Skip to content

L
libcifpp
Commit 93375a50 by Maarten L. Hekkelman Committed by GitHub
Options

Develop (#54) 

* - renamed exists to contains
- fix compare for ints where item is empty

* - checking and optionally dropping ndb_poly_seq_scheme
- fix in iterator_proxy

* formatting data in reconstruction

* Version bump

* Attempt to get code compiling on macOS

* attempt 2 to build on macOS

* Added remove column

* Added rename_column
Added item_alias
Rename columns in reconstruct

* macOS...

* Fixed serious bug in emplace of both datablock and file.

* renaming field and column to item

* replace tag with item or item_name

* Fix validate pdbx

* version bump

* atom_site_anisotrop check

* - changed compound::is_known_peptide/is_know_base
- Add audit_conform only if file is really valid
- Added reconstruction code for PDBx

* pdb2cif work

* gcc diagnostics and clipper

* Fixing pdb2cif, and sequence checking

* work around bug in old gcc

* fix reconstruct sequence

* formatting

* some small optimisations

* Fix url in compound message

* Fix operator= for item_handle

* Fix operator= for item_handle

* new update_value in category

* test builds faster now

* Use Catch2 version 3 if installed

* catch22
parent 22537c0e
Showing with 1097 additions and 536 deletions
.gitignore
......@@ -11,4 +11,5 @@ Testing/
include/cif++/exports.hpp
docs/api
docs/conf.py
build_ci/
\ No newline at end of file
build_ci/
data/components.cif
CMakeLists.txt
......@@ -27,7 +27,7 @@ cmake_minimum_required(VERSION 3.16)
# set the project name
project(
libcifpp
VERSION 6.1.0
VERSION 7.0.0
LANGUAGES CXX)
list(PREPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_SOURCE_DIR}/cmake")
......@@ -546,55 +546,7 @@ if(NOT PROJECT_IS_TOP_LEVEL)
endif()
if(BUILD_TESTING)
# We're using the older version 2 of Catch2
FetchContent_Declare(
Catch2
GIT_REPOSITORY https://github.com/catchorg/Catch2.git
GIT_TAG v2.13.9)
FetchContent_MakeAvailable(Catch2)
list(
APPEND
CIFPP_tests
unit-v2
unit-3d
format
model
rename-compound
sugar
spinner
validate-pdbx)
foreach(CIFPP_TEST IN LISTS CIFPP_tests)
set(CIFPP_TEST "${CIFPP_TEST}-test")
set(CIFPP_TEST_SOURCE "${CMAKE_CURRENT_SOURCE_DIR}/test/${CIFPP_TEST}.cpp")
add_executable(
${CIFPP_TEST} ${CIFPP_TEST_SOURCE}
"${CMAKE_CURRENT_SOURCE_DIR}/test/test-main.cpp")
target_link_libraries(${CIFPP_TEST} PRIVATE Threads::Threads cifpp::cifpp
Catch2::Catch2)
target_include_directories(${CIFPP_TEST} PRIVATE "${EIGEN_INCLUDE_DIR}")
if(MSVC)
# Specify unwind semantics so that MSVC knowns how to handle exceptions
target_compile_options(${CIFPP_TEST} PRIVATE /EHsc)
endif()
add_custom_target(
"run-${CIFPP_TEST}"
DEPENDS ${CMAKE_CURRENT_BINARY_DIR}/Run${CIFPP_TEST}.touch ${CIFPP_TEST})
add_custom_command(
OUTPUT ${CMAKE_CURRENT_BINARY_DIR}/Run${CIFPP_TEST}.touch
COMMAND $<TARGET_FILE:${CIFPP_TEST}> --data-dir
${CMAKE_CURRENT_SOURCE_DIR}/test)
add_test(NAME ${CIFPP_TEST} COMMAND $<TARGET_FILE:${CIFPP_TEST}> --data-dir
${CMAKE_CURRENT_SOURCE_DIR}/test)
endforeach()
add_subdirectory(test)
endif()
# Optionally install the update scripts for CCD and dictionary files
......
changelog
Version 7.0.0
- Renaming many methods and parameters to be more
consistent with the mmCIF dictionaries.
(Most notably, item used to be called column or
tag sometimes).
- validation_error is now a std::system_error error
value. The exception is gone.
- Added repairSequenceInfo to repair invalid files
Version 6.1.0
- Add formula weight to entity in pdb2cif
- Change order of categories inside a datablock to match order in file
......
include/cif++/compound.hpp
......@@ -166,6 +166,12 @@ class compound
return m_id == "HOH" or m_id == "H2O" or m_id == "WAT";
}
/** \brief Return whether this compound has a type of either 'peptide linking' or 'L-peptide linking' */
bool is_peptide() const;
/** \brief Return whether this compound has a type of either 'DNA linking' or 'RNA linking' */
bool is_base() const;
char one_letter_code() const { return m_one_letter_code; }; ///< Return the one letter code to use in a canonical sequence. If unknown the value '\0' is returned
std::string parent_id() const { return m_parent_id; }; ///< Return the parent id code in case a parent is specified (e.g. MET for MSE)
......@@ -237,25 +243,53 @@ class compound_factory
void pop_dictionary();
/// Return whether @a res_name is a valid and known peptide
[[deprecated("use is_peptide or is_std_peptide instead)")]]
bool is_known_peptide(const std::string &res_name) const;
/// Return whether @a res_name is a valid and known base
[[deprecated("use is_base or is_std_base instead)")]]
bool is_known_base(const std::string &res_name) const;
/// Return whether @a res_name is a peptide
bool is_peptide(std::string_view res_name) const;
/// Return whether @a res_name is a base
bool is_base(std::string_view res_name) const;
/// Return whether @a res_name is one of the standard peptides
bool is_std_peptide(std::string_view res_name) const;
/// Return whether @a res_name is one of the standard bases
bool is_std_base(std::string_view res_name) const;
/// Return whether @a res_name is a monomer (either base or peptide)
bool is_monomer(std::string_view res_name) const;
/// Return whether @a res_name is one of the standard bases or peptides
bool is_std_monomer(std::string_view res_name) const
{
return is_std_base(res_name) or is_std_peptide(res_name);
}
bool is_water(std::string_view res_name) const
{
return res_name == "HOH" or res_name == "H2O" or res_name == "WAT";
}
/// \brief Create the compound object for \a id
///
/// This will create the compound instance for \a id if it doesn't exist already.
/// The result is owned by this factory and should not be deleted by the user.
/// \param id The compound ID, a three letter code usually
/// \result The compound, or nullptr if it could not be created (missing info)
const compound *create(std::string id);
const compound *create(std::string_view id);
~compound_factory();
CIFPP_EXPORT static const std::map<std::string, char> kAAMap, ///< Globally accessible static list of the default amino acids
kBaseMap; ///< Globally accessible static list of the default bases
void report_missing_compound(const std::string &compound_id);
void report_missing_compound(std::string_view compound_id);
private:
compound_factory();
......
include/cif++/datablock.hpp
......@@ -107,6 +107,15 @@ class datablock : public std::list<category>
bool is_valid() const;
/**
* @brief Validates the content of this datablock and all its content
* and updates or removes the audit_conform category to match the result.
*
* @return true If the content is valid
* @return false If the content is not valid
*/
bool is_valid();
/**
* @brief Validates all contained data for valid links between parents and children
* as defined in the validator
*
......@@ -169,7 +178,16 @@ class datablock : public std::list<category>
/**
* @brief Get the preferred order of the categories when writing them
*/
std::vector<std::string> get_tag_order() const;
[[deprecated("use get_item_order instead")]]
std::vector<std::string> get_tag_order() const
{
return get_item_order();
}
/**
* @brief Get the preferred order of the categories when writing them
*/
std::vector<std::string> get_item_order() const;
/**
* @brief Write out the contents to @a os
......@@ -177,9 +195,9 @@ class datablock : public std::list<category>
void write(std::ostream &os) const;
/**
* @brief Write out the contents to @a os using the order defined in @a tag_order
* @brief Write out the contents to @a os using the order defined in @a item_name_order
*/
void write(std::ostream &os, const std::vector<std::string> &tag_order);
void write(std::ostream &os, const std::vector<std::string> &item_name_order);
/**
* @brief Friend operator<< to write datablock @a db to std::ostream @a os
......
include/cif++/item.hpp
......@@ -44,7 +44,7 @@
/** \file item.hpp
*
* This file contains the declaration of item but also the item_value and item_handle
* These handle the storage of and access to the data for a single data field.
* These handle the storage of and access to the data for a single data item.
*/
namespace cif
......@@ -120,8 +120,6 @@ class item
if (r.ec != std::errc())
throw std::runtime_error("Could not format number");
assert(r.ptr >= buffer and r.ptr < buffer + sizeof(buffer));
*r.ptr = 0;
m_value.assign(buffer, r.ptr - buffer);
}
......@@ -141,8 +139,6 @@ class item
if (r.ec != std::errc())
throw std::runtime_error("Could not format number");
assert(r.ptr >= buffer and r.ptr < buffer + sizeof(buffer));
*r.ptr = 0;
m_value.assign(buffer, r.ptr - buffer);
}
......@@ -158,8 +154,6 @@ class item
if (r.ec != std::errc())
throw std::runtime_error("Could not format number");
assert(r.ptr >= buffer and r.ptr < buffer + sizeof(buffer));
*r.ptr = 0;
m_value.assign(buffer, r.ptr - buffer);
}
......@@ -174,13 +168,22 @@ class item
/// \brief constructor for an item with name \a name and as
/// content value \a value
item(const std::string_view name, const std::string_view value)
item(const std::string_view name, std::string_view value)
: m_name(name)
, m_value(value)
{
}
/// \brief constructor for an item with name \a name and as
/// content value \a value
template<typename T, std::enable_if_t<std::is_same_v<T, std::string>, int> = 0>
item(const std::string_view name, T &&value)
: m_name(name)
, m_value(std::move(value))
{
}
/// \brief constructor for an item with name \a name and as
/// content the optional value \a value
template <typename T>
item(const std::string_view name, const std::optional<T> &value)
......@@ -219,7 +222,8 @@ class item
/** @endcond */
std::string_view name() const { return m_name; } ///< Return the name of the item
std::string_view value() const { return m_value; } ///< Return the value of the item
std::string_view value() const & { return m_value; } ///< Return the value of the item
std::string value() const && { return std::move(m_value); } ///< Return the value of the item
/// \brief replace the content of the stored value with \a v
void value(std::string_view v) { m_value = v; }
......@@ -227,10 +231,10 @@ class item
/// \brief empty means either null or unknown
bool empty() const { return m_value.empty(); }
/// \brief returns true if the field contains '.'
/// \brief returns true if the item contains '.'
bool is_null() const { return m_value == "."; }
/// \brief returns true if the field contains '?'
/// \brief returns true if the item contains '?'
bool is_unknown() const { return m_value == "?"; }
/// \brief the length of the value string
......@@ -363,8 +367,35 @@ struct item_handle
template <typename T>
item_handle &operator=(const T &value)
{
item v{ "", value };
assign_value(v);
assign_value(item{ "", value }.value());
return *this;
}
/**
* @brief Assign value @a value to the item referenced
*
* @tparam T Type of the value
* @param value The value
* @return reference to this item_handle
*/
template <typename T>
item_handle &operator=(T &&value)
{
assign_value(item{ "", std::move(value) }.value());
return *this;
}
/**
* @brief Assign value @a value to the item referenced
*
* @tparam T Type of the value
* @param value The value
* @return reference to this item_handle
*/
template <size_t N>
item_handle &operator=(const char (&value)[N])
{
assign_value(item{ "", std::move(value) }.value());
return *this;
}
......@@ -464,14 +495,14 @@ struct item_handle
/** Easy way to test for an empty item */
explicit operator bool() const { return not empty(); }
/// is_null return true if the field contains '.'
/// is_null return true if the item contains '.'
bool is_null() const
{
auto txt = text();
return txt.length() == 1 and txt.front() == '.';
}
/// is_unknown returns true if the field contains '?'
/// is_unknown returns true if the item contains '?'
bool is_unknown() const
{
auto txt = text();
......@@ -484,11 +515,11 @@ struct item_handle
/**
* @brief Construct a new item handle object
*
* @param column Column index
* @param item Item index
* @param row Reference to the row
*/
item_handle(uint16_t column, row_handle &row)
: m_column(column)
item_handle(uint16_t item, row_handle &row)
: m_item_ix(item)
, m_row_handle(row)
{
}
......@@ -505,10 +536,10 @@ struct item_handle
private:
item_handle();
uint16_t m_column;
uint16_t m_item_ix;
row_handle &m_row_handle;
void assign_value(const item &value);
void assign_value(std::string_view value);
};
// So sad that older gcc implementations of from_chars did not support floats yet...
......@@ -556,7 +587,7 @@ struct item_handle::item_value_as<T, std::enable_if_t<std::is_arithmetic_v<T> an
auto txt = ref.text();
if (txt.empty())
if (ref.empty())
result = 1;
else
{
......
include/cif++/iterator.hpp
......@@ -90,7 +90,7 @@ class iterator_impl
: m_category(rhs.m_category)
, m_current(rhs.m_current)
, m_value(rhs.m_value)
, m_column_ix(rhs.m_column_ix)
, m_item_ix(rhs.m_item_ix)
{
}
......@@ -99,7 +99,7 @@ class iterator_impl
: m_category(rhs.m_category)
, m_current(const_cast<row_type *>(rhs.m_current))
, m_value(rhs.m_value)
, m_column_ix(rhs.m_column_ix)
, m_item_ix(rhs.m_item_ix)
{
m_value = get(std::make_index_sequence<N>());
}
......@@ -108,7 +108,7 @@ class iterator_impl
iterator_impl(const iterator_impl<IRowType> &rhs, const std::array<uint16_t, N> &cix)
: m_category(rhs.m_category)
, m_current(rhs.m_current)
, m_column_ix(cix)
, m_item_ix(cix)
{
m_value = get(std::make_index_sequence<N>());
}
......@@ -117,7 +117,7 @@ class iterator_impl
{
m_category = i.m_category;
m_current = i.m_current;
m_column_ix = i.m_column_ix;
m_item_ix = i.m_item_ix;
m_value = i.m_value;
return *this;
}
......@@ -185,7 +185,7 @@ class iterator_impl
if (m_current != nullptr)
{
row_handle rh{ *m_category, *m_current };
return tuple_type{ rh[m_column_ix[Is]].template as<Ts>()... };
return tuple_type{ rh[m_item_ix[Is]].template as<Ts>()... };
}
return {};
......@@ -194,7 +194,7 @@ class iterator_impl
category_type *m_category = nullptr;
row_type *m_current = nullptr;
value_type m_value;
std::array<uint16_t, N> m_column_ix;
std::array<uint16_t, N> m_item_ix;
};
/**
......@@ -348,7 +348,7 @@ class iterator_impl<Category, T>
: m_category(rhs.m_category)
, m_current(rhs.m_current)
, m_value(rhs.m_value)
, m_column_ix(rhs.m_column_ix)
, m_item_ix(rhs.m_item_ix)
{
}
......@@ -357,7 +357,7 @@ class iterator_impl<Category, T>
: m_category(rhs.m_category)
, m_current(const_cast<row_type *>(rhs.m_current))
, m_value(rhs.m_value)
, m_column_ix(rhs.m_column_ix)
, m_item_ix(rhs.m_item_ix)
{
m_value = get(m_current);
}
......@@ -366,7 +366,7 @@ class iterator_impl<Category, T>
iterator_impl(const iterator_impl<IRowType> &rhs, const std::array<uint16_t, 1> &cix)
: m_category(rhs.m_category)
, m_current(rhs.m_current)
, m_column_ix(cix[0])
, m_item_ix(cix[0])
{
m_value = get();
}
......@@ -375,7 +375,7 @@ class iterator_impl<Category, T>
{
m_category = i.m_category;
m_current = i.m_current;
m_column_ix = i.m_column_ix;
m_item_ix = i.m_item_ix;
m_value = i.m_value;
return *this;
}
......@@ -442,7 +442,7 @@ class iterator_impl<Category, T>
if (m_current != nullptr)
{
row_handle rh{ *m_category, *m_current };
return rh[m_column_ix].template as<T>();
return rh[m_item_ix].template as<T>();
}
return {};
......@@ -451,7 +451,7 @@ class iterator_impl<Category, T>
category_type *m_category = nullptr;
row_type *m_current = nullptr;
value_type m_value;
uint16_t m_column_ix;
uint16_t m_item_ix;
};
// --------------------------------------------------------------------
......@@ -482,8 +482,8 @@ class iterator_proxy
using iterator = iterator_impl<category_type, Ts...>;
using row_iterator = iterator_impl<category_type>;
iterator_proxy(category_type &cat, row_iterator pos, char const *const columns[N]);
iterator_proxy(category_type &cat, row_iterator pos, std::initializer_list<char const *> columns);
iterator_proxy(category_type &cat, row_iterator pos, char const *const items[N]);
iterator_proxy(category_type &cat, row_iterator pos, std::initializer_list<char const *> items);
iterator_proxy(iterator_proxy &&p);
iterator_proxy &operator=(iterator_proxy &&p);
......@@ -492,8 +492,8 @@ class iterator_proxy
iterator_proxy &operator=(const iterator_proxy &) = delete;
/** @endcond */
iterator begin() const { return iterator(m_begin, m_column_ix); } ///< Return the iterator pointing to the first row
iterator end() const { return iterator(m_end, m_column_ix); } ///< Return the iterator pointing past the last row
iterator begin() const { return iterator(m_begin, m_item_ix); } ///< Return the iterator pointing to the first row
iterator end() const { return iterator(m_end, m_item_ix); } ///< Return the iterator pointing past the last row
bool empty() const { return m_begin == m_end; } ///< Return true if the range is empty
explicit operator bool() const { return not empty(); } ///< Easy way to detect if the range is empty
......@@ -510,13 +510,13 @@ class iterator_proxy
std::swap(m_category, rhs.m_category);
std::swap(m_begin, rhs.m_begin);
std::swap(m_end, rhs.m_end);
std::swap(m_column_ix, rhs.m_column_ix);
std::swap(m_item_ix, rhs.m_item_ix);
}
private:
category_type *m_category;
row_iterator m_begin, m_end;
std::array<uint16_t, N> m_column_ix;
std::array<uint16_t, N> m_item_ix;
};
// --------------------------------------------------------------------
......@@ -562,22 +562,23 @@ class conditional_iterator_proxy
reference operator*()
{
return *mBegin;
return *m_begin;
}
pointer operator->()
{
return &*mBegin;
m_current = *m_begin;
return &m_current;
}
conditional_iterator_impl &operator++()
{
while (mBegin != mEnd)
while (m_begin != m_end)
{
if (++mBegin == mEnd)
if (++m_begin == m_end)
break;
if (m_condition->operator()(mBegin))
if (m_condition->operator()(m_begin))
break;
}
......@@ -591,18 +592,22 @@ class conditional_iterator_proxy
return result;
}
bool operator==(const conditional_iterator_impl &rhs) const { return mBegin == rhs.mBegin; }
bool operator!=(const conditional_iterator_impl &rhs) const { return mBegin != rhs.mBegin; }
bool operator==(const conditional_iterator_impl &rhs) const { return m_begin == rhs.m_begin; }
bool operator!=(const conditional_iterator_impl &rhs) const { return m_begin != rhs.m_begin; }
bool operator==(const row_iterator &rhs) const { return m_begin == rhs; }
bool operator!=(const row_iterator &rhs) const { return m_begin != rhs; }
template <typename IRowType, typename... ITs>
bool operator==(const iterator_impl<IRowType, ITs...> &rhs) const { return mBegin == rhs; }
bool operator==(const iterator_impl<IRowType, ITs...> &rhs) const { return m_begin == rhs; }
template <typename IRowType, typename... ITs>
bool operator!=(const iterator_impl<IRowType, ITs...> &rhs) const { return mBegin != rhs; }
bool operator!=(const iterator_impl<IRowType, ITs...> &rhs) const { return m_begin != rhs; }
private:
CategoryType *mCat;
base_iterator mBegin, mEnd;
CategoryType *m_cat;
base_iterator m_begin, m_end;
value_type m_current;
const condition *m_condition;
};
......@@ -646,26 +651,26 @@ class conditional_iterator_proxy
/** @cond */
template <typename Category, typename... Ts>
iterator_proxy<Category, Ts...>::iterator_proxy(Category &cat, row_iterator pos, char const *const columns[N])
iterator_proxy<Category, Ts...>::iterator_proxy(Category &cat, row_iterator pos, char const *const items[N])
: m_category(&cat)
, m_begin(pos)
, m_end(cat.end())
{
for (uint16_t i = 0; i < N; ++i)
m_column_ix[i] = m_category->get_column_ix(columns[i]);
m_item_ix[i] = m_category->get_item_ix(items[i]);
}
template <typename Category, typename... Ts>
iterator_proxy<Category, Ts...>::iterator_proxy(Category &cat, row_iterator pos, std::initializer_list<char const *> columns)
iterator_proxy<Category, Ts...>::iterator_proxy(Category &cat, row_iterator pos, std::initializer_list<char const *> items)
: m_category(&cat)
, m_begin(pos)
, m_end(cat.end())
{
// static_assert(columns.size() == N, "The list of column names should be exactly the same as the list of requested columns");
// static_assert(items.size() == N, "The list of item names should be exactly the same as the list of requested items");
std::uint16_t i = 0;
for (auto column : columns)
m_column_ix[i++] = m_category->get_column_ix(column);
for (auto item : items)
m_item_ix[i++] = m_category->get_item_ix(item);
}
// --------------------------------------------------------------------
......@@ -673,13 +678,13 @@ iterator_proxy<Category, Ts...>::iterator_proxy(Category &cat, row_iterator pos,
template <typename Category, typename... Ts>
conditional_iterator_proxy<Category, Ts...>::conditional_iterator_impl::conditional_iterator_impl(
Category &cat, row_iterator pos, const condition &cond, const std::array<uint16_t, N> &cix)
: mCat(&cat)
, mBegin(pos, cix)
, mEnd(cat.end(), cix)
: m_cat(&cat)
, m_begin(pos, cix)
, m_end(cat.end(), cix)
, m_condition(&cond)
{
if (m_condition == nullptr or m_condition->empty())
mBegin = mEnd;
m_begin = m_end;
}
template <typename Category, typename... Ts>
......@@ -702,7 +707,7 @@ conditional_iterator_proxy<Category, Ts...>::conditional_iterator_proxy(Category
, mCBegin(pos)
, mCEnd(cat.end())
{
static_assert(sizeof...(Ts) == sizeof...(Ns), "Number of column names should be equal to number of requested value types");
static_assert(sizeof...(Ts) == sizeof...(Ns), "Number of item names should be equal to number of requested value types");
if (m_condition)
{
......@@ -715,7 +720,7 @@ conditional_iterator_proxy<Category, Ts...>::conditional_iterator_proxy(Category
mCBegin = mCEnd;
uint16_t i = 0;
((mCix[i++] = m_cat->get_column_ix(names)), ...);
((mCix[i++] = m_cat->get_item_ix(names)), ...);
}
template <typename Category, typename... Ts>
......
include/cif++/model.hpp
......@@ -72,7 +72,7 @@ class structure;
*
* The class atom is a kind of flyweight class. It can be copied
* with low overhead. All data is stored in the underlying mmCIF
* categories but some very often used fields are cached in the
* categories but some very often used items are cached in the
* impl.
*
* It is also possible to have symmetry copies of atoms. They
......@@ -207,7 +207,7 @@ class atom
/// \brief Copy assignement operator
atom &operator=(const atom &rhs) = default;
/// \brief Return the field named @a name in the _atom_site category for this atom
/// \brief Return the item named @a name in the _atom_site category for this atom
std::string get_property(std::string_view name) const
{
if (not m_impl)
......@@ -215,7 +215,7 @@ class atom
return m_impl->get_property(name);
}
/// \brief Return the field named @a name in the _atom_site category for this atom cast to an int
/// \brief Return the item named @a name in the _atom_site category for this atom cast to an int
int get_property_int(std::string_view name) const
{
if (not m_impl)
......@@ -223,7 +223,7 @@ class atom
return m_impl->get_property_int(name);
}
/// \brief Return the field named @a name in the _atom_site category for this atom cast to a float
/// \brief Return the item named @a name in the _atom_site category for this atom cast to a float
float get_property_float(std::string_view name) const
{
if (not m_impl)
......@@ -231,7 +231,7 @@ class atom
return m_impl->get_property_float(name);
}
/// \brief Set value for the field named @a name in the _atom_site category to @a value
/// \brief Set value for the item named @a name in the _atom_site category to @a value
void set_property(const std::string_view name, const std::string &value)
{
if (not m_impl)
......@@ -239,7 +239,7 @@ class atom
m_impl->set_property(name, value);
}
/// \brief Set value for the field named @a name in the _atom_site category to @a value
/// \brief Set value for the item named @a name in the _atom_site category to @a value
template <typename T, std::enable_if_t<std::is_arithmetic_v<T>, int> = 0>
void set_property(const std::string_view name, const T &value)
{
......@@ -730,7 +730,7 @@ class sugar : public residue
/**
* @brief Return the sugar number in the glycosylation tree
*
* To store the sugar number, the auth_seq_id field has been overloaded
* To store the sugar number, the auth_seq_id item has been overloaded
* in the specification. But since a sugar number should be, ehm, a number
* and auth_seq_id is specified to contain a string, we do a check here
* to see if it really is a number.
......
include/cif++/parser.hpp
......@@ -143,9 +143,9 @@ class sac_parser
enum class CIFToken
{
Unknown,
UNKNOWN,
Eof,
END_OF_FILE,
DATA,
LOOP,
......@@ -153,24 +153,24 @@ class sac_parser
SAVE_,
SAVE_NAME,
STOP,
Tag,
Value
ITEM_NAME,
VALUE
};
static constexpr const char *get_token_name(CIFToken token)
{
switch (token)
{
case CIFToken::Unknown: return "Unknown";
case CIFToken::Eof: return "Eof";
case CIFToken::UNKNOWN: return "Unknown";
case CIFToken::END_OF_FILE: return "Eof";
case CIFToken::DATA: return "DATA";
case CIFToken::LOOP: return "LOOP";
case CIFToken::GLOBAL: return "GLOBAL";
case CIFToken::SAVE_: return "SAVE";
case CIFToken::SAVE_NAME: return "SAVE+name";
case CIFToken::STOP: return "STOP";
case CIFToken::Tag: return "Tag";
case CIFToken::Value: return "Value";
case CIFToken::ITEM_NAME: return "Tag";
case CIFToken::VALUE: return "Value";
default: return "Invalid token parameter";
}
}
......@@ -267,9 +267,9 @@ class sac_parser
QuotedString,
QuotedStringQuote,
UnquotedString,
Tag,
TextField,
TextFieldNL,
ItemName,
TextItem,
TextItemNL,
Reserved,
Value
};
......
include/cif++/pdb.hpp
......@@ -28,6 +28,8 @@
#include "cif++/file.hpp"
#include <system_error>
/**
* @file pdb.hpp
*
......@@ -107,9 +109,10 @@ inline void write(const std::filesystem::path &p, const file &f)
*
* \param file The cif::file that hopefully contains some valid data
* \param dictionary The mmcif dictionary to use
* \result Returns true if the resulting file is valid
*/
void reconstruct_pdbx(file &pdbx_file, std::string_view dictionary = "mmcif_pdbx");
bool reconstruct_pdbx(file &pdbx_file, std::string_view dictionary = "mmcif_pdbx");
/** \brief This is an extension to cif::validator, use the logic in common
* PDBx files to see if the file is internally consistent.
......@@ -119,6 +122,8 @@ void reconstruct_pdbx(file &pdbx_file, std::string_view dictionary = "mmcif_pdbx
* atom_site -> pdbx_poly_seq_scheme -> entity_poly_seq -> entity_poly -> entity
*
* Use the common \ref cif::VERBOSE flag to turn on diagnostic messages.
*
* This function throws a std::system_error in case of an error
*
* \param file The input file
* \param dictionary The mmcif dictionary to use
......@@ -127,6 +132,43 @@ void reconstruct_pdbx(file &pdbx_file, std::string_view dictionary = "mmcif_pdbx
bool is_valid_pdbx_file(const file &pdbx_file, std::string_view dictionary = "mmcif_pdbx");
/** \brief This is an extension to cif::validator, use the logic in common
* PDBx files to see if the file is internally consistent.
*
* This function for now checks if the following categories are consistent:
*
* atom_site -> pdbx_poly_seq_scheme -> entity_poly_seq -> entity_poly -> entity
*
* Use the common \ref cif::VERBOSE flag to turn on diagnostic messages.
*
* The dictionary is assumed to be specified in the file or to be the
* default mmcif_pdbx.dic dictionary.
*
* \param file The input file
* \param ec The error_code in case something was wrong
* \result Returns true if the file was valid and consistent
*/
bool is_valid_pdbx_file(const file &pdbx_file, std::error_code &ec);
/** \brief This is an extension to cif::validator, use the logic in common
* PDBx files to see if the file is internally consistent.
*
* This function for now checks if the following categories are consistent:
*
* atom_site -> pdbx_poly_seq_scheme -> entity_poly_seq -> entity_poly -> entity
*
* Use the common \ref cif::VERBOSE flag to turn on diagnostic messages.
*
* \param file The input file
* \param dictionary The dictionary to use
* \param ec The error_code in case something was wrong
* \result Returns true if the file was valid and consistent
*/
bool is_valid_pdbx_file(const file &pdbx_file, std::string_view dictionary,
std::error_code &ec);
// --------------------------------------------------------------------
// Other I/O related routines
......
include/cif++/point.hpp
......@@ -35,7 +35,10 @@
#if __has_include(<clipper/core/coords.h>)
#define HAVE_LIBCLIPPER 1
#pragma GCC diagnostic push
#pragma GCC diagnostic ignored "-Wignored-qualifiers"
#include <clipper/core/coords.h>
#pragma GCC diagnostic pop
#endif
/** \file point.hpp
......
include/cif++/row.hpp
......@@ -51,7 +51,7 @@
* std::string name = rh["label_atom_id"].as<std::string>();
*
* // by index:
* uint16_t ix = atom_site.get_column_ix("label_atom_id");
* uint16_t ix = atom_site.get_item_ix("label_atom_id");
* assert(rh[ix].as<std::string() == name);
* @endcode
*
......@@ -87,15 +87,15 @@ namespace detail
{
static constexpr size_t N = sizeof...(C);
get_row_result(const row_handle &r, std::array<uint16_t, N> &&columns)
get_row_result(const row_handle &r, std::array<uint16_t, N> &&items)
: m_row(r)
, m_columns(std::move(columns))
, m_items(std::move(items))
{
}
const item_handle operator[](uint16_t ix) const
{
return m_row[m_columns[ix]];
return m_row[m_items[ix]];
}
template <typename... Ts, std::enable_if_t<N == sizeof...(Ts), int> = 0>
......@@ -107,11 +107,11 @@ namespace detail
template <typename... Ts, size_t... Is>
std::tuple<Ts...> get(std::index_sequence<Is...>) const
{
return std::tuple<Ts...>{ m_row[m_columns[Is]].template as<Ts>()... };
return std::tuple<Ts...>{ m_row[m_items[Is]].template as<Ts>()... };
}
const row_handle &m_row;
std::array<uint16_t, N> m_columns;
std::array<uint16_t, N> m_items;
};
// we want to be able to tie some variables to a get_row_result, for this we use tiewraps
......@@ -244,70 +244,70 @@ class row_handle
return not empty();
}
/// \brief return a cif::item_handle to the item in column @a column_ix
item_handle operator[](uint16_t column_ix)
/// \brief return a cif::item_handle to the item in item @a item_ix
item_handle operator[](uint16_t item_ix)
{
return empty() ? item_handle::s_null_item : item_handle(column_ix, *this);
return empty() ? item_handle::s_null_item : item_handle(item_ix, *this);
}
/// \brief return a const cif::item_handle to the item in column @a column_ix
const item_handle operator[](uint16_t column_ix) const
/// \brief return a const cif::item_handle to the item in item @a item_ix
const item_handle operator[](uint16_t item_ix) const
{
return empty() ? item_handle::s_null_item : item_handle(column_ix, const_cast<row_handle &>(*this));
return empty() ? item_handle::s_null_item : item_handle(item_ix, const_cast<row_handle &>(*this));
}
/// \brief return a cif::item_handle to the item in the column named @a column_name
item_handle operator[](std::string_view column_name)
/// \brief return a cif::item_handle to the item in the item named @a item_name
item_handle operator[](std::string_view item_name)
{
return empty() ? item_handle::s_null_item : item_handle(add_column(column_name), *this);
return empty() ? item_handle::s_null_item : item_handle(add_item(item_name), *this);
}
/// \brief return a const cif::item_handle to the item in the column named @a column_name
const item_handle operator[](std::string_view column_name) const
/// \brief return a const cif::item_handle to the item in the item named @a item_name
const item_handle operator[](std::string_view item_name) const
{
return empty() ? item_handle::s_null_item : item_handle(get_column_ix(column_name), const_cast<row_handle &>(*this));
return empty() ? item_handle::s_null_item : item_handle(get_item_ix(item_name), const_cast<row_handle &>(*this));
}
/// \brief Return an object that can be used in combination with cif::tie
/// to assign the values for the columns @a columns
/// to assign the values for the items @a items
template <typename... C>
auto get(C... columns) const
auto get(C... items) const
{
return detail::get_row_result<C...>(*this, { get_column_ix(columns)... });
return detail::get_row_result<C...>(*this, { get_item_ix(items)... });
}
/// \brief Return a tuple of values of types @a Ts for the columns @a columns
/// \brief Return a tuple of values of types @a Ts for the items @a items
template <typename... Ts, typename... C, std::enable_if_t<sizeof...(Ts) == sizeof...(C) and sizeof...(C) != 1, int> = 0>
std::tuple<Ts...> get(C... columns) const
std::tuple<Ts...> get(C... items) const
{
return detail::get_row_result<Ts...>(*this, { get_column_ix(columns)... });
return detail::get_row_result<Ts...>(*this, { get_item_ix(items)... });
}
/// \brief Get the value of column @a column cast to type @a T
/// \brief Get the value of item @a item cast to type @a T
template <typename T>
T get(const char *column) const
T get(const char *item) const
{
return operator[](get_column_ix(column)).template as<T>();
return operator[](get_item_ix(item)).template as<T>();
}
/// \brief Get the value of column @a column cast to type @a T
/// \brief Get the value of item @a item cast to type @a T
template <typename T>
T get(std::string_view column) const
T get(std::string_view item) const
{
return operator[](get_column_ix(column)).template as<T>();
return operator[](get_item_ix(item)).template as<T>();
}
/// \brief assign each of the columns named in @a values to their respective value
/// \brief assign each of the items named in @a values to their respective value
void assign(const std::vector<item> &values)
{
for (auto &value : values)
assign(value, true);
}
/** \brief assign the value @a value to the column named @a name
/** \brief assign the value @a value to the item named @a name
*
* If updateLinked it true, linked records are updated as well.
* That means that if column @a name is part of the link definition
* That means that if item @a name is part of the link definition
* and the link results in a linked record in another category
* this record in the linked category is updated as well.
*
......@@ -317,13 +317,13 @@ class row_handle
void assign(std::string_view name, std::string_view value, bool updateLinked, bool validate = true)
{
assign(add_column(name), value, updateLinked, validate);
assign(add_item(name), value, updateLinked, validate);
}
/** \brief assign the value @a value to column at index @a column
/** \brief assign the value @a value to item at index @a item
*
* If updateLinked it true, linked records are updated as well.
* That means that if column @a column is part of the link definition
* That means that if item @a item is part of the link definition
* and the link results in a linked record in another category
* this record in the linked category is updated as well.
*
......@@ -331,7 +331,7 @@ class row_handle
* checked to see if it conforms to the rules defined in the dictionary
*/
void assign(uint16_t column, std::string_view value, bool updateLinked, bool validate = true);
void assign(uint16_t item, std::string_view value, bool updateLinked, bool validate = true);
/// \brief compare two rows
bool operator==(const row_handle &rhs) const { return m_category == rhs.m_category and m_row == rhs.m_row; }
......@@ -340,10 +340,10 @@ class row_handle
bool operator!=(const row_handle &rhs) const { return m_category != rhs.m_category or m_row != rhs.m_row; }
private:
uint16_t get_column_ix(std::string_view name) const;
std::string_view get_column_name(uint16_t ix) const;
uint16_t get_item_ix(std::string_view name) const;
std::string_view get_item_name(uint16_t ix) const;
uint16_t add_column(std::string_view name);
uint16_t add_item(std::string_view name);
row *get_row()
{
......@@ -360,7 +360,7 @@ class row_handle
assign(i.name(), i.value(), updateLinked);
}
void swap(uint16_t column, row_handle &r);
void swap(uint16_t item, row_handle &r);
category *m_category = nullptr;
row *m_row = nullptr;
......
include/cif++/text.hpp
......@@ -317,7 +317,7 @@ inline char tolower(int ch)
// --------------------------------------------------------------------
/** \brief return a tuple consisting of the category and item name for @a tag
/** \brief return a tuple consisting of the category and item name for @a item_name
*
* The category name is stripped of its leading underscore character.
*
......@@ -325,7 +325,19 @@ inline char tolower(int ch)
* cif 1.0 formatted data.
*/
std::tuple<std::string, std::string> split_tag_name(std::string_view tag);
[[deprecated("use split_item_name instead")]]
std::tuple<std::string, std::string> split_tag_name(std::string_view item_name);
/** \brief return a tuple consisting of the category and item name for @a item_name
*
* The category name is stripped of its leading underscore character.
*
* If no dot character was found, the category name is empty. That's for
* cif 1.0 formatted data.
*/
std::tuple<std::string, std::string> split_item_name(std::string_view item_name);
// --------------------------------------------------------------------
......
rsrc/ccd-subset.cif
......@@ -2712,4 +2712,96 @@ _pdbx_chem_comp_audit.processing_site
HIS "Create component" 1999-07-08 EBI
HIS "Modify descriptor" 2011-06-04 RCSB
#
data_HOH
#
_chem_comp.id HOH
_chem_comp.name WATER
_chem_comp.type NON-POLYMER
_chem_comp.pdbx_type HETAS
_chem_comp.formula "H2 O"
_chem_comp.mon_nstd_parent_comp_id ?
_chem_comp.pdbx_synonyms ?
_chem_comp.pdbx_formal_charge 0
_chem_comp.pdbx_initial_date 1999-07-08
_chem_comp.pdbx_modified_date 2011-06-04
_chem_comp.pdbx_ambiguous_flag N
_chem_comp.pdbx_release_status REL
_chem_comp.pdbx_replaced_by ?
_chem_comp.pdbx_replaces MTO
_chem_comp.formula_weight 18.015
_chem_comp.one_letter_code ?
_chem_comp.three_letter_code HOH
_chem_comp.pdbx_model_coordinates_details ?
_chem_comp.pdbx_model_coordinates_missing_flag N
_chem_comp.pdbx_ideal_coordinates_details ?
_chem_comp.pdbx_ideal_coordinates_missing_flag N
_chem_comp.pdbx_model_coordinates_db_code 1NHE
_chem_comp.pdbx_subcomponent_list ?
_chem_comp.pdbx_processing_site RCSB
# #
loop_
_chem_comp_atom.comp_id
_chem_comp_atom.atom_id
_chem_comp_atom.alt_atom_id
_chem_comp_atom.type_symbol
_chem_comp_atom.charge
_chem_comp_atom.pdbx_align
_chem_comp_atom.pdbx_aromatic_flag
_chem_comp_atom.pdbx_leaving_atom_flag
_chem_comp_atom.pdbx_stereo_config
_chem_comp_atom.model_Cartn_x
_chem_comp_atom.model_Cartn_y
_chem_comp_atom.model_Cartn_z
_chem_comp_atom.pdbx_model_Cartn_x_ideal
_chem_comp_atom.pdbx_model_Cartn_y_ideal
_chem_comp_atom.pdbx_model_Cartn_z_ideal
_chem_comp_atom.pdbx_component_atom_id
_chem_comp_atom.pdbx_component_comp_id
_chem_comp_atom.pdbx_ordinal
HOH O O O 0 1 N N N -23.107 18.401 -21.626 -0.064 0.000 0.000 O HOH 1
HOH H1 1H H 0 1 N N N -22.157 18.401 -21.626 0.512 0.000 -0.776 H1 HOH 2
HOH H2 2H H 0 1 N N N -23.424 18.401 -20.730 0.512 0.000 0.776 H2 HOH 3
# #
loop_
_chem_comp_bond.comp_id
_chem_comp_bond.atom_id_1
_chem_comp_bond.atom_id_2
_chem_comp_bond.value_order
_chem_comp_bond.pdbx_aromatic_flag
_chem_comp_bond.pdbx_stereo_config
_chem_comp_bond.pdbx_ordinal
HOH O H1 SING N N 1
HOH O H2 SING N N 2
# #
loop_
_pdbx_chem_comp_descriptor.comp_id
_pdbx_chem_comp_descriptor.type
_pdbx_chem_comp_descriptor.program
_pdbx_chem_comp_descriptor.program_version
_pdbx_chem_comp_descriptor.descriptor
HOH SMILES ACDLabs 10.04 O
HOH SMILES_CANONICAL CACTVS 3.341 O
HOH SMILES CACTVS 3.341 O
HOH SMILES_CANONICAL "OpenEye OEToolkits" 1.5.0 O
HOH SMILES "OpenEye OEToolkits" 1.5.0 O
HOH InChI InChI 1.03 InChI=1S/H2O/h1H2
HOH InChIKey InChI 1.03 XLYOFNOQVPJJNP-UHFFFAOYSA-N
# #
loop_
_pdbx_chem_comp_identifier.comp_id
_pdbx_chem_comp_identifier.type
_pdbx_chem_comp_identifier.program
_pdbx_chem_comp_identifier.program_version
_pdbx_chem_comp_identifier.identifier
HOH "SYSTEMATIC NAME" ACDLabs 10.04 water
HOH "SYSTEMATIC NAME" "OpenEye OEToolkits" 1.5.0 oxidane
# #
loop_
_pdbx_chem_comp_audit.comp_id
_pdbx_chem_comp_audit.action_type
_pdbx_chem_comp_audit.date
_pdbx_chem_comp_audit.processing_site
HOH "Create component" 1999-07-08 RCSB
HOH "Modify descriptor" 2011-06-04 RCSB
##
src/compound.cpp
......@@ -311,6 +311,18 @@ float compound::bond_length(const std::string &atomId_1, const std::string &atom
}
// --------------------------------------------------------------------
bool compound::is_peptide() const
{
return iequals(m_type, "l-peptide linking") or iequals(m_type, "peptide linking");
}
bool compound::is_base() const
{
return iequals(m_type, "dna linking") or iequals(m_type, "rna linking");
}
// --------------------------------------------------------------------
// known amino acids and bases
const std::map<std::string, char> compound_factory::kAAMap{
......@@ -660,25 +672,67 @@ void compound_factory::pop_dictionary()
m_impl = m_impl->next();
}
const compound *compound_factory::create(std::string id)
const compound *compound_factory::create(std::string_view id)
{
auto result = m_impl ? m_impl->get(id) : nullptr;
auto result = m_impl ? m_impl->get(std::string{ id }) : nullptr;
if (not result)
report_missing_compound(id);
return result;
}
bool compound_factory::is_known_peptide(const std::string &resName) const
bool compound_factory::is_known_peptide(const std::string &res_name) const
{
return kAAMap.count(res_name) > 0;
}
bool compound_factory::is_known_base(const std::string &res_name) const
{
return kBaseMap.count(res_name) > 0;
}
/// Return whether @a res_name is a peptide
bool compound_factory::is_peptide(std::string_view res_name) const
{
bool result = is_std_peptide(res_name);
if (not result and m_impl)
{
auto compound = const_cast<compound_factory&>(*this).create(res_name);
result = compound != nullptr and compound->is_peptide();
}
return result;
}
/// Return whether @a res_name is a base
bool compound_factory::is_base(std::string_view res_name) const
{
bool result = is_std_base(res_name);
if (not result and m_impl)
{
auto compound = const_cast<compound_factory&>(*this).create(res_name);
result = compound != nullptr and compound->is_base();
}
return result;
}
/// Return whether @a res_name is one of the standard peptides
bool compound_factory::is_std_peptide(std::string_view res_name) const
{
return kAAMap.count(std::string{ res_name }) > 0;
}
/// Return whether @a res_name is one of the standard bases
bool compound_factory::is_std_base(std::string_view res_name) const
{
return kAAMap.count(resName) > 0;
return kBaseMap.count(std::string{ res_name }) > 0;
}
bool compound_factory::is_known_base(const std::string &resName) const
/// Return whether @a res_name is a monomer (either base or peptide)
bool compound_factory::is_monomer(std::string_view res_name) const
{
return kBaseMap.count(resName) > 0;
return is_peptide(res_name) or is_base(res_name);
}
void compound_factory::report_missing_compound(const std::string &compound_id)
void compound_factory::report_missing_compound(std::string_view compound_id)
{
static bool s_reported = false;
if (std::exchange(s_reported, true) == false)
......@@ -703,8 +757,8 @@ void compound_factory::report_missing_compound(const std::string &compound_id)
<< "update=true\n\n"
<< "If you do not have a working cron script, you can manually update the files\n"
<< "in /var/cache/libcifpp using the following commands:\n\n"
<< "curl -o " << CACHE_DIR << "/components.cif https://files.wwpdb.org/pub/pdb/data/monomers/components.cif.gz\n"
<< "curl -o " << CACHE_DIR << "/mmcif_pdbx.dic https://mmcif.wwpdb.org/dictionaries/ascii/mmcif_pdbx_v50.dic.gz\n"
<< "curl -o " << CACHE_DIR << "/components.cif https://files.wwpdb.org/pub/pdb/data/monomers/components.cif\n"
<< "curl -o " << CACHE_DIR << "/mmcif_pdbx.dic https://mmcif.wwpdb.org/dictionaries/ascii/mmcif_pdbx_v50.dic\n"
<< "curl -o " << CACHE_DIR << "/mmcif_ma.dic https://github.com/ihmwg/ModelCIF/raw/master/dist/mmcif_ma.dic\n\n";
#endif
......
src/condition.cpp
......@@ -30,17 +30,17 @@
namespace cif
{
iset get_category_fields(const category &cat)
iset get_category_items(const category &cat)
{
return cat.key_fields();
return cat.key_items();
}
uint16_t get_column_ix(const category &cat, std::string_view col)
uint16_t get_item_ix(const category &cat, std::string_view col)
{
return cat.get_column_ix(col);
return cat.get_item_ix(col);
}
bool is_column_type_uchar(const category &cat, std::string_view col)
bool is_item_type_uchar(const category &cat, std::string_view col)
{
bool result = false;
......@@ -63,14 +63,14 @@ namespace detail
condition_impl *key_equals_condition_impl::prepare(const category &c)
{
m_item_ix = c.get_column_ix(m_item_tag);
m_icase = is_column_type_uchar(c, m_item_tag);
m_item_ix = c.get_item_ix(m_item_name);
m_icase = is_item_type_uchar(c, m_item_name);
if (c.get_cat_validator() != nullptr and
c.key_field_indices().contains(m_item_ix) and
c.key_field_indices().size() == 1)
c.key_item_indices().contains(m_item_ix) and
c.key_item_indices().size() == 1)
{
m_single_hit = c[{ { m_item_tag, m_value } }];
m_single_hit = c[{ { m_item_name, m_value } }];
}
return this;
......
src/datablock.cpp
......@@ -85,6 +85,40 @@ bool datablock::is_valid() const
return result;
}
bool datablock::is_valid()
{
if (m_validator == nullptr)
throw std::runtime_error("Validator not specified");
bool result = true;
for (auto &cat : *this)
result = cat.is_valid() and result;
// Add or remove the audit_conform block here.
if (result)
{
// If the dictionary declares an audit_conform category, put it in,
// but only if it does not exist already!
if (m_validator->get_validator_for_category("audit_conform") != nullptr)
{
auto &audit_conform = operator[]("audit_conform");
audit_conform.clear();
audit_conform.emplace({
// clang-format off
{ "dict_name", m_validator->name() },
{ "dict_version", m_validator->version() }
// clang-format on
});
}
}
else
erase(std::find_if(begin(), end(), [](category &cat) { return cat.name() == "audit_conform"; }), end());
return result;
}
bool datablock::validate_links() const
{
bool result = true;
......@@ -143,13 +177,6 @@ std::tuple<datablock::iterator, bool> datablock::emplace(std::string_view name)
if (iequals(name, i->name()))
{
is_new = false;
if (i != begin())
{
auto n = std::next(i);
splice(begin(), *this, i, n);
}
break;
}
......@@ -158,25 +185,24 @@ std::tuple<datablock::iterator, bool> datablock::emplace(std::string_view name)
if (is_new)
{
auto &c = emplace_back(name);
c.set_validator(m_validator, *this);
i = insert(end(), {name});
i->set_validator(m_validator, *this);
}
assert(end() != begin());
return std::make_tuple(std::prev(end()), is_new);
assert(i != end());
return std::make_tuple(i, is_new);
}
std::vector<std::string> datablock::get_tag_order() const
std::vector<std::string> datablock::get_item_order() const
{
std::vector<std::string> result;
// for entry and audit_conform on top
auto ci = find_if(begin(), end(), [](const category &cat)
{ return cat.name() == "entry"; });
if (ci != end())
{
auto cto = ci->get_tag_order();
auto cto = ci->get_item_order();
result.insert(result.end(), cto.begin(), cto.end());
}
......@@ -184,7 +210,7 @@ std::vector<std::string> datablock::get_tag_order() const
{ return cat.name() == "audit_conform"; });
if (ci != end())
{
auto cto = ci->get_tag_order();
auto cto = ci->get_item_order();
result.insert(result.end(), cto.begin(), cto.end());
}
......@@ -192,7 +218,7 @@ std::vector<std::string> datablock::get_tag_order() const
{
if (cat.name() == "entry" or cat.name() == "audit_conform")
continue;
auto cto = cat.get_tag_order();
auto cto = cat.get_item_order();
result.insert(result.end(), cto.begin(), cto.end());
}
......@@ -251,16 +277,6 @@ void datablock::write(std::ostream &os) const
if (m_validator and size() > 0)
{
// If the dictionary declares an audit_conform category, put it in,
// but only if it does not exist already!
if (get("audit_conform") == nullptr and m_validator->get_validator_for_category("audit_conform") != nullptr)
{
category auditConform("audit_conform");
auditConform.emplace({ { "dict_name", m_validator->name() },
{ "dict_version", m_validator->version() } });
auditConform.write(os);
}
// base order on parent child relationships, parents first
cat_order_t cat_order;
......@@ -327,16 +343,16 @@ void datablock::write(std::ostream &os) const
}
}
void datablock::write(std::ostream &os, const std::vector<std::string> &tag_order)
void datablock::write(std::ostream &os, const std::vector<std::string> &item_name_order)
{
os << "data_" << m_name << '\n'
<< "# \n";
std::vector<std::string> cat_order;
for (auto &o : tag_order)
for (auto &o : item_name_order)
{
std::string cat_name, item_name;
std::tie(cat_name, item_name) = split_tag_name(o);
std::tie(cat_name, item_name) = split_item_name(o);
if (find_if(cat_order.rbegin(), cat_order.rend(), [cat_name](const std::string &s) -> bool
{ return iequals(cat_name, s); }) == cat_order.rend())
cat_order.push_back(cat_name);
......@@ -349,10 +365,10 @@ void datablock::write(std::ostream &os, const std::vector<std::string> &tag_orde
continue;
std::vector<std::string> items;
for (auto &o : tag_order)
for (auto &o : item_name_order)
{
std::string cat_name, item_name;
std::tie(cat_name, item_name) = split_tag_name(o);
std::tie(cat_name, item_name) = split_item_name(o);
if (cat_name == c)
items.push_back(item_name);
......@@ -374,6 +390,10 @@ void datablock::write(std::ostream &os, const std::vector<std::string> &tag_orde
bool datablock::operator==(const datablock &rhs) const
{
// shortcut
if (this == &rhs)
return true;
auto &dbA = *this;
auto &dbB = rhs;
......
src/dictionary_parser.cpp
......@@ -50,7 +50,7 @@ class dictionary_parser : public parser
try
{
while (m_lookahead != CIFToken::Eof)
while (m_lookahead != CIFToken::END_OF_FILE)
{
switch (m_lookahead)
{
......@@ -87,7 +87,7 @@ class dictionary_parser : public parser
error("Undefined category '" + iv.first);
for (auto &v : iv.second)
const_cast<category_validator *>(cv)->addItemValidator(std::move(v));
const_cast<category_validator *>(cv)->add_item_validator(std::move(v));
}
// check all item validators for having a typeValidator
......@@ -128,7 +128,7 @@ class dictionary_parser : public parser
datablock::iterator cat = dict.end();
match(CIFToken::SAVE_NAME);
while (m_lookahead == CIFToken::LOOP or m_lookahead == CIFToken::Tag)
while (m_lookahead == CIFToken::LOOP or m_lookahead == CIFToken::ITEM_NAME)
{
if (m_lookahead == CIFToken::LOOP)
{
......@@ -136,30 +136,30 @@ class dictionary_parser : public parser
match(CIFToken::LOOP);
std::vector<std::string> tags;
while (m_lookahead == CIFToken::Tag)
std::vector<std::string> item_names;
while (m_lookahead == CIFToken::ITEM_NAME)
{
std::string catName, item_name;
std::tie(catName, item_name) = split_tag_name(m_token_value);
std::tie(catName, item_name) = split_item_name(m_token_value);
if (cat == dict.end())
std::tie(cat, std::ignore) = dict.emplace(catName);
else if (not iequals(cat->name(), catName))
error("inconsistent categories in loop_");
tags.push_back(item_name);
match(CIFToken::Tag);
item_names.push_back(item_name);
match(CIFToken::ITEM_NAME);
}
while (m_lookahead == CIFToken::Value)
while (m_lookahead == CIFToken::VALUE)
{
cat->emplace({});
auto row = cat->back();
for (auto tag : tags)
for (auto item_name : item_names)
{
row[tag] = m_token_value;
match(CIFToken::Value);
row[item_name] = m_token_value;
match(CIFToken::VALUE);
}
}
......@@ -168,18 +168,18 @@ class dictionary_parser : public parser
else
{
std::string catName, item_name;
std::tie(catName, item_name) = split_tag_name(m_token_value);
std::tie(catName, item_name) = split_item_name(m_token_value);
if (cat == dict.end() or not iequals(cat->name(), catName))
std::tie(cat, std::ignore) = dict.emplace(catName);
match(CIFToken::Tag);
match(CIFToken::ITEM_NAME);
if (cat->empty())
cat->emplace({});
cat->back()[item_name] = m_token_value;
match(CIFToken::Value);
match(CIFToken::VALUE);
}
}
......@@ -191,7 +191,7 @@ class dictionary_parser : public parser
std::vector<std::string> keys;
for (auto k : dict["category_key"])
keys.push_back(std::get<1>(split_tag_name(k["name"].as<std::string>())));
keys.push_back(std::get<1>(split_item_name(k["name"].as<std::string>())));
iset groups;
for (auto g : dict["category_group"])
......@@ -224,20 +224,27 @@ class dictionary_parser : public parser
// }
// }
std::vector<item_alias> aliases;
for (const auto &[alias_name, dictionary, version] :
dict["item_aliases"].rows<std::string,std::string,std::string>("alias_name", "dictionary", "version"))
{
aliases.emplace_back(alias_name, dictionary, version);
}
// collect the dict from our dataBlock and construct validators
for (auto i : dict["item"])
{
std::string tagName, category, mandatory;
cif::tie(tagName, category, mandatory) = i.get("name", "category_id", "mandatory_code");
std::string item, category, mandatory;
cif::tie(item, category, mandatory) = i.get("name", "category_id", "mandatory_code");
std::string cat_name, item_name;
std::tie(cat_name, item_name) = split_tag_name(tagName);
std::tie(cat_name, item_name) = split_item_name(item);
if (cat_name.empty() or item_name.empty())
error("Invalid tag name in _item.name " + tagName);
error("Invalid item name in _item.name " + item);
if (not iequals(category, cat_name) and not(category.empty() or category == "?"))
error("specified category id does match the implicit category name for tag '" + tagName + '\'');
error("specified category id does match the implicit category name for item '" + item + '\'');
else
category = cat_name;
......@@ -245,7 +252,7 @@ class dictionary_parser : public parser
auto vi = find(ivs.begin(), ivs.end(), item_validator{ item_name });
if (vi == ivs.end())
ivs.push_back(item_validator{ item_name, iequals(mandatory, "yes"), tv, ess, defaultValue /*, defaultIsNull*/ });
ivs.push_back(item_validator{ item_name, iequals(mandatory, "yes"), tv, ess, defaultValue, nullptr, std::move(aliases) });
else
{
// need to update the itemValidator?
......@@ -253,22 +260,22 @@ class dictionary_parser : public parser
{
if (VERBOSE > 2)
{
std::cerr << "inconsistent mandatory value for " << tagName << " in dictionary\n";
std::cerr << "inconsistent mandatory value for " << item << " in dictionary\n";
if (iequals(tagName, saveFrameName))
if (iequals(item, saveFrameName))
std::cerr << "choosing " << mandatory << '\n';
else
std::cerr << "choosing " << (vi->m_mandatory ? "Y" : "N") << '\n';
}
if (iequals(tagName, saveFrameName))
if (iequals(item, saveFrameName))
vi->m_mandatory = (iequals(mandatory, "yes"));
}
if (vi->m_type != nullptr and tv != nullptr and vi->m_type != tv)
{
if (VERBOSE > 1)
std::cerr << "inconsistent type for " << tagName << " in dictionary\n";
std::cerr << "inconsistent type for " << item << " in dictionary\n";
}
// vi->mMandatory = (iequals(mandatory, "yes"));
......@@ -351,7 +358,7 @@ class dictionary_parser : public parser
}
size_t ix = linkIndex.at(key);
addLink(ix, piv->m_tag, civ->m_tag);
addLink(ix, piv->m_item_name, civ->m_item_name);
}
// Only process inline linked items if the linked group list is absent
......@@ -379,7 +386,7 @@ class dictionary_parser : public parser
}
size_t ix = linkIndex.at(key);
addLink(ix, piv->m_tag, civ->m_tag);
addLink(ix, piv->m_item_name, civ->m_item_name);
}
}
......@@ -410,7 +417,7 @@ class dictionary_parser : public parser
for (auto &iv : cv.m_item_validators)
{
if (iv.m_type == nullptr and cif::VERBOSE >= 0)
std::cerr << "Missing item_type for " << iv.m_tag << '\n';
std::cerr << "Missing item_type for " << iv.m_item_name << '\n';
}
}
}
......
src/file.cpp
......@@ -158,13 +158,6 @@ std::tuple<file::iterator, bool> file::emplace(std::string_view name)
if (iequals(name, i->name()))
{
is_new = false;
if (i != begin())
{
auto n = std::next(i);
splice(begin(), *this, i, n);
}
break;
}
......@@ -173,12 +166,12 @@ std::tuple<file::iterator, bool> file::emplace(std::string_view name)
if (is_new)
{
auto &db = emplace_back(name);
db.set_validator(m_validator);
i = insert(end(), { name });
i->set_validator(m_validator);
}
assert(begin() != end());
return std::make_tuple(std::prev(end()), is_new);
assert(i != end());
return std::make_tuple(i, is_new);
}
void file::load(const std::filesystem::path &p)
......
src/item.cpp
......@@ -35,7 +35,7 @@ const item_handle item_handle::s_null_item;
row_handle s_null_row_handle;
item_handle::item_handle()
: m_column(std::numeric_limits<uint16_t>::max())
: m_item_ix(std::numeric_limits<uint16_t>::max())
, m_row_handle(s_null_row_handle)
{
}
......@@ -44,7 +44,7 @@ std::string_view item_handle::text() const
{
if (not m_row_handle.empty())
{
auto iv = m_row_handle.m_row->get(m_column);
auto iv = m_row_handle.m_row->get(m_item_ix);
if (iv != nullptr)
return iv->text();
}
......@@ -52,17 +52,17 @@ std::string_view item_handle::text() const
return {};
}
void item_handle::assign_value(const item &v)
void item_handle::assign_value(std::string_view value)
{
assert(not m_row_handle.empty());
m_row_handle.assign(m_column, v.value(), true);
m_row_handle.assign(m_item_ix, value, true);
}
void item_handle::swap(item_handle &b)
{
assert(m_column == b.m_column);
assert(m_item_ix == b.m_item_ix);
// assert(&m_row_handle.m_category == &b.m_row_handle.m_category);
m_row_handle.swap(m_column, b.m_row_handle);
m_row_handle.swap(m_item_ix, b.m_row_handle);
}
}
src/model.cpp
......@@ -163,9 +163,9 @@ int atom::atom_impl::get_charge() const
// const std::string atom::atom_impl::get_property(const std::string_view name) const
// {
// for (auto &&[tag, ref] : mCachedRefs)
// for (auto &&[item_name, ref] : mCachedRefs)
// {
// if (tag == name)
// if (item_name == name)
// return ref.as<std::string>();
// }
......@@ -175,9 +175,9 @@ int atom::atom_impl::get_charge() const
// void atom::atom_impl::set_property(const std::string_view name, const std::string &value)
// {
// for (auto &&[tag, ref] : mCachedRefs)
// for (auto &&[item_name, ref] : mCachedRefs)
// {
// if (tag != name)
// if (item_name != name)
// continue;
// ref = value;
......@@ -1783,7 +1783,7 @@ atom &structure::emplace_atom(atom &&atom)
std::string symbol = atom.get_property("type_symbol");
using namespace cif::literals;
if (not atom_type.exists("symbol"_key == symbol))
if (not atom_type.contains("symbol"_key == symbol))
atom_type.emplace({ { "symbol", symbol } });
return m_atoms.emplace_back(std::move(atom));
......@@ -1969,7 +1969,7 @@ void structure::change_residue(residue &res, const std::string &newCompound,
// create rest
auto &chemComp = m_db["chem_comp"];
if (not chemComp.exists(key("id") == newCompound))
if (not chemComp.contains(key("id") == newCompound))
{
chemComp.emplace({{"id", newCompound},
{"name", compound->name()},
......@@ -2702,7 +2702,7 @@ void structure::cleanup_empty_categories()
for (auto chemComp : chem_comp)
{
std::string compID = chemComp["id"].as<std::string>();
if (atomSite.exists("label_comp_id"_key == compID or "auth_comp_id"_key == compID))
if (atomSite.contains("label_comp_id"_key == compID or "auth_comp_id"_key == compID))
continue;
obsoleteChemComps.push_back(chemComp);
......@@ -2719,7 +2719,7 @@ void structure::cleanup_empty_categories()
for (auto entity : entities)
{
std::string entityID = entity["id"].as<std::string>();
if (atomSite.exists("label_entity_id"_key == entityID))
if (atomSite.contains("label_entity_id"_key == entityID))
continue;
obsoleteEntities.push_back(entity);
......
src/parser.cpp
......@@ -269,7 +269,7 @@ sac_parser::CIFToken sac_parser::get_next_token()
{
const auto kEOF = std::char_traits<char>::eof();
CIFToken result = CIFToken::Unknown;
CIFToken result = CIFToken::UNKNOWN;
int quoteChar = 0;
State state = State::Start;
m_bol = false;
......@@ -279,7 +279,7 @@ sac_parser::CIFToken sac_parser::get_next_token()
reserved_words_automaton dag;
while (result == CIFToken::Unknown)
while (result == CIFToken::UNKNOWN)
{
auto ch = get_next_char();
......@@ -287,7 +287,7 @@ sac_parser::CIFToken sac_parser::get_next_token()
{
case State::Start:
if (ch == kEOF)
result = CIFToken::Eof;
result = CIFToken::END_OF_FILE;
else if (ch == '\n')
{
m_bol = true;
......@@ -298,9 +298,9 @@ sac_parser::CIFToken sac_parser::get_next_token()
else if (ch == '#')
state = State::Comment;
else if (ch == '_')
state = State::Tag;
state = State::ItemName;
else if (ch == ';' and m_bol)
state = State::TextField;
state = State::TextItem;
else if (ch == '?')
state = State::QuestionMark;
else if (ch == '\'' or ch == '"')
......@@ -316,7 +316,7 @@ sac_parser::CIFToken sac_parser::get_next_token()
case State::White:
if (ch == kEOF)
result = CIFToken::Eof;
result = CIFToken::END_OF_FILE;
else if (not is_space(ch))
{
state = State::Start;
......@@ -335,7 +335,7 @@ sac_parser::CIFToken sac_parser::get_next_token()
m_token_buffer.clear();
}
else if (ch == kEOF)
result = CIFToken::Eof;
result = CIFToken::END_OF_FILE;
else if (not is_any_print(ch))
error("invalid character in comment");
break;
......@@ -344,29 +344,29 @@ sac_parser::CIFToken sac_parser::get_next_token()
if (not is_non_blank(ch))
{
retract();
result = CIFToken::Value;
result = CIFToken::VALUE;
}
else
state = State::Value;
break;
case State::TextField:
case State::TextItem:
if (ch == '\n')
state = State::TextFieldNL;
state = State::TextItemNL;
else if (ch == kEOF)
error("unterminated textfield");
else if (not is_any_print(ch) and cif::VERBOSE > 2)
warning("invalid character in text field '" + std::string({static_cast<char>(ch)}) + "' (" + std::to_string((int)ch) + ")");
break;
case State::TextFieldNL:
case State::TextItemNL:
if (is_text_lead(ch) or ch == ' ' or ch == '\t')
state = State::TextField;
state = State::TextItem;
else if (ch == ';')
{
assert(m_token_buffer.size() >= 2);
m_token_value = std::string_view(m_token_buffer.data() + 1, m_token_buffer.size() - 3);
result = CIFToken::Value;
result = CIFToken::VALUE;
}
else if (ch == kEOF)
error("unterminated textfield");
......@@ -387,7 +387,7 @@ sac_parser::CIFToken sac_parser::get_next_token()
if (is_white(ch))
{
retract();
result = CIFToken::Value;
result = CIFToken::VALUE;
if (m_token_buffer.size() < 2)
error("Invalid quoted string token");
......@@ -403,11 +403,11 @@ sac_parser::CIFToken sac_parser::get_next_token()
error("invalid character in quoted string");
break;
case State::Tag:
case State::ItemName:
if (not is_non_blank(ch))
{
retract();
result = CIFToken::Tag;
result = CIFToken::ITEM_NAME;
m_token_value = std::string_view(m_token_buffer.data(), m_token_buffer.size());
}
break;
......@@ -422,7 +422,7 @@ sac_parser::CIFToken sac_parser::get_next_token()
if (not is_non_blank(ch))
{
retract();
result = CIFToken::Value;
result = CIFToken::VALUE;
m_token_value = std::string_view(m_token_buffer.data(), m_token_buffer.size());
}
else
......@@ -467,7 +467,7 @@ sac_parser::CIFToken sac_parser::get_next_token()
if (not is_non_blank(ch))
{
retract();
result = CIFToken::Value;
result = CIFToken::VALUE;
m_token_value = std::string_view(m_token_buffer.data(), m_token_buffer.size());
break;
}
......@@ -483,7 +483,7 @@ sac_parser::CIFToken sac_parser::get_next_token()
if (VERBOSE >= 5)
{
std::cerr << get_token_name(result);
if (result != CIFToken::Eof)
if (result != CIFToken::END_OF_FILE)
std::cerr << " " << std::quoted(m_token_value);
std::cerr << '\n';
}
......@@ -710,7 +710,7 @@ bool sac_parser::parse_single_datablock(const std::string &datablock, const data
void sac_parser::parse_file()
{
while (m_lookahead != CIFToken::Eof)
while (m_lookahead != CIFToken::END_OF_FILE)
{
switch (m_lookahead)
{
......@@ -735,10 +735,10 @@ void sac_parser::parse_file()
void sac_parser::parse_global()
{
match(CIFToken::GLOBAL);
while (m_lookahead == CIFToken::Tag)
while (m_lookahead == CIFToken::ITEM_NAME)
{
match(CIFToken::Tag);
match(CIFToken::Value);
match(CIFToken::ITEM_NAME);
match(CIFToken::VALUE);
}
}
......@@ -747,7 +747,7 @@ void sac_parser::parse_datablock()
static const std::string kUnitializedCategory("<invalid>");
std::string cat = kUnitializedCategory; // intial value acts as a guard for empty category names
while (m_lookahead == CIFToken::LOOP or m_lookahead == CIFToken::Tag or m_lookahead == CIFToken::SAVE_NAME)
while (m_lookahead == CIFToken::LOOP or m_lookahead == CIFToken::ITEM_NAME or m_lookahead == CIFToken::SAVE_NAME)
{
switch (m_lookahead)
{
......@@ -757,12 +757,12 @@ void sac_parser::parse_datablock()
match(CIFToken::LOOP);
std::vector<std::string> tags;
std::vector<std::string> item_names;
while (m_lookahead == CIFToken::Tag)
while (m_lookahead == CIFToken::ITEM_NAME)
{
std::string catName, itemName;
std::tie(catName, itemName) = split_tag_name(m_token_value);
std::tie(catName, itemName) = split_item_name(m_token_value);
if (cat == kUnitializedCategory)
{
......@@ -772,19 +772,19 @@ void sac_parser::parse_datablock()
else if (not iequals(cat, catName))
error("inconsistent categories in loop_");
tags.push_back(itemName);
item_names.push_back(itemName);
match(CIFToken::Tag);
match(CIFToken::ITEM_NAME);
}
while (m_lookahead == CIFToken::Value)
while (m_lookahead == CIFToken::VALUE)
{
produce_row();
for (auto tag : tags)
for (auto item_name : item_names)
{
produce_item(cat, tag, m_token_value);
match(CIFToken::Value);
produce_item(cat, item_name, m_token_value);
match(CIFToken::VALUE);
}
}
......@@ -792,10 +792,10 @@ void sac_parser::parse_datablock()
break;
}
case CIFToken::Tag:
case CIFToken::ITEM_NAME:
{
std::string catName, itemName;
std::tie(catName, itemName) = split_tag_name(m_token_value);
std::tie(catName, itemName) = split_item_name(m_token_value);
if (not iequals(cat, catName))
{
......@@ -804,11 +804,11 @@ void sac_parser::parse_datablock()
produce_row();
}
match(CIFToken::Tag);
match(CIFToken::ITEM_NAME);
produce_item(cat, itemName, m_token_value);
match(CIFToken::Value);
match(CIFToken::VALUE);
break;
}
......
src/pdb/pdb2cif.cpp
......@@ -1123,9 +1123,6 @@ void PDBFileParser::PreParseInput(std::istream &is)
if (lookahead.back() == '\r')
lookahead.pop_back();
// 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");
auto contNr = [&lookahead](int offset, int len) -> int
{
std::string cs = lookahead.substr(offset, len);
......@@ -1558,52 +1555,54 @@ void PDBFileParser::ParseTitle()
// 11 - 80 Specification compound Description of the molecular components.
// list
std::string value{ mRec->vS(11) };
if (value.find(':') == std::string::npos)
{
// special case for dumb, stripped files
auto &comp = GetOrCreateCompound(1);
comp.mInfo["MOLECULE"] = value;
}
else
if (mRec->is("COMPND"))
{
SpecificationListParser p(value);
for (;;)
std::string value{ mRec->vS(11) };
if (value.find(':') == std::string::npos)
{
std::string key, val;
std::tie(key, val) = p.GetNextSpecification();
if (key.empty())
break;
// special case for dumb, stripped files
auto &comp = GetOrCreateCompound(1);
comp.mInfo["MOLECULE"] = value;
}
else
{
SpecificationListParser p(value);
if (not iequals(key, "MOL_ID") and mCompounds.empty())
for (;;)
{
if (cif::VERBOSE > 0)
std::cerr << "Ignoring invalid COMPND record\n";
break;
}
std::string key, val;
std::tie(key, val) = p.GetNextSpecification();
if (key == "MOL_ID")
{
auto &comp = GetOrCreateCompound(stoi(val));
comp.mTitle = title;
}
else if (key == "CHAIN")
{
for (auto c : cif::split<std::string>(val, ","))
if (key.empty())
break;
if (not iequals(key, "MOL_ID") and mCompounds.empty())
{
cif::trim(c);
mCompounds.back().mChains.insert(c[0]);
if (cif::VERBOSE > 0)
std::cerr << "Ignoring invalid COMPND record\n";
break;
}
if (key == "MOL_ID")
{
auto &comp = GetOrCreateCompound(stoi(val));
comp.mTitle = title;
}
else if (key == "CHAIN")
{
for (auto c : cif::split<std::string>(val, ","))
{
cif::trim(c);
mCompounds.back().mChains.insert(c[0]);
}
}
else
mCompounds.back().mInfo[key] = val;
}
else
mCompounds.back().mInfo[key] = val;
}
}
if (mRec->is("COMPND"))
GetNextRecord();
}
// SOURCE
Match("SOURCE", false);
......@@ -1740,7 +1739,7 @@ void PDBFileParser::ParseTitle()
int n = 1;
cat = getCategory("audit_author");
value = { mRec->vS(11) };
std::string value = { mRec->vS(11) };
for (auto author : cif::split<std::string>(value, ",", true))
{
// clang-format off
......@@ -3646,7 +3645,7 @@ void PDBFileParser::ConstructEntities()
PDBChain::AtomRes ar{ resName, resSeq, iCode };
if ((chain.mResiduesSeen.empty() or chain.mResiduesSeen.back() != ar) and
(cif::compound_factory::instance().is_known_peptide(resName) or cif::compound_factory::instance().is_known_base(resName)))
cif::compound_factory::instance().is_monomer(resName))
{
chain.mResiduesSeen.push_back(ar);
}
......@@ -3731,11 +3730,8 @@ void PDBFileParser::ConstructEntities()
{
std::string resName = chain.mResiduesSeen[ix].mMonID;
if (cif::compound_factory::instance().is_known_peptide(resName) or
cif::compound_factory::instance().is_known_base(resName))
{
if (cif::compound_factory::instance().is_monomer(resName))
chain.mTerIndex = ix + 1;
}
InsertChemComp(resName);
}
......@@ -3814,7 +3810,7 @@ void PDBFileParser::ConstructEntities()
int residueCount = (residuePerChainCounter[chainID] += 1);
// There appears to be a program that writes out HETATM records as ATOM records....
if (not(cif::compound_factory::instance().is_known_peptide(resName) or cif::compound_factory::instance().is_known_base(resName)) or
if (not cif::compound_factory::instance().is_monomer(resName) or
terminatedChains.count(chainID) or
(chain.mTerIndex > 0 and residueCount >= chain.mTerIndex))
{
......@@ -4559,7 +4555,7 @@ void PDBFileParser::ConstructEntities()
std::string formula;
std::string type;
std::string nstd = ".";
std::string formulaWeight;
std::optional<float> formulaWeight;
if (compound != nullptr)
{
......@@ -4570,7 +4566,7 @@ void PDBFileParser::ConstructEntities()
nstd = "y";
formula = compound->formula();
formulaWeight = std::to_string(compound->formula_weight());
formulaWeight = compound->formula_weight();
}
if (name.empty())
......@@ -4597,7 +4593,7 @@ void PDBFileParser::ConstructEntities()
{ "id", cc },
{ "name", name },
{ "formula", formula },
{ "formula_weight", formulaWeight },
{ "formula_weight", formulaWeight, 3 },
{ "mon_nstd_flag", nstd },
{ "type", type }
});
......@@ -4712,7 +4708,7 @@ void PDBFileParser::ConstructEntities()
}
if (formula_weight > 0)
entity["formula_weight"] = formula_weight;
entity.assign({ { "formula_weight", formula_weight, 3 } });
}
}
......@@ -5581,31 +5577,6 @@ void PDBFileParser::ParseCrystallographic()
GetNextRecord();
}
else
{
// clang-format off
// no cryst1, make a simple one, like this:
// CRYST1 1.000 1.000 1.000 90.00 90.00 90.00 P 1 1
getCategory("cell")->emplace({
{ "entry_id", mStructureID }, // 1 - 6 Record name "CRYST1"
{ "length_a", 1 }, // 7 - 15 Real(9.3) a a (Angstroms).
{ "length_b", 1 }, // 16 - 24 Real(9.3) b b (Angstroms).
{ "length_c", 1 }, // 25 - 33 Real(9.3) c c (Angstroms).
{ "angle_alpha", 90 }, // 34 - 40 Real(7.2) alpha alpha (degrees).
{ "angle_beta", 90 }, // 41 - 47 Real(7.2) beta beta (degrees).
{ "angle_gamma", 90 }, // 48 - 54 Real(7.2) gamma gamma (degrees).
/* goes into symmetry */ // 56 - 66 LString sGroup Space group.
{ "Z_PDB", 1 } // 67 - 70 Integer z Z value.
});
getCategory("symmetry")->emplace({
{ "entry_id", mStructureID },
{ "space_group_name_H-M", "P 1" },
{ "Int_Tables_number", 1 }
});
// clang-format on
}
}
void PDBFileParser::ParseCoordinateTransformation()
......@@ -6466,7 +6437,12 @@ file read(std::istream &is)
// and so the very first character in a valid PDB file
// is 'H'. It is as simple as that.
if (ch == 'h' or ch == 'H')
// Well, not quite, Unfortunately... People insisted that
// having only ATOM records also makes up a valid PDB file...
// Since mmCIF files cannot validly start with a letter character
// apart from the letter 'd', the test has changed into the following:
if (std::isalpha(ch) and std::toupper(ch) != 'D')
read_pdb_file(is, result);
else
{
......
src/pdb/pdb2cif_remark_3.cpp
......@@ -1493,8 +1493,8 @@ bool Remark3Parser::parse(const std::string &expMethod, PDBRecord *r, cif::datab
auto r1 = cat1.front();
auto r2 = cat2.front();
for (auto column : cat1.key_fields())
r2[column] = r1[column].text();
for (auto item : cat1.key_items())
r2[item] = r1[item].text();
}
}
else
......
src/pdb/validate-pdbx.cpp
......@@ -69,26 +69,65 @@ condition get_parents_condition(const validator &validator, row_handle rh, const
bool is_valid_pdbx_file(const file &file, std::string_view dictionary)
{
using namespace cif::literals;
std::error_code ec;
bool result = is_valid_pdbx_file(file, dictionary, ec);
return result and ec == std::errc();
}
auto &cf = cif::compound_factory::instance();
auto &validator = cif::validator_factory::instance().operator[](dictionary);
bool is_valid_pdbx_file(const file &file, std::error_code &ec)
{
bool result = false;
if (file.empty())
ec = make_error_code(validation_error::empty_file);
else
{
std::string dictionary = "mmcif_pdbx";
for (auto &db : file)
{
auto audit_conform = db.get("audit_conform");
if (audit_conform == nullptr)
continue;
if (not audit_conform->empty())
{
auto specified_dict = audit_conform->front()["dict_name"];
if (not specified_dict.empty())
dictionary = specified_dict.as<std::string>();
}
break;
}
result = is_valid_pdbx_file(file, dictionary, ec);
}
return result;
}
bool is_valid_pdbx_file(const file &file, std::string_view dictionary, std::error_code &ec)
{
using namespace cif::literals;
bool result = true;
try
{
auto &cf = cif::compound_factory::instance();
auto &validator = cif::validator_factory::instance().operator[](dictionary);
if (file.empty())
throw validation_error("Empty file");
throw std::runtime_error("Empty file");
auto &db = file.front();
if (db.empty())
throw validation_error("Empty datablock");
throw std::runtime_error("Empty datablock");
auto &atom_site = db["atom_site"];
if (atom_site.empty())
throw validation_error("Empty or missing atom_site category");
throw std::runtime_error("Empty or missing atom_site category");
auto &pdbx_poly_seq_scheme = db["pdbx_poly_seq_scheme"];
......@@ -106,34 +145,38 @@ bool is_valid_pdbx_file(const file &file, std::string_view dictionary)
last_seq_id = *seq_id;
auto comp_id = r.get<std::string>("label_comp_id");
if (not cf.is_known_peptide(comp_id))
if (not cf.is_monomer(comp_id))
continue;
auto p = pdbx_poly_seq_scheme.find(get_parents_condition(validator, r, pdbx_poly_seq_scheme));
if (p.size() != 1)
throw validation_error("For each residue in atom_site that is a residue in a polymer there should be exactly one pdbx_poly_seq_scheme record");
{
if (cif::VERBOSE > 0)
std::clog << "In atom_site record: " << r["id"].text() << '\n';
throw std::runtime_error("For each monomer in atom_site there should be exactly one pdbx_poly_seq_scheme record");
}
}
auto &entity = db["entity"];
if (entity.empty())
throw validation_error("Entity category is missing or empty");
throw std::runtime_error("Entity category is missing or empty");
auto &entity_poly = db["entity_poly"];
if (entity_poly.empty())
throw validation_error("Entity_poly category is missing or empty");
throw std::runtime_error("Entity_poly category is missing or empty");
auto &entity_poly_seq = db["entity_poly_seq"];
if (entity_poly_seq.empty())
throw validation_error("Entity_poly_seq category is missing or empty");
throw std::runtime_error("Entity_poly_seq category is missing or empty");
auto &struct_asym = db["struct_asym"];
if (struct_asym.empty())
throw validation_error("struct_asym category is missing or empty");
throw std::runtime_error("struct_asym category is missing or empty");
for (auto entity_id : entity.find<std::string>("type"_key == "polymer", "id"))
{
if (entity_poly.count("entity_id"_key == entity_id) != 1)
throw validation_error("There should be exactly one entity_poly record per polymer entity");
throw std::runtime_error("There should be exactly one entity_poly record per polymer entity");
const auto entity_poly_type = entity_poly.find1<std::string>("entity_id"_key == entity_id, "type");
......@@ -151,7 +194,7 @@ bool is_valid_pdbx_file(const file &file, std::string_view dictionary)
"seq_id"_key == num and
"hetero"_key == hetero) != 1)
{
throw validation_error("For each entity_poly_seq record there should be exactly one pdbx_poly_seq record");
throw std::runtime_error("For each entity_poly_seq record there should be exactly one pdbx_poly_seq record");
}
}
}
......@@ -163,11 +206,11 @@ bool is_valid_pdbx_file(const file &file, std::string_view dictionary)
"num"_key == seq_id and
"hetero"_key == hetero) != 1)
{
throw validation_error("For each pdbx_poly_seq/struct_asym record there should be exactly one entity_poly_seq record");
throw std::runtime_error("For each pdbx_poly_seq/struct_asym record there should be exactly one entity_poly_seq record");
}
if ((mon_per_seq_id[seq_id].size() > 1) != hetero)
throw validation_error("Mismatch between the hetero flag in the poly seq schemes and the number residues per seq_id");
throw std::runtime_error("Mismatch between the hetero flag in the poly seq schemes and the number residues per seq_id");
}
for (const auto &[seq_id, mon_ids] : mon_per_seq_id)
......@@ -183,8 +226,8 @@ bool is_valid_pdbx_file(const file &file, std::string_view dictionary)
"label_asym_id"_key == asym_id and
"label_seq_id"_key == seq_id and not std::move(cond);
if (atom_site.exists(std::move(cond)))
throw validation_error("An atom_site record exists that has no parent in the poly seq scheme categories");
if (atom_site.contains(std::move(cond)))
throw std::runtime_error("An atom_site record exists that has no parent in the poly seq scheme categories");
}
}
......@@ -205,13 +248,12 @@ bool is_valid_pdbx_file(const file &file, std::string_view dictionary)
for (auto comp_id : comp_ids)
{
std::string letter;
if (cf.is_known_base(comp_id))
letter = compound_factory::kBaseMap.at(comp_id);
else if (cf.is_known_peptide(comp_id))
letter = compound_factory::kAAMap.at(comp_id);
else
if (can)
{
if (can)
if (compound_factory::kBaseMap.contains(comp_id))
letter = compound_factory::kBaseMap.at(comp_id);
else
{
auto c = cf.create(comp_id);
if (c and c->one_letter_code())
......@@ -219,6 +261,13 @@ bool is_valid_pdbx_file(const file &file, std::string_view dictionary)
else
letter = "X";
}
}
else
{
if (compound_factory::kAAMap.contains(comp_id))
letter = compound_factory::kAAMap.at(comp_id);
else if (comp_id.length() == 1 and compound_factory::kBaseMap.contains(comp_id))
letter = compound_factory::kBaseMap.at(comp_id);
else
letter = '(' + comp_id + ')';
}
......@@ -250,7 +299,7 @@ bool is_valid_pdbx_file(const file &file, std::string_view dictionary)
seq->erase(std::remove_if(seq->begin(), seq->end(), [](char ch) { return std::isspace(ch); }), seq->end());
if (not seq_match(false, seq->begin(), seq->end()))
throw validation_error("Sequences do not match for entity " + entity_id);
throw std::runtime_error("Sequences do not match for entity " + entity_id);
}
if (not seq_can.has_value())
......@@ -261,11 +310,10 @@ bool is_valid_pdbx_file(const file &file, std::string_view dictionary)
else
{
seq_can->erase(std::remove_if(seq_can->begin(), seq_can->end(), [](char ch) { return std::isspace(ch); }), seq_can->end());
if (not seq_match(true, seq_can->begin(), seq_can->end()))
throw validation_error("Canonical sequences do not match for entity " + entity_id);
throw std::runtime_error("Canonical sequences do not match for entity " + entity_id);
}
}
result = true;
......@@ -275,8 +323,12 @@ bool is_valid_pdbx_file(const file &file, std::string_view dictionary)
result = false;
if (cif::VERBOSE > 0)
std::clog << ex.what() << '\n';
ec = make_error_code(validation_error::not_valid_pdbx);
}
if (not result and ec == std::errc())
ec = make_error_code(validation_error::not_valid_pdbx);
return result;
}
......
src/row.cpp
......@@ -29,44 +29,44 @@
namespace cif
{
void row_handle::assign(uint16_t column, std::string_view value, bool updateLinked, bool validate)
void row_handle::assign(uint16_t item, std::string_view value, bool updateLinked, bool validate)
{
if (not m_category)
throw std::runtime_error("uninitialized row");
m_category->update_value(m_row, column, value, updateLinked, validate);
m_category->update_value(m_row, item, value, updateLinked, validate);
}
uint16_t row_handle::get_column_ix(std::string_view name) const
uint16_t row_handle::get_item_ix(std::string_view name) const
{
if (not m_category)
throw std::runtime_error("uninitialized row");
return m_category->get_column_ix(name);
return m_category->get_item_ix(name);
}
std::string_view row_handle::get_column_name(uint16_t ix) const
std::string_view row_handle::get_item_name(uint16_t ix) const
{
if (not m_category)
throw std::runtime_error("uninitialized row");
return m_category->get_column_name(ix);
return m_category->get_item_name(ix);
}
uint16_t row_handle::add_column(std::string_view name)
uint16_t row_handle::add_item(std::string_view name)
{
if (not m_category)
throw std::runtime_error("uninitialized row");
return m_category->add_column(name);
return m_category->add_item(name);
}
void row_handle::swap(uint16_t column, row_handle &b)
void row_handle::swap(uint16_t item, row_handle &b)
{
if (not m_category)
throw std::runtime_error("uninitialized row");
m_category->swap_item(column, *this, b);
m_category->swap_item(item, *this, b);
}
// --------------------------------------------------------------------
......@@ -86,7 +86,7 @@ row_initializer::row_initializer(row_handle rh)
auto &i = r->operator[](ix);
if (not i)
continue;
emplace_back(cat.get_column_name(ix), i.text());
emplace_back(cat.get_item_name(ix), i.text());
}
}
......
src/validate.cpp
......@@ -39,39 +39,47 @@
// the code will use boost::regex instead.
#if USE_BOOST_REGEX
#include <boost/regex.hpp>
# include <boost/regex.hpp>
using boost::regex;
#else
#include <regex>
# include <regex>
using std::regex;
#endif
namespace cif
{
struct regex_impl : public regex
validation_exception::validation_exception(std::error_code ec)
: runtime_error(ec.message())
{
regex_impl(std::string_view rx)
: regex(rx.begin(), rx.end(), regex::extended | regex::optimize)
{
}
};
}
validation_error::validation_error(const std::string &msg)
: m_msg(msg)
validation_exception::validation_exception(std::error_code ec, std::string_view category)
: runtime_error((ec.message() + "; category: ").append(category))
{
}
validation_error::validation_error(const std::string &cat, const std::string &item, const std::string &msg)
: m_msg("When validating _" + cat + '.' + item + ": " + msg)
validation_exception::validation_exception(std::error_code ec, std::string_view category, std::string_view item)
: runtime_error((ec.message() + "; category: ").append(category).append("; item: ").append(item))
{
}
// --------------------------------------------------------------------
DDL_PrimitiveType map_to_primitive_type(std::string_view s)
struct regex_impl : public regex
{
regex_impl(std::string_view rx)
: regex(rx.begin(), rx.end(), regex::extended | regex::optimize)
{
}
};
// --------------------------------------------------------------------
DDL_PrimitiveType map_to_primitive_type(std::string_view s, std::error_code &ec) noexcept
{
DDL_PrimitiveType result;
ec = {};
DDL_PrimitiveType result = DDL_PrimitiveType::Char;
if (iequals(s, "char"))
result = DDL_PrimitiveType::Char;
else if (iequals(s, "uchar"))
......@@ -79,7 +87,16 @@ DDL_PrimitiveType map_to_primitive_type(std::string_view s)
else if (iequals(s, "numb"))
result = DDL_PrimitiveType::Numb;
else
throw validation_error("Not a known primitive type");
ec = make_error_code(validation_error::not_a_known_primitive_type);
return result;
}
DDL_PrimitiveType map_to_primitive_type(std::string_view s)
{
std::error_code ec;
auto result = map_to_primitive_type(s, ec);
if (ec)
throw std::system_error(ec, std::string{ s });
return result;
}
......@@ -196,63 +213,72 @@ int type_validator::compare(std::string_view a, std::string_view b) const
// --------------------------------------------------------------------
// void ValidateItem::addLinked(ValidateItem* parent, const std::string& parentItem, const std::string& childItem)
//{
//// if (mParent != nullptr and VERBOSE)
//// cerr << "replacing parent in " << mCategory->m_name << " from " << mParent->mCategory->m_name << " to " << parent->mCategory->m_name << endl;
//// mParent = parent;
//
// if (m_type == nullptr and parent != nullptr)
// m_type = parent->m_type;
//
// if (parent != nullptr)
// {
// mLinked.push_back({parent, parentItem, childItem});
//
// parent->mChildren.insert(this);
////
//// if (mCategory->mKeys == std::vector<std::string>{mTag})
//// parent->mForeignKeys.insert(this);
// }
//}
void item_validator::operator()(std::string_view value) const
{
std::error_code ec;
if (not validate_value(value, ec))
throw std::system_error(ec, std::string{ value } + " does not match rx for " + m_item_name);
}
bool item_validator::validate_value(std::string_view value, std::error_code &ec) const noexcept
{
ec = {};
if (not value.empty() and value != "?" and value != ".")
{
if (m_type != nullptr and not regex_match(value.begin(), value.end(), *m_type->m_rx))
throw validation_error(m_category->m_name, m_tag, "Value '" + std::string{ value } + "' does not match type expression for type " + m_type->m_name);
if (not m_enums.empty())
{
if (m_enums.count(std::string{ value }) == 0)
throw validation_error(m_category->m_name, m_tag, "Value '" + std::string{ value } + "' is not in the list of allowed values");
}
ec = make_error_code(validation_error::value_does_not_match_rx);
else if (not m_enums.empty() and m_enums.count(std::string{ value }) == 0)
ec = make_error_code(validation_error::value_is_not_in_enumeration_list);
}
return ec == std::errc();
}
// --------------------------------------------------------------------
void category_validator::addItemValidator(item_validator &&v)
void category_validator::add_item_validator(item_validator &&v)
{
if (v.m_mandatory)
m_mandatory_fields.insert(v.m_tag);
m_mandatory_items.insert(v.m_item_name);
v.m_category = this;
auto r = m_item_validators.insert(std::move(v));
if (not r.second and VERBOSE >= 4)
std::cout << "Could not add validator for item " << v.m_tag << " to category " << m_name << '\n';
std::cout << "Could not add validator for item " << v.m_item_name << " to category " << m_name << '\n';
}
const item_validator *category_validator::get_validator_for_item(std::string_view tag) const
const item_validator *category_validator::get_validator_for_item(std::string_view item_name) const
{
const item_validator *result = nullptr;
auto i = m_item_validators.find(item_validator{ std::string(tag) });
auto i = m_item_validators.find(item_validator{ std::string(item_name) });
if (i != m_item_validators.end())
result = &*i;
else if (VERBOSE > 4)
std::cout << "No validator for tag " << tag << '\n';
std::cout << "No validator for item " << item_name << '\n';
return result;
}
const item_validator *category_validator::get_validator_for_aliased_item(std::string_view item_name) const
{
const item_validator *result = nullptr;
for (auto &iv : m_item_validators)
{
for (auto &ai : iv.m_aliases)
{
const auto &[cat, name] = split_item_name(ai.m_name);
if (iequals(name, item_name) and iequals(cat, m_name))
{
result = &iv;
break;
}
}
if (result)
break;
}
return result;
}
......@@ -295,19 +321,19 @@ const category_validator *validator::get_validator_for_category(std::string_view
return result;
}
item_validator *validator::get_validator_for_item(std::string_view tag) const
item_validator *validator::get_validator_for_item(std::string_view item_name) const
{
item_validator *result = nullptr;
std::string cat, item;
std::tie(cat, item) = split_tag_name(tag);
std::tie(cat, item) = split_item_name(item_name);
auto *cv = get_validator_for_category(cat);
if (cv != nullptr)
result = const_cast<item_validator *>(cv->get_validator_for_item(item));
if (result == nullptr and VERBOSE > 4)
std::cout << "No validator for item " << tag << '\n';
std::cout << "No validator for item " << item_name << '\n';
return result;
}
......@@ -332,11 +358,11 @@ void validator::add_link_validator(link_validator &&v)
auto piv = pcv->get_validator_for_item(v.m_parent_keys[i]);
if (piv == nullptr)
throw std::runtime_error("unknown parent tag _" + v.m_parent_category + '.' + v.m_parent_keys[i]);
throw std::runtime_error("unknown parent item _" + v.m_parent_category + '.' + v.m_parent_keys[i]);
auto civ = ccv->get_validator_for_item(v.m_child_keys[i]);
if (civ == nullptr)
throw std::runtime_error("unknown child tag _" + v.m_child_category + '.' + v.m_child_keys[i]);
throw std::runtime_error("unknown child item _" + v.m_child_category + '.' + v.m_child_keys[i]);
if (civ->m_type == nullptr and piv->m_type != nullptr)
const_cast<item_validator *>(civ)->m_type = piv->m_type;
......@@ -351,7 +377,7 @@ std::vector<const link_validator *> validator::get_links_for_parent(std::string_
for (auto &l : m_link_validators)
{
if (l.m_parent_category == category)
if (iequals(l.m_parent_category, category))
result.push_back(&l);
}
......@@ -364,19 +390,32 @@ std::vector<const link_validator *> validator::get_links_for_child(std::string_v
for (auto &l : m_link_validators)
{
if (l.m_child_category == category)
if (iequals(l.m_child_category, category))
result.push_back(&l);
}
return result;
}
void validator::report_error(const std::string &msg, bool fatal) const
void validator::report_error(std::error_code ec, bool fatal) const
{
if (m_strict or fatal)
throw validation_error(msg);
else if (VERBOSE > 0)
std::cerr << msg << '\n';
throw validation_exception(ec);
else
std::cerr << ec.message() << '\n';
}
void validator::report_error(std::error_code ec, std::string_view category,
std::string_view item, bool fatal) const
{
auto ex = item.empty() ?
validation_exception(ec, category) :
validation_exception(ec, category, item);
if (m_strict or fatal)
throw ex;
else
std::cerr << ex.what() << '\n';
}
// --------------------------------------------------------------------
......@@ -438,12 +477,12 @@ const validator &validator_factory::operator[](std::string_view dictionary_name)
if (not std::filesystem::exists(p, ec) or ec)
{
for (const char *dir : {
#if defined(CACHE_DIR)
# if defined(CACHE_DIR)
CACHE_DIR,
#endif
#if defined(DATA_DIR)
# endif
# if defined(DATA_DIR)
DATA_DIR
#endif
# endif
})
{
auto p2 = std::filesystem::path(dir) / p;
......
test/CMakeLists.txt 0 → 100644
# We're using the older version 2 of Catch2
find_package(Catch2 QUIET)
if(NOT Catch2_FOUND)
FetchContent_Declare(
Catch2
GIT_REPOSITORY https://github.com/catchorg/Catch2.git
GIT_TAG v2.13.9)
FetchContent_MakeAvailable(Catch2)
set(Catch2_VERSION "2.13.9")
endif()
list(
APPEND
CIFPP_tests
unit-v2
unit-3d
format
model
rename-compound
sugar
spinner
reconstruction
validate-pdbx)
add_library(test-main OBJECT "${CMAKE_CURRENT_SOURCE_DIR}/test-main.cpp")
target_link_libraries(test-main cifpp::cifpp Catch2::Catch2)
if(${Catch2_VERSION} VERSION_GREATER_EQUAL 3.0.0)
target_compile_definitions(test-main PUBLIC CATCH22=0)
else()
target_compile_definitions(test-main PUBLIC CATCH22=1)
endif()
foreach(CIFPP_TEST IN LISTS CIFPP_tests)
set(CIFPP_TEST "${CIFPP_TEST}-test")
set(CIFPP_TEST_SOURCE "${CMAKE_CURRENT_SOURCE_DIR}/${CIFPP_TEST}.cpp")
add_executable(
${CIFPP_TEST} ${CIFPP_TEST_SOURCE} $<TARGET_OBJECTS:test-main>)
if(${Catch2_VERSION} VERSION_GREATER_EQUAL 3.0.0)
target_compile_definitions(${CIFPP_TEST} PUBLIC CATCH22=0)
else()
target_compile_definitions(${CIFPP_TEST} PUBLIC CATCH22=1)
endif()
target_link_libraries(${CIFPP_TEST} PRIVATE Threads::Threads cifpp::cifpp
Catch2::Catch2)
target_include_directories(${CIFPP_TEST} PRIVATE "${EIGEN_INCLUDE_DIR}")
if(MSVC)
# Specify unwind semantics so that MSVC knowns how to handle exceptions
target_compile_options(${CIFPP_TEST} PRIVATE /EHsc)
endif()
add_custom_target(
"run-${CIFPP_TEST}"
DEPENDS ${CMAKE_CURRENT_BINARY_DIR}/Run${CIFPP_TEST}.touch ${CIFPP_TEST})
add_custom_command(
OUTPUT ${CMAKE_CURRENT_BINARY_DIR}/Run${CIFPP_TEST}.touch
COMMAND $<TARGET_FILE:${CIFPP_TEST}> --data-dir
${CMAKE_CURRENT_SOURCE_DIR})
add_test(NAME ${CIFPP_TEST} COMMAND $<TARGET_FILE:${CIFPP_TEST}> --data-dir
${CMAKE_CURRENT_SOURCE_DIR})
endforeach()
\ No newline at end of file
test/format-test.cpp
......@@ -24,7 +24,8 @@
* SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
#include <catch2/catch.hpp>
#include "test-main.hpp"
#include <stdexcept>
......
test/model-test.cpp
......@@ -26,8 +26,6 @@
#include "test-main.hpp"
#include <catch2/catch.hpp>
#include <stdexcept>
#include <cif++.hpp>
......
test/reconstruct/cif2fasta-1cbs_insert.cif 0 → 100644
This source diff could not be displayed because it is too large. You can view the blob instead.
test/reconstruct/cif2fasta-1cbs_mutate.cif 0 → 100644
This source diff could not be displayed because it is too large. You can view the blob instead.
test/reconstruct/cif2fasta-1cbs_mutate_extend.cif 0 → 100644
This source diff could not be displayed because it is too large. You can view the blob instead.
test/reconstruct/phenix.cif 0 → 100644
This source diff could not be displayed because it is too large. You can view the blob instead.
test/reconstruction-test.cpp 0 → 100644
/*-
* SPDX-License-Identifier: BSD-2-Clause
*
* Copyright (c) 2024 NKI/AVL, Netherlands Cancer Institute
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
*
* 1. Redistributions of source code must retain the above copyright notice, this
* list of conditions and the following disclaimer
* 2. Redistributions in binary form must reproduce the above copyright notice,
* this list of conditions and the following disclaimer in the documentation
* and/or other materials provided with the distribution.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
* WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
* DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR
* ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
* (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
* ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
* SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
#include "test-main.hpp"
#include <cif++.hpp>
#include <iostream>
#include <fstream>
TEST_CASE("reconstruct")
{
cif::compound_factory::instance().push_dictionary(gTestDir / "REA.cif");
for (std::filesystem::directory_iterator i(gTestDir / "reconstruct"); i != std::filesystem::directory_iterator{}; ++i)
{
std::cout << i->path() << '\n';
if (i->path().extension() == ".pdb")
{
cif::file f = cif::pdb::read(i->path());
std::error_code ec;
if (not cif::pdb::is_valid_pdbx_file(f, ec))
CHECK(cif::pdb::reconstruct_pdbx(f));
}
else
{
cif::file f(i->path());
std::error_code ec;
CHECK_FALSE(cif::pdb::is_valid_pdbx_file(f, ec));
CHECK(ec != std::errc{});
CHECK(cif::pdb::reconstruct_pdbx(f));
}
}
}
\ No newline at end of file
test/rename-compound-test.cpp
......@@ -28,8 +28,6 @@
#include <cif++.hpp>
#include <catch2/catch.hpp>
#include <iostream>
#include <fstream>
......
test/spinner-test.cpp
#include "cif++/utilities.hpp"
/*-
* SPDX-License-Identifier: BSD-2-Clause
*
* Copyright (c) 2024 NKI/AVL, Netherlands Cancer Institute
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
*
* 1. Redistributions of source code must retain the above copyright notice, this
* list of conditions and the following disclaimer
* 2. Redistributions in binary form must reproduce the above copyright notice,
* this list of conditions and the following disclaimer in the documentation
* and/or other materials provided with the distribution.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
* WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
* DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR
* ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
* (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
* ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
* SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
#include "test-main.hpp"
#include <catch2/catch.hpp>
#include "cif++/utilities.hpp"
#include <random>
#include <thread>
......
test/sugar-test.cpp
......@@ -26,8 +26,6 @@
#include "test-main.hpp"
#include <catch2/catch.hpp>
#include <stdexcept>
#include <cif++.hpp>
......
test/test-main.cpp
#define CATCH_CONFIG_RUNNER 1
#include "test-main.hpp"
#include <cif++.hpp>
#define CATCH_CONFIG_RUNNER
#include <catch2/catch.hpp>
std::filesystem::path gTestDir = std::filesystem::current_path();
int main(int argc, char *argv[])
......@@ -12,7 +11,13 @@ int main(int argc, char *argv[])
Catch::Session session; // There must be exactly one instance
// Build a new parser on top of Catch2's
#if CATCH22
using namespace Catch::clara;
#else
// Build a new parser on top of Catch2's
using namespace Catch::Clara;
#endif
auto cli = session.cli() // Get Catch2's command line parser
| Opt(gTestDir, "data-dir") // bind variable to a new option, with a hint string
["-D"]["--data-dir"] // the option names it will respond to
......
test/test-main.hpp
/*-
* SPDX-License-Identifier: BSD-2-Clause
*
* Copyright (c) 2024 NKI/AVL, Netherlands Cancer Institute
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
*
* 1. Redistributions of source code must retain the above copyright notice, this
* list of conditions and the following disclaimer
* 2. Redistributions in binary form must reproduce the above copyright notice,
* this list of conditions and the following disclaimer in the documentation
* and/or other materials provided with the distribution.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
* WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
* DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR
* ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
* (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
* ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
* SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
#pragma once
#if CATCH22
#include <catch2/catch.hpp>
#else
#include <catch2/catch_all.hpp>
#endif
#include <filesystem>
extern std::filesystem::path gTestDir;
test/unit-3d-test.cpp
......@@ -26,8 +26,6 @@
#include "test-main.hpp"
#include <catch2/catch.hpp>
#include <stdexcept>
#include <cif++.hpp>
......
test/unit-v2-test.cpp
......@@ -26,8 +26,6 @@
#include "test-main.hpp"
#include <catch2/catch.hpp>
#include <cif++.hpp>
#include "cif++/dictionary_parser.hpp"
......@@ -568,7 +566,7 @@ _test.value
auto &test = db["test"];
REQUIRE(test.size() == 5);
REQUIRE(test.exists("value"_key == cif::null));
REQUIRE(test.contains("value"_key == cif::null));
REQUIRE(test.find("value"_key == cif::null).size() == 2);
}
......@@ -746,27 +744,51 @@ _cat_2.desc
std::istream is_data(&data_buffer);
f.load(is_data);
auto &cat1 = f.front()["cat_1"];
auto &cat2 = f.front()["cat_2"];
SECTION("one")
{
auto &cat1 = f.front()["cat_1"];
auto &cat2 = f.front()["cat_2"];
REQUIRE(cat1.size() == 3);
REQUIRE(cat2.size() == 3);
REQUIRE(cat1.size() == 3);
REQUIRE(cat2.size() == 3);
cat1.erase(cif::key("id") == 1);
cat1.erase(cif::key("id") == 1);
REQUIRE(cat1.size() == 2);
REQUIRE(cat2.size() == 1);
REQUIRE(cat1.size() == 2);
REQUIRE(cat2.size() == 1);
// REQUIRE_THROWS_AS(cat2.emplace({
// { "id", 4 },
// { "parent_id", 4 },
// { "desc", "moet fout gaan" }
// }), std::exception);
// REQUIRE_THROWS_AS(cat2.emplace({
// { "id", 4 },
// { "parent_id", 4 },
// { "desc", "moet fout gaan" }
// }), std::exception);
REQUIRE_THROWS_AS(cat2.emplace({ { "id", "vijf" }, // <- invalid value
{ "parent_id", 2 },
{ "desc", "moet fout gaan" } }),
std::exception);
REQUIRE_THROWS_AS(cat2.emplace({ { "id", "vijf" }, // <- invalid value
{ "parent_id", 2 },
{ "desc", "moet fout gaan" } }),
std::exception);
}
// SECTION("two")
// {
// auto &cat1 = f.front()["cat_1"];
// auto &cat2 = f.front()["cat_2"];
// cat1.update_value(cif::all(), "id", [](std::string_view v) -> std::string
// {
// int vi;
// auto [ec, ptr] = std::from_chars(v.data(), v.data() + v.length(), vi);
// return std::to_string(vi + 1);
// });
// REQUIRE(cat1.find1<std::string>(cif::key("id") == 2, "name") == "Aap");
// REQUIRE(cat1.find1<std::string>(cif::key("id") == 3, "name") == "Noot");
// REQUIRE(cat1.find1<std::string>(cif::key("id") == 4, "name") == "Mies");
// REQUIRE(cat2.find1<int>(cif::key("id") == 1, "parent_id") == 2);
// REQUIRE(cat2.find1<int>(cif::key("id") == 2, "parent_id") == 2);
// REQUIRE(cat2.find1<int>(cif::key("id") == 3, "parent_id") == 3);
// }
}
// --------------------------------------------------------------------
......@@ -3486,4 +3508,11 @@ TEST_CASE("pdb2cif_formula_weight")
fw = a.front()["entity"].find1<float>(cif::key("id") == 3, "formula_weight");
CHECK(fw == 18.015f);
}
// --------------------------------------------------------------------
TEST_CASE("update_values_with_provider")
{
}
\ No newline at end of file
test/validate-pdbx-test.cpp
......@@ -26,8 +26,6 @@
#include "test-main.hpp"
#include <catch2/catch.hpp>
#include <cif++.hpp>
#include <stdexcept>
......
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