOST_CHECK(c == c2); // BOOST_CHECK(c == c2);
} }
BOOST_AUTO_TEST_CASE(ci_1) BOOST_AUTO_TEST_CASE(ci_1)
...@@ -333,10 +333,10 @@ _test.name ...@@ -333,10 +333,10 @@ _test.name
auto &db = f.front(); auto &db = f.front();
BOOST_CHECK(db.name() == "TEST"); BOOST_CHECK_EQUAL(db.name(), "TEST");
auto &test = db["test"]; auto &test = db["test"];
BOOST_CHECK(test.size() == 3); BOOST_CHECK_EQUAL(test.size(), 3);
const char *ts[] = {"aap", "noot", "mies"}; const char *ts[] = {"aap", "noot", "mies"};
...@@ -382,27 +382,27 @@ _test.value ...@@ -382,27 +382,27 @@ _test.value
auto &db = f.front(); auto &db = f.front();
BOOST_CHECK(db.name() == "TEST"); BOOST_CHECK_EQUAL(db.name(), "TEST");
auto &test = db["test"]; auto &test = db["test"];
BOOST_CHECK(test.size() == 3); BOOST_CHECK_EQUAL(test.size(), 3);
int n = 0; int n = 0;
for (auto r : test.find(cif::v2::key("name") == "aap")) for (auto r : test.find(cif::v2::key("name") == "aap"))
{ {
BOOST_CHECK(++n == 1); BOOST_CHECK_EQUAL(++n, 1);
BOOST_CHECK(r["id"].as<int>() == 1); BOOST_CHECK_EQUAL(r["id"].as<int>(), 1);
BOOST_CHECK(r["name"].as<std::string>() == "aap"); BOOST_CHECK_EQUAL(r["name"].as<std::string>(), "aap");
BOOST_CHECK(r["value"].as<float>() == 1.0); BOOST_CHECK_EQUAL(r["value"].as<float>(), 1.0);
} }
auto t = test.find(cif::v2::key("id") == 1); auto t = test.find(cif::v2::key("id") == 1);
BOOST_CHECK(not t.empty()); BOOST_CHECK(not t.empty());
BOOST_CHECK(t.front()["name"].as<std::string>() == "aap"); BOOST_CHECK_EQUAL(t.front()["name"].as<std::string>(), "aap");
auto t2 = test.find(cif::v2::key("value") == 1.2); auto t2 = test.find(cif::v2::key("value") == 1.2);
BOOST_CHECK(not t2.empty()); BOOST_CHECK(not t2.empty());
BOOST_CHECK(t2.front()["name"].as<std::string>() == "mies"); BOOST_CHECK_EQUAL(t2.front()["name"].as<std::string>(), "mies");
} }
BOOST_AUTO_TEST_CASE(ut3) BOOST_AUTO_TEST_CASE(ut3)
...@@ -424,13 +424,13 @@ _test.value ...@@ -424,13 +424,13 @@ _test.value
auto &db = f.front(); auto &db = f.front();
BOOST_CHECK(db.name() == "TEST"); BOOST_CHECK_EQUAL(db.name(), "TEST");
auto &test = db["test"]; auto &test = db["test"];
BOOST_CHECK(test.size() == 5); BOOST_CHECK_EQUAL(test.size(), 5);
BOOST_CHECK(test.exists("value"_key == cif::v2::null)); BOOST_CHECK(test.exists("value"_key == cif::v2::null));
BOOST_CHECK(test.find("value"_key == cif::v2::null).size() == 2); BOOST_CHECK_EQUAL(test.find("value"_key == cif::v2::null).size(), 2);
} }
// -------------------------------------------------------------------- // --------------------------------------------------------------------
...@@ -579,13 +579,13 @@ _cat_2.desc ...@@ -579,13 +579,13 @@ _cat_2.desc
auto &cat1 = f.front()["cat_1"]; auto &cat1 = f.front()["cat_1"];
auto &cat2 = f.front()["cat_2"]; auto &cat2 = f.front()["cat_2"];
BOOST_CHECK(cat1.size() == 3); BOOST_CHECK_EQUAL(cat1.size(), 3);
BOOST_CHECK(cat2.size() == 3); BOOST_CHECK_EQUAL(cat2.size(), 3);
cat1.erase(cif::v2::key("id") == 1); cat1.erase(cif::v2::key("id") == 1);
BOOST_CHECK(cat1.size() == 2); BOOST_CHECK_EQUAL(cat1.size(), 2);
BOOST_CHECK(cat2.size() == 1); BOOST_CHECK_EQUAL(cat2.size(), 1);
// BOOST_CHECK_THROW(cat2.emplace({ // BOOST_CHECK_THROW(cat2.emplace({
// { "id", 4 }, // { "id", 4 },
...@@ -700,15 +700,15 @@ mies Mies ...@@ -700,15 +700,15 @@ mies Mies
auto &cat1 = f.front()["cat_1"]; auto &cat1 = f.front()["cat_1"];
BOOST_CHECK(cat1.size() == 3); BOOST_CHECK_EQUAL(cat1.size(), 3);
cat1.erase(cif::v2::key("id") == "AAP"); cat1.erase(cif::v2::key("id") == "AAP");
BOOST_CHECK(cat1.size() == 3); BOOST_CHECK_EQUAL(cat1.size(), 3);
cat1.erase(cif::v2::key("id") == "noot"); cat1.erase(cif::v2::key("id") == "noot");
BOOST_CHECK(cat1.size() == 2); BOOST_CHECK_EQUAL(cat1.size(), 2);
// should fail with duplicate key: // should fail with duplicate key:
BOOST_CHECK_THROW(cat1.emplace({ BOOST_CHECK_THROW(cat1.emplace({
...@@ -718,14 +718,14 @@ mies Mies ...@@ -718,14 +718,14 @@ mies Mies
cat1.erase(cif::v2::key("id") == "aap"); cat1.erase(cif::v2::key("id") == "aap");
BOOST_CHECK(cat1.size() == 1); BOOST_CHECK_EQUAL(cat1.size(), 1);
cat1.emplace({ cat1.emplace({
{"id", "aap"}, {"id", "aap"},
{"c", "2e-aap"} {"c", "2e-aap"}
}); });
BOOST_CHECK(cat1.size() == 2); BOOST_CHECK_EQUAL(cat1.size(), 2);
} }
// -------------------------------------------------------------------- // --------------------------------------------------------------------
...@@ -885,14 +885,14 @@ _cat_2.desc ...@@ -885,14 +885,14 @@ _cat_2.desc
break; break;
} }
BOOST_CHECK(cat1.size() == 3); BOOST_CHECK_EQUAL(cat1.size(), 3);
BOOST_CHECK(cat2.size() == 4); BOOST_CHECK_EQUAL(cat2.size(), 4);
BOOST_CHECK(cat1.find(cif::v2::key("id") == 1).size() == 0); BOOST_CHECK_EQUAL(cat1.find(cif::v2::key("id") == 1).size(), 0);
BOOST_CHECK(cat1.find(cif::v2::key("id") == 10).size() == 1); BOOST_CHECK_EQUAL(cat1.find(cif::v2::key("id") == 10).size(), 1);
BOOST_CHECK(cat2.find(cif::v2::key("parent_id") == 1).size() == 0); BOOST_CHECK_EQUAL(cat2.find(cif::v2::key("parent_id") == 1).size(), 0);
BOOST_CHECK(cat2.find(cif::v2::key("parent_id") == 10).size() == 2); BOOST_CHECK_EQUAL(cat2.find(cif::v2::key("parent_id") == 10).size(), 2);
// check a rename in parent and child, this time only one child should be renamed // check a rename in parent and child, this time only one child should be renamed
...@@ -902,31 +902,31 @@ _cat_2.desc ...@@ -902,31 +902,31 @@ _cat_2.desc
break; break;
} }
BOOST_CHECK(cat1.size() == 3); BOOST_CHECK_EQUAL(cat1.size(), 3);
BOOST_CHECK(cat2.size() == 4); BOOST_CHECK_EQUAL(cat2.size(), 4);
BOOST_CHECK(cat1.find(cif::v2::key("id") == 2).size() == 0); BOOST_CHECK_EQUAL(cat1.find(cif::v2::key("id") == 2).size(), 0);
BOOST_CHECK(cat1.find(cif::v2::key("id") == 20).size() == 1); BOOST_CHECK_EQUAL(cat1.find(cif::v2::key("id") == 20).size(), 1);
BOOST_CHECK(cat2.find(cif::v2::key("parent_id") == 2).size() == 1); BOOST_CHECK_EQUAL(cat2.find(cif::v2::key("parent_id") == 2).size(), 1);
BOOST_CHECK(cat2.find(cif::v2::key("parent_id") == 20).size() == 1); BOOST_CHECK_EQUAL(cat2.find(cif::v2::key("parent_id") == 20).size(), 1);
BOOST_CHECK(cat2.find(cif::v2::key("parent_id") == 2 and cif::v2::key("name2") == "noot").size() == 0); BOOST_CHECK_EQUAL(cat2.find(cif::v2::key("parent_id") == 2 and cif::v2::key("name2") == "noot").size(), 0);
BOOST_CHECK(cat2.find(cif::v2::key("parent_id") == 2 and cif::v2::key("name2") == "n2").size() == 1); BOOST_CHECK_EQUAL(cat2.find(cif::v2::key("parent_id") == 2 and cif::v2::key("name2") == "n2").size(), 1);
BOOST_CHECK(cat2.find(cif::v2::key("parent_id") == 20 and cif::v2::key("name2") == "noot").size() == 1); BOOST_CHECK_EQUAL(cat2.find(cif::v2::key("parent_id") == 20 and cif::v2::key("name2") == "noot").size(), 1);
BOOST_CHECK(cat2.find(cif::v2::key("parent_id") == 20 and cif::v2::key("name2") == "n2").size() == 0); BOOST_CHECK_EQUAL(cat2.find(cif::v2::key("parent_id") == 20 and cif::v2::key("name2") == "n2").size(), 0);
// -------------------------------------------------------------------- // --------------------------------------------------------------------
cat1.erase(cif::v2::key("id") == 10); cat1.erase(cif::v2::key("id") == 10);
BOOST_CHECK(cat1.size() == 2); BOOST_CHECK_EQUAL(cat1.size(), 2);
BOOST_CHECK(cat2.size() == 2); BOOST_CHECK_EQUAL(cat2.size(), 2);
cat1.erase(cif::v2::key("id") == 20); cat1.erase(cif::v2::key("id") == 20);
BOOST_CHECK(cat1.size() == 1); BOOST_CHECK_EQUAL(cat1.size(), 1);
BOOST_CHECK(cat2.size() == 1); BOOST_CHECK_EQUAL(cat2.size(), 1);
} }
// -------------------------------------------------------------------- // --------------------------------------------------------------------
...@@ -1098,14 +1098,14 @@ _cat_2.parent_id3 ...@@ -1098,14 +1098,14 @@ _cat_2.parent_id3
break; break;
} }
BOOST_CHECK(cat1.size() == 4); BOOST_CHECK_EQUAL(cat1.size(), 4);
BOOST_CHECK(cat2.size() == 13); BOOST_CHECK_EQUAL(cat2.size(), 13);
BOOST_CHECK(cat1.find(cif::v2::key("id") == 1).size() == 0); BOOST_CHECK_EQUAL(cat1.find(cif::v2::key("id") == 1).size(), 0);
BOOST_CHECK(cat1.find(cif::v2::key("id") == 10).size() == 1); BOOST_CHECK_EQUAL(cat1.find(cif::v2::key("id") == 10).size(), 1);
BOOST_CHECK(cat2.find(cif::v2::key("parent_id") == 1).size() == 1); BOOST_CHECK_EQUAL(cat2.find(cif::v2::key("parent_id") == 1).size(), 1);
BOOST_CHECK(cat2.find(cif::v2::key("parent_id") == 10).size() == 2); BOOST_CHECK_EQUAL(cat2.find(cif::v2::key("parent_id") == 10).size(), 2);
for (auto r : cat1.find(cif::v2::key("id") == 2)) for (auto r : cat1.find(cif::v2::key("id") == 2))
{ {
...@@ -1113,14 +1113,14 @@ _cat_2.parent_id3 ...@@ -1113,14 +1113,14 @@ _cat_2.parent_id3
break; break;
} }
BOOST_CHECK(cat1.size() == 4); BOOST_CHECK_EQUAL(cat1.size(), 4);
BOOST_CHECK(cat2.size() == 13); BOOST_CHECK_EQUAL(cat2.size(), 13);
BOOST_CHECK(cat1.find(cif::v2::key("id") == 2).size() == 0); BOOST_CHECK_EQUAL(cat1.find(cif::v2::key("id") == 2).size(), 0);
BOOST_CHECK(cat1.find(cif::v2::key("id") == 20).size() == 1); BOOST_CHECK_EQUAL(cat1.find(cif::v2::key("id") == 20).size(), 1);
BOOST_CHECK(cat2.find(cif::v2::key("parent_id") == 2).size() == 2); BOOST_CHECK_EQUAL(cat2.find(cif::v2::key("parent_id") == 2).size(), 2);
BOOST_CHECK(cat2.find(cif::v2::key("parent_id") == 20).size() == 2); BOOST_CHECK_EQUAL(cat2.find(cif::v2::key("parent_id") == 20).size(), 2);
for (auto r : cat1.find(cif::v2::key("id") == 3)) for (auto r : cat1.find(cif::v2::key("id") == 3))
{ {
...@@ -1128,14 +1128,14 @@ _cat_2.parent_id3 ...@@ -1128,14 +1128,14 @@ _cat_2.parent_id3
break; break;
} }
BOOST_CHECK(cat1.size() == 4); BOOST_CHECK_EQUAL(cat1.size(), 4);
BOOST_CHECK(cat2.size() == 13); BOOST_CHECK_EQUAL(cat2.size(), 13);
BOOST_CHECK(cat1.find(cif::v2::key("id") == 3).size() == 0); BOOST_CHECK_EQUAL(cat1.find(cif::v2::key("id") == 3).size(), 0);
BOOST_CHECK(cat1.find(cif::v2::key("id") == 30).size() == 1); BOOST_CHECK_EQUAL(cat1.find(cif::v2::key("id") == 30).size(), 1);
BOOST_CHECK(cat2.find(cif::v2::key("parent_id") == 3).size() == 2); BOOST_CHECK_EQUAL(cat2.find(cif::v2::key("parent_id") == 3).size(), 2);
BOOST_CHECK(cat2.find(cif::v2::key("parent_id") == 30).size() == 1); BOOST_CHECK_EQUAL(cat2.find(cif::v2::key("parent_id") == 30).size(), 1);
for (auto r : cat1.find(cif::v2::key("id") == 4)) for (auto r : cat1.find(cif::v2::key("id") == 4))
{ {
...@@ -1143,14 +1143,14 @@ _cat_2.parent_id3 ...@@ -1143,14 +1143,14 @@ _cat_2.parent_id3
break; break;
} }
BOOST_CHECK(cat1.size() == 4); BOOST_CHECK_EQUAL(cat1.size(), 4);
BOOST_CHECK(cat2.size() == 13); BOOST_CHECK_EQUAL(cat2.size(), 13);
BOOST_CHECK(cat1.find(cif::v2::key("id") == 4).size() == 0); BOOST_CHECK_EQUAL(cat1.find(cif::v2::key("id") == 4).size(), 0);
BOOST_CHECK(cat1.find(cif::v2::key("id") == 10).size() == 1); BOOST_CHECK_EQUAL(cat1.find(cif::v2::key("id") == 10).size(), 1);
BOOST_CHECK(cat2.find(cif::v2::key("parent_id") == 4).size() == 3); BOOST_CHECK_EQUAL(cat2.find(cif::v2::key("parent_id") == 4).size(), 3);
BOOST_CHECK(cat2.find(cif::v2::key("parent_id") == 40).size() == 0); BOOST_CHECK_EQUAL(cat2.find(cif::v2::key("parent_id") == 40).size(), 0);
} }
// -------------------------------------------------------------------- // --------------------------------------------------------------------
...@@ -1310,7 +1310,7 @@ _cat_2.parent_id3 ...@@ -1310,7 +1310,7 @@ _cat_2.parent_id3
auto PR2set = cat1.find(cif::v2::key("id") == 2); auto PR2set = cat1.find(cif::v2::key("id") == 2);
BOOST_ASSERT(PR2set.size() == 1); BOOST_ASSERT(PR2set.size() == 1);
auto PR2 = PR2set.front(); auto PR2 = PR2set.front();
BOOST_CHECK(PR2["id"].as<int>() == 2); BOOST_CHECK_EQUAL(PR2["id"].as<int>(), 2);
auto CR2set = cat1.get_children(PR2, cat2); auto CR2set = cat1.get_children(PR2, cat2);
BOOST_ASSERT(CR2set.size() == 3); BOOST_ASSERT(CR2set.size() == 3);
...@@ -1329,18 +1329,18 @@ _cat_2.parent_id3 ...@@ -1329,18 +1329,18 @@ _cat_2.parent_id3
break; break;
} }
BOOST_CHECK(cat1.size() == 3); BOOST_CHECK_EQUAL(cat1.size(), 3);
BOOST_CHECK(cat2.size() == 7); BOOST_CHECK_EQUAL(cat2.size(), 7);
BOOST_CHECK(cat1.find(cif::v2::key("id") == 1).size() == 0); BOOST_CHECK_EQUAL(cat1.find(cif::v2::key("id") == 1).size(), 0);
BOOST_CHECK(cat1.find(cif::v2::key("id") == 10).size() == 1); BOOST_CHECK_EQUAL(cat1.find(cif::v2::key("id") == 10).size(), 1);
BOOST_CHECK(cat2.find(cif::v2::key("parent_id") == 1).size() == 0); BOOST_CHECK_EQUAL(cat2.find(cif::v2::key("parent_id") == 1).size(), 0);
BOOST_CHECK(cat2.find(cif::v2::key("parent_id2") == 1).size() == 0); BOOST_CHECK_EQUAL(cat2.find(cif::v2::key("parent_id2") == 1).size(), 0);
BOOST_CHECK(cat2.find(cif::v2::key("parent_id3") == 1).size() == 0); BOOST_CHECK_EQUAL(cat2.find(cif::v2::key("parent_id3") == 1).size(), 0);
BOOST_CHECK(cat2.find(cif::v2::key("parent_id") == 10).size() == 1); BOOST_CHECK_EQUAL(cat2.find(cif::v2::key("parent_id") == 10).size(), 1);
BOOST_CHECK(cat2.find(cif::v2::key("parent_id2") == 10).size() == 1); BOOST_CHECK_EQUAL(cat2.find(cif::v2::key("parent_id2") == 10).size(), 1);
BOOST_CHECK(cat2.find(cif::v2::key("parent_id3") == 10).size() == 1); BOOST_CHECK_EQUAL(cat2.find(cif::v2::key("parent_id3") == 10).size(), 1);
for (auto r : cat1.find(cif::v2::key("id") == 2)) for (auto r : cat1.find(cif::v2::key("id") == 2))
{ {
...@@ -1348,18 +1348,18 @@ _cat_2.parent_id3 ...@@ -1348,18 +1348,18 @@ _cat_2.parent_id3
break; break;
} }
BOOST_CHECK(cat1.size() == 3); BOOST_CHECK_EQUAL(cat1.size(), 3);
BOOST_CHECK(cat2.size() == 7); BOOST_CHECK_EQUAL(cat2.size(), 7);
BOOST_CHECK(cat1.find(cif::v2::key("id") == 2).size() == 0); BOOST_CHECK_EQUAL(cat1.find(cif::v2::key("id") == 2).size(), 0);
BOOST_CHECK(cat1.find(cif::v2::key("id") == 20).size() == 1); BOOST_CHECK_EQUAL(cat1.find(cif::v2::key("id") == 20).size(), 1);
BOOST_CHECK(cat2.find(cif::v2::key("parent_id") == 2).size() == 0); BOOST_CHECK_EQUAL(cat2.find(cif::v2::key("parent_id") == 2).size(), 0);
BOOST_CHECK(cat2.find(cif::v2::key("parent_id2") == 2).size() == 0); BOOST_CHECK_EQUAL(cat2.find(cif::v2::key("parent_id2") == 2).size(), 0);
BOOST_CHECK(cat2.find(cif::v2::key("parent_id3") == 2).size() == 0); BOOST_CHECK_EQUAL(cat2.find(cif::v2::key("parent_id3") == 2).size(), 0);
BOOST_CHECK(cat2.find(cif::v2::key("parent_id") == 20).size() == 2); BOOST_CHECK_EQUAL(cat2.find(cif::v2::key("parent_id") == 20).size(), 2);
BOOST_CHECK(cat2.find(cif::v2::key("parent_id2") == 20).size() == 2); BOOST_CHECK_EQUAL(cat2.find(cif::v2::key("parent_id2") == 20).size(), 2);
BOOST_CHECK(cat2.find(cif::v2::key("parent_id3") == 20).size() == 2); BOOST_CHECK_EQUAL(cat2.find(cif::v2::key("parent_id3") == 20).size(), 2);
for (auto r : cat1.find(cif::v2::key("id") == 3)) for (auto r : cat1.find(cif::v2::key("id") == 3))
{ {
...@@ -1367,32 +1367,32 @@ _cat_2.parent_id3 ...@@ -1367,32 +1367,32 @@ _cat_2.parent_id3
break; break;
} }
BOOST_CHECK(cat1.size() == 3); BOOST_CHECK_EQUAL(cat1.size(), 3);
BOOST_CHECK(cat2.size() == 7); BOOST_CHECK_EQUAL(cat2.size(), 7);
BOOST_CHECK(cat1.find(cif::v2::key("id") == 3).size() == 0); BOOST_CHECK_EQUAL(cat1.find(cif::v2::key("id") == 3).size(), 0);
BOOST_CHECK(cat1.find(cif::v2::key("id") == 30).size() == 1); BOOST_CHECK_EQUAL(cat1.find(cif::v2::key("id") == 30).size(), 1);
BOOST_CHECK(cat2.find(cif::v2::key("parent_id") == 3).size() == 0); BOOST_CHECK_EQUAL(cat2.find(cif::v2::key("parent_id") == 3).size(), 0);
BOOST_CHECK(cat2.find(cif::v2::key("parent_id2") == 3).size() == 0); BOOST_CHECK_EQUAL(cat2.find(cif::v2::key("parent_id2") == 3).size(), 0);
BOOST_CHECK(cat2.find(cif::v2::key("parent_id3") == 3).size() == 0); BOOST_CHECK_EQUAL(cat2.find(cif::v2::key("parent_id3") == 3).size(), 0);
BOOST_CHECK(cat2.find(cif::v2::key("parent_id") == 30).size() == 1); BOOST_CHECK_EQUAL(cat2.find(cif::v2::key("parent_id") == 30).size(), 1);
BOOST_CHECK(cat2.find(cif::v2::key("parent_id2") == 30).size() == 1); BOOST_CHECK_EQUAL(cat2.find(cif::v2::key("parent_id2") == 30).size(), 1);
BOOST_CHECK(cat2.find(cif::v2::key("parent_id3") == 30).size() == 1); BOOST_CHECK_EQUAL(cat2.find(cif::v2::key("parent_id3") == 30).size(), 1);
// test delete // test delete
cat1.erase(cif::v2::key("id") == 10); cat1.erase(cif::v2::key("id") == 10);
BOOST_CHECK(cat1.size() == 2); BOOST_CHECK_EQUAL(cat1.size(), 2);
BOOST_CHECK(cat2.size() == 4); BOOST_CHECK_EQUAL(cat2.size(), 4);
cat1.erase(cif::v2::key("id") == 20); cat1.erase(cif::v2::key("id") == 20);
BOOST_CHECK(cat1.size() == 1); BOOST_CHECK_EQUAL(cat1.size(), 1);
BOOST_CHECK(cat2.size() == 1); BOOST_CHECK_EQUAL(cat2.size(), 1);
cat1.erase(cif::v2::key("id") == 30); cat1.erase(cif::v2::key("id") == 30);
BOOST_CHECK(cat1.size() == 0); BOOST_CHECK_EQUAL(cat1.size(), 0);
BOOST_CHECK(cat2.size() == 0); BOOST_CHECK_EQUAL(cat2.size(), 0);
} }
// -------------------------------------------------------------------- // --------------------------------------------------------------------
...@@ -1418,21 +1418,21 @@ _test.name ...@@ -1418,21 +1418,21 @@ _test.name
for (auto r : db["test"].find(cif::v2::key("id") == 1)) for (auto r : db["test"].find(cif::v2::key("id") == 1))
{ {
const auto &[id, name] = r.get<int, std::string>({"id", "name"}); const auto &[id, name] = r.get<int, std::string>({"id", "name"});
BOOST_CHECK(id == 1); BOOST_CHECK_EQUAL(id, 1);
BOOST_CHECK(name == "aap"); BOOST_CHECK_EQUAL(name, "aap");
} }
for (auto r : db["test"].find(cif::v2::key("id") == 4)) for (auto r : db["test"].find(cif::v2::key("id") == 4))
{ {
const auto &[id, name] = r.get<int, std::string>({"id", "name"}); const auto &[id, name] = r.get<int, std::string>({"id", "name"});
BOOST_CHECK(id == 4); BOOST_CHECK_EQUAL(id, 4);
BOOST_CHECK(name.empty()); BOOST_CHECK(name.empty());
} }
for (auto r : db["test"].find(cif::v2::key("id") == 5)) for (auto r : db["test"].find(cif::v2::key("id") == 5))
{ {
const auto &[id, name] = r.get<int, std::string>({"id", "name"}); const auto &[id, name] = r.get<int, std::string>({"id", "name"});
BOOST_CHECK(id == 5); BOOST_CHECK_EQUAL(id, 5);
BOOST_CHECK(name.empty()); BOOST_CHECK(name.empty());
} }
...@@ -1524,8 +1524,8 @@ _test.name ...@@ -1524,8 +1524,8 @@ _test.name
const auto &[id, name] = db["test"].find1<int, std::string>(cif::v2::key("id") == 1, "id", "name"); const auto &[id, name] = db["test"].find1<int, std::string>(cif::v2::key("id") == 1, "id", "name");
BOOST_CHECK(id == 1); BOOST_CHECK_EQUAL(id, 1);
BOOST_CHECK(name == "aap"); BOOST_CHECK_EQUAL(name, "aap");
} }
// -------------------------------------------------------------------- // --------------------------------------------------------------------
...@@ -1739,24 +1739,22 @@ _cat_3.num ...@@ -1739,24 +1739,22 @@ _cat_3.num
auto &cat2 = f.front()["cat_2"]; auto &cat2 = f.front()["cat_2"];
auto &cat3 = f.front()["cat_3"]; auto &cat3 = f.front()["cat_3"];
// TODO: enable test cat3.update_value("name"_key == "aap" and "num"_key == 1, "name", "aapje");
// cat3.update_value("name"_key == "aap" and "num"_key == 1, "name", "aapje");
BOOST_CHECK_EQUAL(cat3.size(), 2);
BOOST_CHECK(cat3.size() == 2);
{ {
int id, num; int id, num;
std::string name; std::string name;
cif::v2::tie(id, name, num) = cat3.front().get("id", "name", "num"); cif::v2::tie(id, name, num) = cat3.front().get("id", "name", "num");
BOOST_CHECK(id == 1); BOOST_CHECK_EQUAL(id, 1);
BOOST_CHECK(num == 1); BOOST_CHECK_EQUAL(num, 1);
BOOST_CHECK(name == "aapje"); BOOST_CHECK_EQUAL(name, "aapje");
cif::v2::tie(id, name, num) = cat3.back().get("id", "name", "num"); cif::v2::tie(id, name, num) = cat3.back().get("id", "name", "num");
BOOST_CHECK(id == 2); BOOST_CHECK_EQUAL(id, 2);
BOOST_CHECK(num == 2); BOOST_CHECK_EQUAL(num, 2);
BOOST_CHECK(name == "aap"); BOOST_CHECK_EQUAL(name, "aap");
} }
int i = 0; int i = 0;
...@@ -1765,24 +1763,24 @@ _cat_3.num ...@@ -1765,24 +1763,24 @@ _cat_3.num
switch (++i) switch (++i)
{ {
case 1: case 1:
BOOST_CHECK(id == 1); BOOST_CHECK_EQUAL(id, 1);
BOOST_CHECK(num == 1); BOOST_CHECK_EQUAL(num, 1);
BOOST_CHECK(name == "aapje"); BOOST_CHECK_EQUAL(name, "aapje");
BOOST_CHECK(desc == "Een dier"); BOOST_CHECK_EQUAL(desc, "Een dier");
break; break;
case 2: case 2:
BOOST_CHECK(id == 2); BOOST_CHECK_EQUAL(id, 2);
BOOST_CHECK(num == 2); BOOST_CHECK_EQUAL(num, 2);
BOOST_CHECK(name == "aap"); BOOST_CHECK_EQUAL(name, "aap");
BOOST_CHECK(desc == "Een andere aap"); BOOST_CHECK_EQUAL(desc, "Een andere aap");
break; break;
case 3: case 3:
BOOST_CHECK(id == 3); BOOST_CHECK_EQUAL(id, 3);
BOOST_CHECK(num == 1); BOOST_CHECK_EQUAL(num, 1);
BOOST_CHECK(name == "noot"); BOOST_CHECK_EQUAL(name, "noot");
BOOST_CHECK(desc == "walnoot bijvoorbeeld"); BOOST_CHECK_EQUAL(desc, "walnoot bijvoorbeeld");
break; break;
default: default:
...@@ -1790,34 +1788,34 @@ _cat_3.num ...@@ -1790,34 +1788,34 @@ _cat_3.num
} }
} }
BOOST_CHECK(cat1.size() == 4); BOOST_CHECK_EQUAL(cat1.size(), 4);
i = 0; i = 0;
for (const auto &[id, name, desc] : cat1.rows<int, std::string, std::string>("id", "name", "desc")) for (const auto &[id, name, desc] : cat1.rows<int, std::string, std::string>("id", "name", "desc"))
{ {
switch (++i) switch (++i)
{ {
case 1: case 1:
BOOST_CHECK(id == 1); BOOST_CHECK_EQUAL(id, 1);
BOOST_CHECK(name == "aapje"); BOOST_CHECK_EQUAL(name, "aapje");
BOOST_CHECK(desc == "Aap"); BOOST_CHECK_EQUAL(desc, "Aap");
break; break;
case 2: case 2:
BOOST_CHECK(id == 2); BOOST_CHECK_EQUAL(id, 2);
BOOST_CHECK(name == "noot"); BOOST_CHECK_EQUAL(name, "noot");
BOOST_CHECK(desc == "Noot"); BOOST_CHECK_EQUAL(desc, "Noot");
break; break;
case 3: case 3:
BOOST_CHECK(id == 3); BOOST_CHECK_EQUAL(id, 3);
BOOST_CHECK(name == "mies"); BOOST_CHECK_EQUAL(name, "mies");
BOOST_CHECK(desc == "Mies"); BOOST_CHECK_EQUAL(desc, "Mies");
break; break;
case 4: case 4:
BOOST_CHECK(id == 4); BOOST_CHECK_EQUAL(id, 4);
BOOST_CHECK(name == "aap"); BOOST_CHECK_EQUAL(name, "aap");
BOOST_CHECK(desc == "Aap"); BOOST_CHECK_EQUAL(desc, "Aap");
break; break;
default: default:
...@@ -2094,3 +2092,71 @@ BOOST_AUTO_TEST_CASE(reading_file_1) ...@@ -2094,3 +2092,71 @@ BOOST_AUTO_TEST_CASE(reading_file_1)
// BOOST_CHECK_EQUAL(text, kS[i++].s); // BOOST_CHECK_EQUAL(text, kS[i++].s);
// } // }
// } // }
BOOST_AUTO_TEST_CASE(trim_test)
{
BOOST_CHECK_EQUAL(cif::trim_copy("aap"), "aap");
BOOST_CHECK_EQUAL(cif::trim_copy(" aap"), "aap");
BOOST_CHECK_EQUAL(cif::trim_copy(" aap "), "aap");
BOOST_CHECK_EQUAL(cif::trim_copy("aap "), "aap");
BOOST_CHECK_EQUAL(cif::trim_copy(" aap "), "aap");
BOOST_CHECK_EQUAL(cif::trim_left_copy("aap"), "aap");
BOOST_CHECK_EQUAL(cif::trim_left_copy(" aap"), "aap");
BOOST_CHECK_EQUAL(cif::trim_left_copy(" aap "), "aap ");
BOOST_CHECK_EQUAL(cif::trim_left_copy("aap "), "aap ");
BOOST_CHECK_EQUAL(cif::trim_left_copy("aap "), "aap ");
BOOST_CHECK_EQUAL(cif::trim_right_copy("aap"), "aap");
BOOST_CHECK_EQUAL(cif::trim_right_copy(" aap"), " aap");
BOOST_CHECK_EQUAL(cif::trim_right_copy(" aap "), " aap");
BOOST_CHECK_EQUAL(cif::trim_right_copy("aap "), "aap");
BOOST_CHECK_EQUAL(cif::trim_right_copy(" aap "), " aap");
std::string s;
s = "aap"; cif::trim(s); BOOST_CHECK_EQUAL(s, "aap");
s = " aap"; cif::trim(s); BOOST_CHECK_EQUAL(s, "aap");
s = " aap "; cif::trim(s); BOOST_CHECK_EQUAL(s, "aap");
s = "aap "; cif::trim(s); BOOST_CHECK_EQUAL(s, "aap");
s = " aap "; cif::trim(s); BOOST_CHECK_EQUAL(s, "aap");
s = "aap"; cif::trim_left(s); BOOST_CHECK_EQUAL(s, "aap");
s = " aap"; cif::trim_left(s); BOOST_CHECK_EQUAL(s, "aap");
s = " aap "; cif::trim_left(s); BOOST_CHECK_EQUAL(s, "aap ");
s = "aap "; cif::trim_left(s); BOOST_CHECK_EQUAL(s, "aap ");
s = "aap "; cif::trim_left(s); BOOST_CHECK_EQUAL(s, "aap ");
s = "aap"; cif::trim_right(s); BOOST_CHECK_EQUAL(s, "aap");
s = " aap"; cif::trim_right(s); BOOST_CHECK_EQUAL(s, " aap");
s = " aap "; cif::trim_right(s); BOOST_CHECK_EQUAL(s, " aap");
s = "aap "; cif::trim_right(s); BOOST_CHECK_EQUAL(s, "aap");
s = " aap "; cif::trim_right(s); BOOST_CHECK_EQUAL(s, " aap");
}
BOOST_AUTO_TEST_CASE(split_test)
{
std::vector<std::string_view> v, t;
v = cif::split<>("aap;noot;mies", ";");
t = std::vector<std::string_view>{ "aap", "noot", "mies" };
BOOST_CHECK(v == t);
v = cif::split("aap;noot,mies", ";,");
// t = std::vector<std::string>{ "aap", "noot", "mies" };
BOOST_CHECK(v == t);
v = cif::split(";aap;noot,mies;", ";,");
t = std::vector<std::string_view>{ "", "aap", "noot", "mies", "" };
BOOST_CHECK(v == t);
v = cif::split(";aap;noot,mies;", ";,", true);
t = std::vector<std::string_view>{ "aap", "noot", "mies" };
BOOST_CHECK(v == t);
}
\ No newline at end of file
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment