Skip to content

L
libcifpp
Commit 19210df6 by Maarten L. Hekkelman
Options

Fix parsing mmCIF files with an unquoted string ??

parent 15c57307
Showing with 651 additions and 657 deletions
CMakeLists.txt
......@@ -25,7 +25,7 @@
cmake_minimum_required(VERSION 3.16)
# set the project name
project(cifpp VERSION 3.0.2 LANGUAGES CXX)
project(cifpp VERSION 3.0.4 LANGUAGES CXX)
list(PREPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_SOURCE_DIR}/cmake")
......
changelog
Version 3.0.4
- Fix in mmCIF parser, now correctly handles the unquoted
string ??
Version 3.0.3
- Better configuration checks, for atomic e.g.
- Fixed a problem introduced in refactoring mmcif::Atom
......@@ -17,6 +21,9 @@ Version 3.0.0
- Upgraded mmcif::Structure
- various other small fixes
Version 2.0.5
- Backporting updated CMakeLists.txt file
Version 2.0.4
- Reverted a too strict test when reading cif files.
......
include/cif++/CifParser.hpp
/*-
* SPDX-License-Identifier: BSD-2-Clause
*
*
* Copyright (c) 2020 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
......@@ -139,7 +139,7 @@ class SacParser
int getNextChar();
void retract();
void restart();
int restart(int start);
CIFToken getNextToken();
void match(CIFToken token);
......@@ -181,8 +181,9 @@ class SacParser
eStateTextField,
eStateFloat = 100,
eStateInt = 110,
// eStateNumericSuffix = 200,
eStateValue = 300
eStateValue = 300,
eStateDATA,
eStateSAVE
};
std::istream &mData;
......@@ -191,7 +192,6 @@ class SacParser
bool mValidate;
uint32_t mLineNr;
bool mBol;
int mState, mStart;
CIFToken mLookahead;
std::string mTokenValue;
CIFValueType mTokenType;
......
src/CifParser.cpp
/*-
* SPDX-License-Identifier: BSD-2-Clause
*
*
* Copyright (c) 2020 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
......@@ -42,7 +42,7 @@ namespace cif
const uint32_t kMaxLineLength = 132;
const uint8_t kCharTraitsTable[128] = {
// 0 1 2 3 4 5 6 7 8 9 a b c d e f
// 0 1 2 3 4 5 6 7 8 9 a b c d e f
14, 15, 14, 14, 14, 15, 15, 14, 15, 15, 15, 15, 15, 15, 15, 15, // 2
15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 10, 15, 15, 15, 15, // 3
15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, // 4
......@@ -151,23 +151,26 @@ void SacParser::retract()
mTokenValue.pop_back();
}
void SacParser::restart()
int SacParser::restart(int start)
{
int result = 0;
while (not mTokenValue.empty())
retract();
switch (mStart)
switch (start)
{
case eStateStart:
mState = mStart = eStateFloat;
result = eStateFloat;
break;
case eStateFloat:
mState = mStart = eStateInt;
result = eStateInt;
break;
case eStateInt:
mState = mStart = eStateValue;
result = eStateValue;
break;
default:
......@@ -175,6 +178,8 @@ void SacParser::restart()
}
mBol = false;
return result;
}
void SacParser::match(SacParser::CIFToken t)
......@@ -191,7 +196,7 @@ SacParser::CIFToken SacParser::getNextToken()
CIFToken result = eCIFTokenUnknown;
int quoteChar = 0;
mState = mStart = eStateStart;
int state = eStateStart, start = eStateStart;
mBol = false;
mTokenValue.clear();
......@@ -201,7 +206,7 @@ SacParser::CIFToken SacParser::getNextToken()
{
auto ch = getNextChar();
switch (mState)
switch (state)
{
case eStateStart:
if (ch == kEOF)
......@@ -209,27 +214,23 @@ SacParser::CIFToken SacParser::getNextToken()
else if (ch == '\n')
{
mBol = true;
mState = eStateWhite;
state = eStateWhite;
}
else if (ch == ' ' or ch == '\t')
mState = eStateWhite;
state = eStateWhite;
else if (ch == '#')
mState = eStateComment;
else if (ch == '.')
mState = eStateDot;
state = eStateComment;
else if (ch == '_')
mState = eStateTag;
state = eStateTag;
else if (ch == ';' and mBol)
mState = eStateTextField;
state = eStateTextField;
else if (ch == '\'' or ch == '"')
{
quoteChar = ch;
mState = eStateQuotedString;
state = eStateQuotedString;
}
else if (ch == '?')
mState = eStateQuestionMark;
else
restart();
state = start = restart(start);
break;
case eStateWhite:
......@@ -237,7 +238,7 @@ SacParser::CIFToken SacParser::getNextToken()
result = eCIFTokenEOF;
else if (not isspace(ch))
{
mState = eStateStart;
state = eStateStart;
retract();
mTokenValue.clear();
}
......@@ -248,7 +249,7 @@ SacParser::CIFToken SacParser::getNextToken()
case eStateComment:
if (ch == '\n')
{
mState = eStateStart;
state = eStateStart;
mBol = true;
mTokenValue.clear();
}
......@@ -258,44 +259,19 @@ SacParser::CIFToken SacParser::getNextToken()
error("invalid character in comment");
break;
case eStateQuestionMark:
if (isNonBlank(ch))
mState = eStateValue;
else
{
retract();
result = eCIFTokenValue;
mTokenValue.clear();
mTokenType = eCIFValueUnknown;
}
break;
case eStateDot:
if (isdigit(ch))
mState = eStateFloat + 2;
else if (isspace(ch))
{
retract();
result = eCIFTokenValue;
mTokenType = eCIFValueInapplicable;
}
else
mState = eStateValue;
break;
case eStateTextField:
if (ch == '\n')
mState = eStateTextField + 1;
state = eStateTextField + 1;
else if (ch == kEOF)
error("unterminated textfield");
else if (not isAnyPrint(ch) and cif::VERBOSE >= 0)
else if (not isAnyPrint(ch))
// error("invalid character in text field '" + string({ static_cast<char>(ch) }) + "' (" + to_string((int)ch) + ")");
std::cerr << "invalid character in text field '" << std::string({static_cast<char>(ch)}) << "' (" << ch << ") line: " << mLineNr << std::endl;
break;
case eStateTextField + 1:
if (isTextLead(ch) or ch == ' ' or ch == '\t')
mState = eStateTextField;
state = eStateTextField;
else if (ch == ';')
{
assert(mTokenValue.length() >= 2);
......@@ -313,7 +289,7 @@ SacParser::CIFToken SacParser::getNextToken()
if (ch == kEOF)
error("unterminated quoted string");
else if (ch == quoteChar)
mState = eStateQuotedStringQuote;
state = eStateQuotedStringQuote;
else if (not isAnyPrint(ch))
error("invalid character in quoted string");
break;
......@@ -331,7 +307,7 @@ SacParser::CIFToken SacParser::getNextToken()
else if (ch == quoteChar)
;
else if (isAnyPrint(ch))
mState = eStateQuotedString;
state = eStateQuotedString;
else if (ch == kEOF)
error("unterminated quoted string");
else
......@@ -349,12 +325,12 @@ SacParser::CIFToken SacParser::getNextToken()
case eStateFloat:
if (ch == '+' or ch == '-')
{
mState = eStateFloat + 1;
state = eStateFloat + 1;
}
else if (isdigit(ch))
mState = eStateFloat + 1;
state = eStateFloat + 1;
else
restart();
state = start = restart(start);
break;
case eStateFloat + 1:
......@@ -362,9 +338,9 @@ SacParser::CIFToken SacParser::getNextToken()
// mState = eStateNumericSuffix;
// else
if (ch == '.')
mState = eStateFloat + 2;
state = eStateFloat + 2;
else if (tolower(ch) == 'e')
mState = eStateFloat + 3;
state = eStateFloat + 3;
else if (isWhite(ch) or ch == kEOF)
{
retract();
......@@ -372,16 +348,13 @@ SacParser::CIFToken SacParser::getNextToken()
mTokenType = eCIFValueInt;
}
else
restart();
state = start = restart(start);
break;
// parsed '.'
case eStateFloat + 2:
// if (ch == '(') // numeric???
// mState = eStateNumericSuffix;
// else
if (tolower(ch) == 'e')
mState = eStateFloat + 3;
state = eStateFloat + 3;
else if (isWhite(ch) or ch == kEOF)
{
retract();
......@@ -389,30 +362,27 @@ SacParser::CIFToken SacParser::getNextToken()
mTokenType = eCIFValueFloat;
}
else
restart();
state = start = restart(start);
break;
// parsed 'e'
case eStateFloat + 3:
if (ch == '-' or ch == '+')
mState = eStateFloat + 4;
state = eStateFloat + 4;
else if (isdigit(ch))
mState = eStateFloat + 5;
state = eStateFloat + 5;
else
restart();
state = start = restart(start);
break;
case eStateFloat + 4:
if (isdigit(ch))
mState = eStateFloat + 5;
state = eStateFloat + 5;
else
restart();
state = start = restart(start);
break;
case eStateFloat + 5:
// if (ch == '(')
// mState = eStateNumericSuffix;
// else
if (isWhite(ch) or ch == kEOF)
{
retract();
......@@ -420,14 +390,14 @@ SacParser::CIFToken SacParser::getNextToken()
mTokenType = eCIFValueFloat;
}
else
restart();
state = start = restart(start);
break;
case eStateInt:
if (isdigit(ch) or ch == '+' or ch == '-')
mState = eStateInt + 1;
state = eStateInt + 1;
else
restart();
state = start = restart(start);
break;
case eStateInt + 1:
......@@ -438,35 +408,11 @@ SacParser::CIFToken SacParser::getNextToken()
mTokenType = eCIFValueInt;
}
else
restart();
state = start = restart(start);
break;
// case eStateNumericSuffix:
// if (isdigit(ch))
// mState = eStateNumericSuffix + 1;
// else
// restart();
// break;
//
// case eStateNumericSuffix + 1:
// if (ch == ')')
// {
// result = eCIFTokenValue;
// mTokenType = eCIFValueNumeric;
// }
// else if (not isdigit(ch))
// restart();
// break;
case eStateValue:
if (isNonBlank(ch))
mState = eStateValue + 1;
else
error("invalid character at this position");
break;
case eStateValue + 1:
if (ch == '_') // first _, check for keywords
if (ch == '_')
{
std::string s = toLowerCopy(mTokenValue);
......@@ -476,23 +422,40 @@ SacParser::CIFToken SacParser::getNextToken()
result = eCIFTokenSTOP;
else if (s == "loop_")
result = eCIFTokenLOOP;
else if (s == "data_" or s == "save_")
mState = eStateValue + 2;
else if (s == "data_")
{
state = eStateDATA;
continue;
}
else if (s == "save_")
{
state = eStateSAVE;
continue;
}
}
else if (not isNonBlank(ch))
if (result == eCIFTokenUnknown and not isNonBlank(ch))
{
retract();
result = eCIFTokenValue;
mTokenType = eCIFValueString;
if (mTokenValue == ".")
mTokenType = eCIFValueInapplicable;
else if (mTokenValue == "?")
{
mTokenType = eCIFValueUnknown;
mTokenValue.clear();
}
}
break;
case eStateValue + 2:
case eStateDATA:
case eStateSAVE:
if (not isNonBlank(ch))
{
retract();
if (tolower(mTokenValue[0]) == 'd')
if (state == eStateDATA)
result = eCIFTokenDATA;
else
result = eCIFTokenSAVE;
......@@ -521,6 +484,7 @@ SacParser::CIFToken SacParser::getNextToken()
return result;
}
DatablockIndex SacParser::indexDatablocks()
{
DatablockIndex index;
......
test/unit-test.cpp
/*-
* SPDX-License-Identifier: BSD-2-Clause
*
*
* Copyright (c) 2020 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
......@@ -31,36 +31,35 @@
#include <stdexcept>
// #include "cif++/DistanceMap.hpp"
#include "cif++/Cif++.hpp"
#include "cif++/BondMap.hpp"
#include "cif++/Cif++.hpp"
#include "cif++/CifValidator.hpp"
namespace tt = boost::test_tools;
std::filesystem::path gTestDir = std::filesystem::current_path(); // filled in first test
std::filesystem::path gTestDir = std::filesystem::current_path(); // filled in first test
// --------------------------------------------------------------------
cif::File operator""_cf(const char* text, size_t length)
cif::File operator""_cf(const char *text, size_t length)
{
struct membuf : public std::streambuf
{
membuf(char* text, size_t length)
{
this->setg(text, text, text + length);
}
} buffer(const_cast<char*>(text), length);
std::istream is(&buffer);
return cif::File(is);
struct membuf : public std::streambuf
{
membuf(char *text, size_t length)
{
this->setg(text, text, text + length);
}
} buffer(const_cast<char *>(text), length);
std::istream is(&buffer);
return cif::File(is);
}
// --------------------------------------------------------------------
bool init_unit_test()
{
cif::VERBOSE = 1;
cif::VERBOSE = 1;
// not a test, just initialize test dir
if (boost::unit_test::framework::master_test_suite().argc == 2)
......@@ -79,9 +78,9 @@ bool init_unit_test()
BOOST_AUTO_TEST_CASE(ut1)
{
// using namespace mmcif;
// using namespace mmcif;
auto f = R"(data_TEST
auto f = R"(data_TEST
#
loop_
_test.id
......@@ -91,36 +90,36 @@ _test.name
3 mies
)"_cf;
auto& db = f.firstDatablock();
auto &db = f.firstDatablock();
BOOST_CHECK(db.getName() == "TEST");
auto &test = db["test"];
BOOST_CHECK(test.size() == 3);
BOOST_CHECK(db.getName() == "TEST");
auto& test = db["test"];
BOOST_CHECK(test.size() == 3);
// wrong! the next lines will crash. And that's OK, don't do that
// for (auto r: test)
// test.erase(r);
// wrong! the next lines will crash. And that's OK, don't do that
// for (auto r: test)
// test.erase(r);
// BOOST_CHECK(test.empty());
// BOOST_CHECK(test.empty());
// test.purge();
// test.purge();
auto n = test.erase(cif::Key("id") == 1, [](const cif::Row& r) {
auto n = test.erase(cif::Key("id") == 1, [](const cif::Row &r)
{
BOOST_CHECK_EQUAL(r["id"].as<int>(), 1);
BOOST_CHECK_EQUAL(r["name"].as<std::string>(), "aap");
});
BOOST_CHECK_EQUAL(r["name"].as<std::string>(), "aap"); });
BOOST_CHECK_EQUAL(n, 1);
BOOST_CHECK_EQUAL(n, 1);
}
// --------------------------------------------------------------------
BOOST_AUTO_TEST_CASE(ut2)
{
// using namespace mmcif;
// using namespace mmcif;
auto f = R"(data_TEST
auto f = R"(data_TEST
#
loop_
_test.id
......@@ -131,36 +130,36 @@ _test.value
3 mies 1.2
)"_cf;
auto& db = f.firstDatablock();
BOOST_CHECK(db.getName() == "TEST");
auto& test = db["test"];
BOOST_CHECK(test.size() == 3);
int n = 0;
for (auto r: test.find(cif::Key("name") == "aap"))
{
BOOST_CHECK(++n == 1);
BOOST_CHECK(r["id"].as<int>() == 1);
BOOST_CHECK(r["name"].as<std::string>() == "aap");
BOOST_CHECK(r["value"].as<float>() == 1.0);
}
auto t = test.find(cif::Key("id") == 1);
BOOST_CHECK(not t.empty());
BOOST_CHECK(t.front()["name"].as<std::string>() == "aap");
auto t2 = test.find(cif::Key("value") == 1.2);
BOOST_CHECK(not t2.empty());
BOOST_CHECK(t2.front()["name"].as<std::string>() == "mies");
auto &db = f.firstDatablock();
BOOST_CHECK(db.getName() == "TEST");
auto &test = db["test"];
BOOST_CHECK(test.size() == 3);
int n = 0;
for (auto r : test.find(cif::Key("name") == "aap"))
{
BOOST_CHECK(++n == 1);
BOOST_CHECK(r["id"].as<int>() == 1);
BOOST_CHECK(r["name"].as<std::string>() == "aap");
BOOST_CHECK(r["value"].as<float>() == 1.0);
}
auto t = test.find(cif::Key("id") == 1);
BOOST_CHECK(not t.empty());
BOOST_CHECK(t.front()["name"].as<std::string>() == "aap");
auto t2 = test.find(cif::Key("value") == 1.2);
BOOST_CHECK(not t2.empty());
BOOST_CHECK(t2.front()["name"].as<std::string>() == "mies");
}
// --------------------------------------------------------------------
BOOST_AUTO_TEST_CASE(d1)
{
const char dict[] = R"(
const char dict[] = R"(
data_test_dict.dic
_datablock.id test_dict.dic
_datablock.description
......@@ -253,24 +252,24 @@ save__cat_2.desc
save_
)";
struct membuf : public std::streambuf
{
membuf(char* text, size_t length)
{
this->setg(text, text, text + length);
}
} buffer(const_cast<char*>(dict), sizeof(dict) - 1);
struct membuf : public std::streambuf
{
membuf(char *text, size_t length)
{
this->setg(text, text, text + length);
}
} buffer(const_cast<char *>(dict), sizeof(dict) - 1);
std::istream is_dict(&buffer);
std::istream is_dict(&buffer);
cif::Validator validator("test", is_dict);
cif::File f;
f.setValidator(&validator);
cif::File f;
f.setValidator(&validator);
// --------------------------------------------------------------------
// --------------------------------------------------------------------
const char data[] = R"(
const char data[] = R"(
data_test
loop_
_cat_1.id
......@@ -286,48 +285,47 @@ _cat_2.desc
1 1 'Een dier'
2 1 'Een andere aap'
3 2 'walnoot bijvoorbeeld'
)";
)";
struct data_membuf : public std::streambuf
{
data_membuf(char* text, size_t length)
{
this->setg(text, text, text + length);
}
} data_buffer(const_cast<char*>(data), sizeof(data) - 1);
struct data_membuf : public std::streambuf
{
data_membuf(char *text, size_t length)
{
this->setg(text, text, text + length);
}
} data_buffer(const_cast<char *>(data), sizeof(data) - 1);
std::istream is_data(&data_buffer);
f.load(is_data);
std::istream is_data(&data_buffer);
f.load(is_data);
auto& cat1 = f.firstDatablock()["cat_1"];
auto& cat2 = f.firstDatablock()["cat_2"];
auto &cat1 = f.firstDatablock()["cat_1"];
auto &cat2 = f.firstDatablock()["cat_2"];
BOOST_CHECK(cat1.size() == 3);
BOOST_CHECK(cat2.size() == 3);
BOOST_CHECK(cat1.size() == 3);
BOOST_CHECK(cat2.size() == 3);
cat1.erase(cif::Key("id") == 1);
cat1.erase(cif::Key("id") == 1);
BOOST_CHECK(cat1.size() == 2);
BOOST_CHECK(cat2.size() == 1);
BOOST_CHECK(cat1.size() == 2);
BOOST_CHECK(cat2.size() == 1);
// BOOST_CHECK_THROW(cat2.emplace({
// { "id", 4 },
// { "parent_id", 4 },
// { "desc", "moet fout gaan" }
// }), std::exception);
// BOOST_CHECK_THROW(cat2.emplace({
// { "id", 4 },
// { "parent_id", 4 },
// { "desc", "moet fout gaan" }
// }), std::exception);
BOOST_CHECK_THROW(cat2.emplace({
{ "id", "vijf" }, // <- invalid value
{ "parent_id", 2 },
{ "desc", "moet fout gaan" }
}), std::exception);
BOOST_CHECK_THROW(cat2.emplace({{"id", "vijf"}, // <- invalid value
{"parent_id", 2},
{"desc", "moet fout gaan"}}),
std::exception);
}
// --------------------------------------------------------------------
BOOST_AUTO_TEST_CASE(d2)
{
const char dict[] = R"(
const char dict[] = R"(
data_test_dict.dic
_datablock.id test_dict.dic
_datablock.description
......@@ -383,24 +381,24 @@ save__cat_1.c
save_
)";
struct membuf : public std::streambuf
{
membuf(char* text, size_t length)
{
this->setg(text, text, text + length);
}
} buffer(const_cast<char*>(dict), sizeof(dict) - 1);
struct membuf : public std::streambuf
{
membuf(char *text, size_t length)
{
this->setg(text, text, text + length);
}
} buffer(const_cast<char *>(dict), sizeof(dict) - 1);
std::istream is_dict(&buffer);
std::istream is_dict(&buffer);
cif::Validator validator("test", is_dict);
cif::File f;
f.setValidator(&validator);
cif::File f;
f.setValidator(&validator);
// --------------------------------------------------------------------
// --------------------------------------------------------------------
const char data[] = R"(
const char data[] = R"(
data_test
loop_
_cat_1.id
......@@ -408,39 +406,37 @@ _cat_1.c
aap Aap
noot Noot
mies Mies
)";
struct data_membuf : public std::streambuf
{
data_membuf(char* text, size_t length)
{
this->setg(text, text, text + length);
}
} data_buffer(const_cast<char*>(data), sizeof(data) - 1);
std::istream is_data(&data_buffer);
f.load(is_data);
)";
auto& cat1 = f.firstDatablock()["cat_1"];
struct data_membuf : public std::streambuf
{
data_membuf(char *text, size_t length)
{
this->setg(text, text, text + length);
}
} data_buffer(const_cast<char *>(data), sizeof(data) - 1);
BOOST_CHECK(cat1.size() == 3);
std::istream is_data(&data_buffer);
f.load(is_data);
cat1.erase(cif::Key("id") == "AAP");
auto &cat1 = f.firstDatablock()["cat_1"];
BOOST_CHECK(cat1.size() == 3);
BOOST_CHECK(cat1.size() == 3);
cat1.erase(cif::Key("id") == "noot");
cat1.erase(cif::Key("id") == "AAP");
BOOST_CHECK(cat1.size() == 2);
BOOST_CHECK(cat1.size() == 3);
cat1.erase(cif::Key("id") == "noot");
BOOST_CHECK(cat1.size() == 2);
}
// --------------------------------------------------------------------
BOOST_AUTO_TEST_CASE(d3)
{
const char dict[] = R"(
const char dict[] = R"(
data_test_dict.dic
_datablock.id test_dict.dic
_datablock.description
......@@ -533,24 +529,24 @@ save__cat_2.desc
save_
)";
struct membuf : public std::streambuf
{
membuf(char* text, size_t length)
{
this->setg(text, text, text + length);
}
} buffer(const_cast<char*>(dict), sizeof(dict) - 1);
struct membuf : public std::streambuf
{
membuf(char *text, size_t length)
{
this->setg(text, text, text + length);
}
} buffer(const_cast<char *>(dict), sizeof(dict) - 1);
std::istream is_dict(&buffer);
std::istream is_dict(&buffer);
cif::Validator validator("test", is_dict);
cif::File f;
f.setValidator(&validator);
cif::File f;
f.setValidator(&validator);
// --------------------------------------------------------------------
// --------------------------------------------------------------------
const char data[] = R"(
const char data[] = R"(
data_test
loop_
_cat_1.id
......@@ -569,84 +565,79 @@ _cat_2.desc
2 1 . 'Een andere aap'
3 2 noot 'walnoot bijvoorbeeld'
4 2 n2 hazelnoot
)";
struct data_membuf : public std::streambuf
{
data_membuf(char* text, size_t length)
{
this->setg(text, text, text + length);
}
} data_buffer(const_cast<char*>(data), sizeof(data) - 1);
std::istream is_data(&data_buffer);
f.load(is_data);
auto& cat1 = f.firstDatablock()["cat_1"];
auto& cat2 = f.firstDatablock()["cat_2"];
// check a rename in parent and child
)";
for (auto r: cat1.find(cif::Key("id") == 1))
{
r["id"] = 10;
break;
}
struct data_membuf : public std::streambuf
{
data_membuf(char *text, size_t length)
{
this->setg(text, text, text + length);
}
} data_buffer(const_cast<char *>(data), sizeof(data) - 1);
BOOST_CHECK(cat1.size() == 3);
BOOST_CHECK(cat2.size() == 4);
std::istream is_data(&data_buffer);
f.load(is_data);
BOOST_CHECK(cat1.find(cif::Key("id") == 1).size() == 0);
BOOST_CHECK(cat1.find(cif::Key("id") == 10).size() == 1);
auto &cat1 = f.firstDatablock()["cat_1"];
auto &cat2 = f.firstDatablock()["cat_2"];
BOOST_CHECK(cat2.find(cif::Key("parent_id") == 1).size() == 0);
BOOST_CHECK(cat2.find(cif::Key("parent_id") == 10).size() == 2);
// check a rename in parent and child
// check a rename in parent and child, this time only one child should be renamed
for (auto r : cat1.find(cif::Key("id") == 1))
{
r["id"] = 10;
break;
}
for (auto r: cat1.find(cif::Key("id") == 2))
{
r["id"] = 20;
break;
}
BOOST_CHECK(cat1.size() == 3);
BOOST_CHECK(cat2.size() == 4);
BOOST_CHECK(cat1.size() == 3);
BOOST_CHECK(cat2.size() == 4);
BOOST_CHECK(cat1.find(cif::Key("id") == 1).size() == 0);
BOOST_CHECK(cat1.find(cif::Key("id") == 10).size() == 1);
BOOST_CHECK(cat1.find(cif::Key("id") == 2).size() == 0);
BOOST_CHECK(cat1.find(cif::Key("id") == 20).size() == 1);
BOOST_CHECK(cat2.find(cif::Key("parent_id") == 1).size() == 0);
BOOST_CHECK(cat2.find(cif::Key("parent_id") == 10).size() == 2);
BOOST_CHECK(cat2.find(cif::Key("parent_id") == 2).size() == 1);
BOOST_CHECK(cat2.find(cif::Key("parent_id") == 20).size() == 1);
// check a rename in parent and child, this time only one child should be renamed
BOOST_CHECK(cat2.find(cif::Key("parent_id") == 2 and cif::Key("name2") == "noot").size() == 0);
BOOST_CHECK(cat2.find(cif::Key("parent_id") == 2 and cif::Key("name2") == "n2").size() == 1);
BOOST_CHECK(cat2.find(cif::Key("parent_id") == 20 and cif::Key("name2") == "noot").size() == 1);
BOOST_CHECK(cat2.find(cif::Key("parent_id") == 20 and cif::Key("name2") == "n2").size() == 0);
for (auto r : cat1.find(cif::Key("id") == 2))
{
r["id"] = 20;
break;
}
BOOST_CHECK(cat1.size() == 3);
BOOST_CHECK(cat2.size() == 4);
BOOST_CHECK(cat1.find(cif::Key("id") == 2).size() == 0);
BOOST_CHECK(cat1.find(cif::Key("id") == 20).size() == 1);
// // --------------------------------------------------------------------
// cat1.erase(cif::Key("id") == 10);
BOOST_CHECK(cat2.find(cif::Key("parent_id") == 2).size() == 1);
BOOST_CHECK(cat2.find(cif::Key("parent_id") == 20).size() == 1);
// BOOST_CHECK(cat1.size() == 2);
// BOOST_CHECK(cat2.size() == 2);
BOOST_CHECK(cat2.find(cif::Key("parent_id") == 2 and cif::Key("name2") == "noot").size() == 0);
BOOST_CHECK(cat2.find(cif::Key("parent_id") == 2 and cif::Key("name2") == "n2").size() == 1);
BOOST_CHECK(cat2.find(cif::Key("parent_id") == 20 and cif::Key("name2") == "noot").size() == 1);
BOOST_CHECK(cat2.find(cif::Key("parent_id") == 20 and cif::Key("name2") == "n2").size() == 0);
// cat1.erase(cif::Key("id") == 20);
// // --------------------------------------------------------------------
// BOOST_CHECK(cat1.size() == 1);
// BOOST_CHECK(cat2.size() == 1);
// cat1.erase(cif::Key("id") == 10);
// BOOST_CHECK(cat1.size() == 2);
// BOOST_CHECK(cat2.size() == 2);
// cat1.erase(cif::Key("id") == 20);
// BOOST_CHECK(cat1.size() == 1);
// BOOST_CHECK(cat2.size() == 1);
}
// --------------------------------------------------------------------
BOOST_AUTO_TEST_CASE(d4)
{
const char dict[] = R"(
const char dict[] = R"(
data_test_dict.dic
_datablock.id test_dict.dic
_datablock.description
......@@ -741,24 +732,24 @@ save__cat_2.parent_id3
)";
struct membuf : public std::streambuf
{
membuf(char* text, size_t length)
{
this->setg(text, text, text + length);
}
} buffer(const_cast<char*>(dict), sizeof(dict) - 1);
struct membuf : public std::streambuf
{
membuf(char *text, size_t length)
{
this->setg(text, text, text + length);
}
} buffer(const_cast<char *>(dict), sizeof(dict) - 1);
std::istream is_dict(&buffer);
std::istream is_dict(&buffer);
cif::Validator validator("test", is_dict);
cif::File f;
f.setValidator(&validator);
cif::File f;
f.setValidator(&validator);
// --------------------------------------------------------------------
// --------------------------------------------------------------------
const char data[] = R"(
const char data[] = R"(
data_test
loop_
_cat_1.id
......@@ -787,93 +778,90 @@ _cat_2.parent_id3
11 4 roos roos
12 4 . roos
13 4 roos .
)";
struct data_membuf : public std::streambuf
{
data_membuf(char* text, size_t length)
{
this->setg(text, text, text + length);
}
} data_buffer(const_cast<char*>(data), sizeof(data) - 1);
std::istream is_data(&data_buffer);
f.load(is_data);
auto& cat1 = f.firstDatablock()["cat_1"];
auto& cat2 = f.firstDatablock()["cat_2"];
)";
// check a rename in parent and child
struct data_membuf : public std::streambuf
{
data_membuf(char *text, size_t length)
{
this->setg(text, text, text + length);
}
} data_buffer(const_cast<char *>(data), sizeof(data) - 1);
for (auto r: cat1.find(cif::Key("id") == 1))
{
r["id"] = 10;
break;
}
std::istream is_data(&data_buffer);
f.load(is_data);
BOOST_CHECK(cat1.size() == 4);
BOOST_CHECK(cat2.size() == 13);
auto &cat1 = f.firstDatablock()["cat_1"];
auto &cat2 = f.firstDatablock()["cat_2"];
BOOST_CHECK(cat1.find(cif::Key("id") == 1).size() == 0);
BOOST_CHECK(cat1.find(cif::Key("id") == 10).size() == 1);
// check a rename in parent and child
BOOST_CHECK(cat2.find(cif::Key("parent_id") == 1).size() == 1);
BOOST_CHECK(cat2.find(cif::Key("parent_id") == 10).size() == 2);
for (auto r : cat1.find(cif::Key("id") == 1))
{
r["id"] = 10;
break;
}
BOOST_CHECK(cat1.size() == 4);
BOOST_CHECK(cat2.size() == 13);
for (auto r: cat1.find(cif::Key("id") == 2))
{
r["id"] = 20;
break;
}
BOOST_CHECK(cat1.find(cif::Key("id") == 1).size() == 0);
BOOST_CHECK(cat1.find(cif::Key("id") == 10).size() == 1);
BOOST_CHECK(cat1.size() == 4);
BOOST_CHECK(cat2.size() == 13);
BOOST_CHECK(cat2.find(cif::Key("parent_id") == 1).size() == 1);
BOOST_CHECK(cat2.find(cif::Key("parent_id") == 10).size() == 2);
BOOST_CHECK(cat1.find(cif::Key("id") == 2).size() == 0);
BOOST_CHECK(cat1.find(cif::Key("id") == 20).size() == 1);
for (auto r : cat1.find(cif::Key("id") == 2))
{
r["id"] = 20;
break;
}
BOOST_CHECK(cat2.find(cif::Key("parent_id") == 2).size() == 2);
BOOST_CHECK(cat2.find(cif::Key("parent_id") == 20).size() == 2);
BOOST_CHECK(cat1.size() == 4);
BOOST_CHECK(cat2.size() == 13);
BOOST_CHECK(cat1.find(cif::Key("id") == 2).size() == 0);
BOOST_CHECK(cat1.find(cif::Key("id") == 20).size() == 1);
for (auto r: cat1.find(cif::Key("id") == 3))
{
r["id"] = 30;
break;
}
BOOST_CHECK(cat2.find(cif::Key("parent_id") == 2).size() == 2);
BOOST_CHECK(cat2.find(cif::Key("parent_id") == 20).size() == 2);
BOOST_CHECK(cat1.size() == 4);
BOOST_CHECK(cat2.size() == 13);
for (auto r : cat1.find(cif::Key("id") == 3))
{
r["id"] = 30;
break;
}
BOOST_CHECK(cat1.find(cif::Key("id") == 3).size() == 0);
BOOST_CHECK(cat1.find(cif::Key("id") == 30).size() == 1);
BOOST_CHECK(cat1.size() == 4);
BOOST_CHECK(cat2.size() == 13);
BOOST_CHECK(cat2.find(cif::Key("parent_id") == 3).size() == 2);
BOOST_CHECK(cat2.find(cif::Key("parent_id") == 30).size() == 1);
BOOST_CHECK(cat1.find(cif::Key("id") == 3).size() == 0);
BOOST_CHECK(cat1.find(cif::Key("id") == 30).size() == 1);
BOOST_CHECK(cat2.find(cif::Key("parent_id") == 3).size() == 2);
BOOST_CHECK(cat2.find(cif::Key("parent_id") == 30).size() == 1);
for (auto r: cat1.find(cif::Key("id") == 4))
{
r["id"] = 40;
break;
}
for (auto r : cat1.find(cif::Key("id") == 4))
{
r["id"] = 40;
break;
}
BOOST_CHECK(cat1.size() == 4);
BOOST_CHECK(cat2.size() == 13);
BOOST_CHECK(cat1.size() == 4);
BOOST_CHECK(cat2.size() == 13);
BOOST_CHECK(cat1.find(cif::Key("id") == 4).size() == 0);
BOOST_CHECK(cat1.find(cif::Key("id") == 10).size() == 1);
BOOST_CHECK(cat1.find(cif::Key("id") == 4).size() == 0);
BOOST_CHECK(cat1.find(cif::Key("id") == 10).size() == 1);
BOOST_CHECK(cat2.find(cif::Key("parent_id") == 4).size() == 3);
BOOST_CHECK(cat2.find(cif::Key("parent_id") == 40).size() == 0);
BOOST_CHECK(cat2.find(cif::Key("parent_id") == 4).size() == 3);
BOOST_CHECK(cat2.find(cif::Key("parent_id") == 40).size() == 0);
}
// --------------------------------------------------------------------
BOOST_AUTO_TEST_CASE(d5)
{
const char dict[] = R"(
const char dict[] = R"(
data_test_dict.dic
_datablock.id test_dict.dic
_datablock.description
......@@ -965,24 +953,24 @@ cat_2 2 cat_2:cat_1:2
cat_2 3 cat_2:cat_1:3
)";
struct membuf : public std::streambuf
{
membuf(char* text, size_t length)
{
this->setg(text, text, text + length);
}
} buffer(const_cast<char*>(dict), sizeof(dict) - 1);
struct membuf : public std::streambuf
{
membuf(char *text, size_t length)
{
this->setg(text, text, text + length);
}
} buffer(const_cast<char *>(dict), sizeof(dict) - 1);
std::istream is_dict(&buffer);
std::istream is_dict(&buffer);
cif::Validator validator("test", is_dict);
cif::File f;
f.setValidator(&validator);
cif::File f;
f.setValidator(&validator);
// --------------------------------------------------------------------
// --------------------------------------------------------------------
const char data[] = R"(
const char data[] = R"(
data_test
loop_
_cat_1.id
......@@ -1004,119 +992,120 @@ _cat_2.parent_id3
7 3 3 3
)";
// --------------------------------------------------------------------
struct data_membuf : public std::streambuf
{
data_membuf(char* text, size_t length)
{
this->setg(text, text, text + length);
}
} data_buffer(const_cast<char*>(data), sizeof(data) - 1);
std::istream is_data(&data_buffer);
f.load(is_data);
auto& cat1 = f.firstDatablock()["cat_1"];
auto& cat2 = f.firstDatablock()["cat_2"];
// --------------------------------------------------------------------
// check iterate children
auto PR2set = cat1.find(cif::Key("id") == 2);
BOOST_ASSERT(PR2set.size() == 1);
auto PR2 = PR2set.front();
BOOST_CHECK(PR2["id"].as<int>() == 2);
auto CR2set = cat1.getChildren(PR2, "cat_2");
BOOST_ASSERT(CR2set.size() == 3);
std::vector<int> CRids;
std::transform(CR2set.begin(), CR2set.end(), std::back_inserter(CRids), [](cif::Row r) { return r["id"].as<int>(); });
std::sort(CRids.begin(), CRids.end());
BOOST_CHECK(CRids == std::vector<int>({ 4, 5, 6}));
// check a rename in parent and child
for (auto r: cat1.find(cif::Key("id") == 1))
{
r["id"] = 10;
break;
}
BOOST_CHECK(cat1.size() == 3);
BOOST_CHECK(cat2.size() == 7);
BOOST_CHECK(cat1.find(cif::Key("id") == 1).size() == 0);
BOOST_CHECK(cat1.find(cif::Key("id") == 10).size() == 1);
BOOST_CHECK(cat2.find(cif::Key("parent_id") == 1).size() == 0);
BOOST_CHECK(cat2.find(cif::Key("parent_id2") == 1).size() == 0);
BOOST_CHECK(cat2.find(cif::Key("parent_id3") == 1).size() == 0);
BOOST_CHECK(cat2.find(cif::Key("parent_id") == 10).size() == 1);
BOOST_CHECK(cat2.find(cif::Key("parent_id2") == 10).size() == 1);
BOOST_CHECK(cat2.find(cif::Key("parent_id3") == 10).size() == 1);
for (auto r: cat1.find(cif::Key("id") == 2))
{
r["id"] = 20;
break;
}
BOOST_CHECK(cat1.size() == 3);
BOOST_CHECK(cat2.size() == 7);
BOOST_CHECK(cat1.find(cif::Key("id") == 2).size() == 0);
BOOST_CHECK(cat1.find(cif::Key("id") == 20).size() == 1);
BOOST_CHECK(cat2.find(cif::Key("parent_id") == 2).size() == 0);
BOOST_CHECK(cat2.find(cif::Key("parent_id2") == 2).size() == 0);
BOOST_CHECK(cat2.find(cif::Key("parent_id3") == 2).size() == 0);
BOOST_CHECK(cat2.find(cif::Key("parent_id") == 20).size() == 2);
BOOST_CHECK(cat2.find(cif::Key("parent_id2") == 20).size() == 2);
BOOST_CHECK(cat2.find(cif::Key("parent_id3") == 20).size() == 2);
for (auto r: cat1.find(cif::Key("id") == 3))
{
r["id"] = 30;
break;
}
BOOST_CHECK(cat1.size() == 3);
BOOST_CHECK(cat2.size() == 7);
BOOST_CHECK(cat1.find(cif::Key("id") == 3).size() == 0);
BOOST_CHECK(cat1.find(cif::Key("id") == 30).size() == 1);
BOOST_CHECK(cat2.find(cif::Key("parent_id") == 3).size() == 0);
BOOST_CHECK(cat2.find(cif::Key("parent_id2") == 3).size() == 0);
BOOST_CHECK(cat2.find(cif::Key("parent_id3") == 3).size() == 0);
BOOST_CHECK(cat2.find(cif::Key("parent_id") == 30).size() == 1);
BOOST_CHECK(cat2.find(cif::Key("parent_id2") == 30).size() == 1);
BOOST_CHECK(cat2.find(cif::Key("parent_id3") == 30).size() == 1);
// test delete
cat1.erase(cif::Key("id") == 10);
BOOST_CHECK(cat1.size() == 2);
BOOST_CHECK(cat2.size() == 4);
cat1.erase(cif::Key("id") == 20);
BOOST_CHECK(cat1.size() == 1);
BOOST_CHECK(cat2.size() == 1);
cat1.erase(cif::Key("id") == 30);
BOOST_CHECK(cat1.size() == 0);
BOOST_CHECK(cat2.size() == 0);
// --------------------------------------------------------------------
struct data_membuf : public std::streambuf
{
data_membuf(char *text, size_t length)
{
this->setg(text, text, text + length);
}
} data_buffer(const_cast<char *>(data), sizeof(data) - 1);
std::istream is_data(&data_buffer);
f.load(is_data);
auto &cat1 = f.firstDatablock()["cat_1"];
auto &cat2 = f.firstDatablock()["cat_2"];
// --------------------------------------------------------------------
// check iterate children
auto PR2set = cat1.find(cif::Key("id") == 2);
BOOST_ASSERT(PR2set.size() == 1);
auto PR2 = PR2set.front();
BOOST_CHECK(PR2["id"].as<int>() == 2);
auto CR2set = cat1.getChildren(PR2, "cat_2");
BOOST_ASSERT(CR2set.size() == 3);
std::vector<int> CRids;
std::transform(CR2set.begin(), CR2set.end(), std::back_inserter(CRids), [](cif::Row r)
{ return r["id"].as<int>(); });
std::sort(CRids.begin(), CRids.end());
BOOST_CHECK(CRids == std::vector<int>({4, 5, 6}));
// check a rename in parent and child
for (auto r : cat1.find(cif::Key("id") == 1))
{
r["id"] = 10;
break;
}
BOOST_CHECK(cat1.size() == 3);
BOOST_CHECK(cat2.size() == 7);
BOOST_CHECK(cat1.find(cif::Key("id") == 1).size() == 0);
BOOST_CHECK(cat1.find(cif::Key("id") == 10).size() == 1);
BOOST_CHECK(cat2.find(cif::Key("parent_id") == 1).size() == 0);
BOOST_CHECK(cat2.find(cif::Key("parent_id2") == 1).size() == 0);
BOOST_CHECK(cat2.find(cif::Key("parent_id3") == 1).size() == 0);
BOOST_CHECK(cat2.find(cif::Key("parent_id") == 10).size() == 1);
BOOST_CHECK(cat2.find(cif::Key("parent_id2") == 10).size() == 1);
BOOST_CHECK(cat2.find(cif::Key("parent_id3") == 10).size() == 1);
for (auto r : cat1.find(cif::Key("id") == 2))
{
r["id"] = 20;
break;
}
BOOST_CHECK(cat1.size() == 3);
BOOST_CHECK(cat2.size() == 7);
BOOST_CHECK(cat1.find(cif::Key("id") == 2).size() == 0);
BOOST_CHECK(cat1.find(cif::Key("id") == 20).size() == 1);
BOOST_CHECK(cat2.find(cif::Key("parent_id") == 2).size() == 0);
BOOST_CHECK(cat2.find(cif::Key("parent_id2") == 2).size() == 0);
BOOST_CHECK(cat2.find(cif::Key("parent_id3") == 2).size() == 0);
BOOST_CHECK(cat2.find(cif::Key("parent_id") == 20).size() == 2);
BOOST_CHECK(cat2.find(cif::Key("parent_id2") == 20).size() == 2);
BOOST_CHECK(cat2.find(cif::Key("parent_id3") == 20).size() == 2);
for (auto r : cat1.find(cif::Key("id") == 3))
{
r["id"] = 30;
break;
}
BOOST_CHECK(cat1.size() == 3);
BOOST_CHECK(cat2.size() == 7);
BOOST_CHECK(cat1.find(cif::Key("id") == 3).size() == 0);
BOOST_CHECK(cat1.find(cif::Key("id") == 30).size() == 1);
BOOST_CHECK(cat2.find(cif::Key("parent_id") == 3).size() == 0);
BOOST_CHECK(cat2.find(cif::Key("parent_id2") == 3).size() == 0);
BOOST_CHECK(cat2.find(cif::Key("parent_id3") == 3).size() == 0);
BOOST_CHECK(cat2.find(cif::Key("parent_id") == 30).size() == 1);
BOOST_CHECK(cat2.find(cif::Key("parent_id2") == 30).size() == 1);
BOOST_CHECK(cat2.find(cif::Key("parent_id3") == 30).size() == 1);
// test delete
cat1.erase(cif::Key("id") == 10);
BOOST_CHECK(cat1.size() == 2);
BOOST_CHECK(cat2.size() == 4);
cat1.erase(cif::Key("id") == 20);
BOOST_CHECK(cat1.size() == 1);
BOOST_CHECK(cat2.size() == 1);
cat1.erase(cif::Key("id") == 30);
BOOST_CHECK(cat1.size() == 0);
BOOST_CHECK(cat2.size() == 0);
}
// --------------------------------------------------------------------
BOOST_AUTO_TEST_CASE(c1)
{
cif::VERBOSE = 1;
cif::VERBOSE = 1;
auto f = R"(data_TEST
auto f = R"(data_TEST
#
loop_
_test.id
......@@ -1128,52 +1117,52 @@ _test.name
5 ?
)"_cf;
auto& db = f.firstDatablock();
for (auto r: db["test"].find(cif::Key("id") == 1))
{
const auto& [id, name] = r.get<int, std::string>({"id", "name"});
BOOST_CHECK(id == 1);
BOOST_CHECK(name == "aap");
}
for (auto r: db["test"].find(cif::Key("id") == 4))
{
const auto& [id, name] = r.get<int, std::string>({"id", "name"});
BOOST_CHECK(id == 4);
BOOST_CHECK(name.empty());
}
for (auto r: db["test"].find(cif::Key("id") == 5))
{
const auto& [id, name] = r.get<int, std::string>({"id", "name"});
BOOST_CHECK(id == 5);
BOOST_CHECK(name.empty());
}
// optional
for (auto r: db["test"])
{
const auto& [id, name] = r.get<int, std::optional<std::string>>({"id", "name"});
switch (id)
{
case 1: BOOST_CHECK(name == "aap"); break;
case 2: BOOST_CHECK(name == "noot"); break;
case 3: BOOST_CHECK(name == "mies"); break;
case 4:
case 5: BOOST_CHECK(not name); break;
default:
BOOST_CHECK(false);
}
}
auto &db = f.firstDatablock();
for (auto r : db["test"].find(cif::Key("id") == 1))
{
const auto &[id, name] = r.get<int, std::string>({"id", "name"});
BOOST_CHECK(id == 1);
BOOST_CHECK(name == "aap");
}
for (auto r : db["test"].find(cif::Key("id") == 4))
{
const auto &[id, name] = r.get<int, std::string>({"id", "name"});
BOOST_CHECK(id == 4);
BOOST_CHECK(name.empty());
}
for (auto r : db["test"].find(cif::Key("id") == 5))
{
const auto &[id, name] = r.get<int, std::string>({"id", "name"});
BOOST_CHECK(id == 5);
BOOST_CHECK(name.empty());
}
// optional
for (auto r : db["test"])
{
const auto &[id, name] = r.get<int, std::optional<std::string>>({"id", "name"});
switch (id)
{
case 1: BOOST_CHECK(name == "aap"); break;
case 2: BOOST_CHECK(name == "noot"); break;
case 3: BOOST_CHECK(name == "mies"); break;
case 4:
case 5: BOOST_CHECK(not name); break;
default:
BOOST_CHECK(false);
}
}
}
BOOST_AUTO_TEST_CASE(c2)
{
cif::VERBOSE = 1;
cif::VERBOSE = 1;
auto f = R"(data_TEST
auto f = R"(data_TEST
#
loop_
_test.id
......@@ -1185,31 +1174,30 @@ _test.name
5 ?
)"_cf;
auto& db = f.firstDatablock();
// query tests
for (const auto& [id, name]: db["test"].rows<int, std::optional<std::string>>("id", "name"))
{
switch (id)
{
case 1: BOOST_CHECK(name == "aap"); break;
case 2: BOOST_CHECK(name == "noot"); break;
case 3: BOOST_CHECK(name == "mies"); break;
case 4:
case 5: BOOST_CHECK(not name); break;
default:
BOOST_CHECK(false);
}
}
}
auto &db = f.firstDatablock();
// query tests
for (const auto &[id, name] : db["test"].rows<int, std::optional<std::string>>("id", "name"))
{
switch (id)
{
case 1: BOOST_CHECK(name == "aap"); break;
case 2: BOOST_CHECK(name == "noot"); break;
case 3: BOOST_CHECK(name == "mies"); break;
case 4:
case 5: BOOST_CHECK(not name); break;
default:
BOOST_CHECK(false);
}
}
}
BOOST_AUTO_TEST_CASE(c3)
{
cif::VERBOSE = 1;
cif::VERBOSE = 1;
auto f = R"(data_TEST
auto f = R"(data_TEST
#
loop_
_test.id
......@@ -1221,27 +1209,27 @@ _test.name
5 ?
)"_cf;
auto& db = f.firstDatablock();
// query tests
for (const auto& [id, name]: db["test"].find<int, std::optional<std::string>>(cif::All(), "id", "name"))
{
switch (id)
{
case 1: BOOST_CHECK(name == "aap"); break;
case 2: BOOST_CHECK(name == "noot"); break;
case 3: BOOST_CHECK(name == "mies"); break;
case 4:
case 5: BOOST_CHECK(not name); break;
default:
BOOST_CHECK(false);
}
}
const auto& [id, name] = db["test"].find1<int, std::string>(cif::Key("id") == 1, "id", "name");
BOOST_CHECK(id == 1);
BOOST_CHECK(name == "aap");
auto &db = f.firstDatablock();
// query tests
for (const auto &[id, name] : db["test"].find<int, std::optional<std::string>>(cif::All(), "id", "name"))
{
switch (id)
{
case 1: BOOST_CHECK(name == "aap"); break;
case 2: BOOST_CHECK(name == "noot"); break;
case 3: BOOST_CHECK(name == "mies"); break;
case 4:
case 5: BOOST_CHECK(not name); break;
default:
BOOST_CHECK(false);
}
}
const auto &[id, name] = db["test"].find1<int, std::string>(cif::Key("id") == 1, "id", "name");
BOOST_CHECK(id == 1);
BOOST_CHECK(name == "aap");
}
// --------------------------------------------------------------------
......@@ -1250,22 +1238,22 @@ _test.name
BOOST_AUTO_TEST_CASE(r1)
{
/*
Rationale:
The pdbx_mmcif dictionary contains inconsistent child-parent relations. E.g. atom_site is parent
of pdbx_nonpoly_scheme which itself is a parent of pdbx_entity_nonpoly. If I want to rename a residue
I cannot update pdbx_nonpoly_scheme since changing a parent changes children, but not vice versa.
But if I change the comp_id in atom_site, the pdbx_nonpoly_scheme is update, that's good, and then
pdbx_entity_nonpoly is updated and that's bad.
The idea is now that if we update a parent and a child that must change as well, we first check
if there are more parents of this child that will not change. In that case we have to split the
child into two, one with the new value and one with the old. We then of course have to split all
children of this split row that are direct children.
Rationale:
The pdbx_mmcif dictionary contains inconsistent child-parent relations. E.g. atom_site is parent
of pdbx_nonpoly_scheme which itself is a parent of pdbx_entity_nonpoly. If I want to rename a residue
I cannot update pdbx_nonpoly_scheme since changing a parent changes children, but not vice versa.
But if I change the comp_id in atom_site, the pdbx_nonpoly_scheme is update, that's good, and then
pdbx_entity_nonpoly is updated and that's bad.
The idea is now that if we update a parent and a child that must change as well, we first check
if there are more parents of this child that will not change. In that case we have to split the
child into two, one with the new value and one with the old. We then of course have to split all
children of this split row that are direct children.
*/
const char dict[] = R"(
const char dict[] = R"(
data_test_dict.dic
_datablock.id test_dict.dic
_datablock.description
......@@ -1394,23 +1382,23 @@ cat_2 1 '_cat_2.num' '_cat_3.num' cat_3
)";
struct membuf : public std::streambuf
{
membuf(char* text, size_t length)
{
this->setg(text, text, text + length);
}
} buffer(const_cast<char*>(dict), sizeof(dict) - 1);
struct membuf : public std::streambuf
{
membuf(char *text, size_t length)
{
this->setg(text, text, text + length);
}
} buffer(const_cast<char *>(dict), sizeof(dict) - 1);
std::istream is_dict(&buffer);
std::istream is_dict(&buffer);
cif::Validator validator("test", is_dict);
cif::File f;
f.setValidator(&validator);
cif::File f;
f.setValidator(&validator);
// --------------------------------------------------------------------
// --------------------------------------------------------------------
const char data[] = R"(
const char data[] = R"(
data_test
loop_
_cat_1.id
......@@ -1435,29 +1423,29 @@ _cat_3.name
_cat_3.num
1 aap 1
2 aap 2
)";
)";
using namespace cif::literals;
struct data_membuf : public std::streambuf
{
data_membuf(char* text, size_t length)
{
this->setg(text, text, text + length);
}
} data_buffer(const_cast<char*>(data), sizeof(data) - 1);
struct data_membuf : public std::streambuf
{
data_membuf(char *text, size_t length)
{
this->setg(text, text, text + length);
}
} data_buffer(const_cast<char *>(data), sizeof(data) - 1);
std::istream is_data(&data_buffer);
f.load(is_data);
std::istream is_data(&data_buffer);
f.load(is_data);
auto& cat1 = f.firstDatablock()["cat_1"];
auto& cat2 = f.firstDatablock()["cat_2"];
auto& cat3 = f.firstDatablock()["cat_3"];
auto &cat1 = f.firstDatablock()["cat_1"];
auto &cat2 = f.firstDatablock()["cat_2"];
auto &cat3 = f.firstDatablock()["cat_3"];
cat3.update_value("name"_key == "aap" and "num"_key == 1, "name", "aapje");
BOOST_CHECK(cat3.size() == 2);
{
int id, num;
std::string name;
......@@ -1471,9 +1459,9 @@ _cat_3.num
BOOST_CHECK(num == 2);
BOOST_CHECK(name == "aap");
}
int i = 0;
for (const auto &[id, name, num, desc]: cat2.rows<int,std::string,int,std::string>("id", "name", "num", "desc"))
int i = 0;
for (const auto &[id, name, num, desc] : cat2.rows<int, std::string, int, std::string>("id", "name", "num", "desc"))
{
switch (++i)
{
......@@ -1497,7 +1485,7 @@ _cat_3.num
BOOST_CHECK(name == "noot");
BOOST_CHECK(desc == "walnoot bijvoorbeeld");
break;
default:
BOOST_FAIL("Unexpected record");
}
......@@ -1505,7 +1493,7 @@ _cat_3.num
BOOST_CHECK(cat1.size() == 4);
i = 0;
for (const auto &[id, name, desc]: cat1.rows<int,std::string,std::string>("id", "name", "desc"))
for (const auto &[id, name, desc] : cat1.rows<int, std::string, std::string>("id", "name", "desc"))
{
switch (++i)
{
......@@ -1526,13 +1514,13 @@ _cat_3.num
BOOST_CHECK(name == "mies");
BOOST_CHECK(desc == "Mies");
break;
case 4:
BOOST_CHECK(id == 4);
BOOST_CHECK(name == "aap");
BOOST_CHECK(desc == "Aap");
break;
default:
BOOST_FAIL("Unexpected record");
}
......@@ -1545,7 +1533,7 @@ _cat_3.num
BOOST_AUTO_TEST_CASE(bondmap_1)
{
cif::VERBOSE = 2;
cif::VERBOSE = 2;
// sections taken from CCD compounds.cif
auto components = R"(
......@@ -1634,7 +1622,7 @@ PRO CD HD3 SING N N 16
PRO OXT HXT SING N N 17
)"_cf;
const std::filesystem::path example(gTestDir / ".."/"examples"/"1cbs.cif.gz");
const std::filesystem::path example(gTestDir / ".." / "examples" / "1cbs.cif.gz");
mmcif::File file(example.string());
mmcif::Structure structure(file);
......@@ -1642,11 +1630,11 @@ PRO OXT HXT SING N N 17
mmcif::BondMap bm(structure);
// Test the bonds of the first three residues, that's PRO A 1, ASN A 2, PHE A 3
// Test the bonds of the first three residues, that's PRO A 1, ASN A 2, PHE A 3
for (const auto& [compound, seqnr]: std::initializer_list<std::tuple<std::string,int>>{ { "PRO", 1 }, { "ASN", 2 }, { "PHE", 3 } })
for (const auto &[compound, seqnr] : std::initializer_list<std::tuple<std::string, int>>{{"PRO", 1}, {"ASN", 2}, {"PHE", 3}})
{
auto& res = structure.getResidue("A", compound, seqnr);
auto &res = structure.getResidue("A", compound, seqnr);
auto atoms = res.atoms();
auto dc = components.get(compound);
......@@ -1655,14 +1643,14 @@ PRO OXT HXT SING N N 17
auto cc = dc->get("chem_comp_bond");
BOOST_ASSERT(cc != nullptr);
std::set<std::tuple<std::string,std::string>> bonded;
std::set<std::tuple<std::string, std::string>> bonded;
for (const auto& [atom_id_1, atom_id_2]: cc->rows<std::string,std::string>("atom_id_1", "atom_id_2"))
for (const auto &[atom_id_1, atom_id_2] : cc->rows<std::string, std::string>("atom_id_1", "atom_id_2"))
{
if (atom_id_1 > atom_id_2)
bonded.insert({ atom_id_2, atom_id_1 });
bonded.insert({atom_id_2, atom_id_1});
else
bonded.insert({ atom_id_1, atom_id_2 });
bonded.insert({atom_id_1, atom_id_2});
}
for (size_t i = 0; i + 1 < atoms.size(); ++i)
......@@ -1677,8 +1665,8 @@ PRO OXT HXT SING N N 17
bool bonded_1_i = bm(atoms[j], atoms[i]);
bool bonded_t = label_i > label_j
? bonded.count({ label_j, label_i })
: bonded.count({ label_i, label_j });
? bonded.count({label_j, label_i})
: bonded.count({label_i, label_j});
BOOST_CHECK(bonded_1 == bonded_t);
BOOST_CHECK(bonded_1_i == bonded_t);
......@@ -1718,20 +1706,19 @@ BOOST_AUTO_TEST_CASE(t1)
// q = Normalize(q);
// Quaternion q{ 0.1, 0.2, 0.3, 0.4 };
Quaternion q{ 0.5, 0.5, 0.5, 0.5 };
Quaternion q{0.5, 0.5, 0.5, 0.5};
q = Normalize(q);
const auto &&[angle0, axis0] = QuaternionToAngleAxis(q);
std::vector<Point> p1{
{ 16.979, 13.301, 44.555 },
{ 18.150, 13.525, 43.680 },
{ 18.656, 14.966, 43.784 },
{ 17.890, 15.889, 44.078 },
{ 17.678, 13.270, 42.255 },
{ 16.248, 13.734, 42.347 },
{ 15.762, 13.216, 43.724 }
};
{16.979, 13.301, 44.555},
{18.150, 13.525, 43.680},
{18.656, 14.966, 43.784},
{17.890, 15.889, 44.078},
{17.678, 13.270, 42.255},
{16.248, 13.734, 42.347},
{15.762, 13.216, 43.724}};
auto p2 = p1;
......@@ -1739,7 +1726,7 @@ BOOST_AUTO_TEST_CASE(t1)
for (auto &p : p2)
p.rotate(q);
CenterPoints(p2);
auto q2 = AlignPoints(p1, p2);
......@@ -1757,3 +1744,38 @@ BOOST_AUTO_TEST_CASE(t1)
// std::cout << "rmsd: " << RMSd(p1, p2) << std::endl;
}
BOOST_AUTO_TEST_CASE(parser_test_1)
{
auto data1 = R"(
data_QM
_test.text ??
)"_cf;
auto &db1 = data1.firstDatablock();
auto &test1 = db1["test"];
BOOST_CHECK_EQUAL(test1.size(), 1);
for (auto r : test1)
{
const auto &[text] = r.get<std::string>({"text"});
BOOST_CHECK_EQUAL(text, "??");
}
std::stringstream ss;
data1.save(ss);
auto data2 = cif::File(ss);
auto &db2 = data2.firstDatablock();
auto &test2 = db2["test"];
BOOST_CHECK_EQUAL(test2.size(), 1);
for (auto r : test2)
{
const auto &[text] = r.get<std::string>({"text"});
BOOST_CHECK_EQUAL(text, "??");
}
}
\ No newline at end of file
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment