2 * This file is part of the GROMACS molecular simulation package.
4 * Copyright (c) 2015,2016,2017,2019,2020, by the GROMACS development team, led by
5 * Mark Abraham, David van der Spoel, Berk Hess, and Erik Lindahl,
6 * and including many others, as listed in the AUTHORS file in the
7 * top-level source directory and at http://www.gromacs.org.
9 * GROMACS is free software; you can redistribute it and/or
10 * modify it under the terms of the GNU Lesser General Public License
11 * as published by the Free Software Foundation; either version 2.1
12 * of the License, or (at your option) any later version.
14 * GROMACS is distributed in the hope that it will be useful,
15 * but WITHOUT ANY WARRANTY; without even the implied warranty of
16 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
17 * Lesser General Public License for more details.
19 * You should have received a copy of the GNU Lesser General Public
20 * License along with GROMACS; if not, see
21 * http://www.gnu.org/licenses, or write to the Free Software Foundation,
22 * Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
24 * If you want to redistribute modifications to GROMACS, please
25 * consider that scientific software is very special. Version
26 * control is crucial - bugs must be traceable. We will be happy to
27 * consider code for inclusion in the official distribution, but
28 * derived work must not be called official GROMACS. Details are found
29 * in the README & COPYING files - if they are missing, get the
30 * official version at http://www.gromacs.org.
32 * To help us fund GROMACS development, we humbly ask that you cite
33 * the research papers on the package. Check out http://www.gromacs.org.
37 * Implements reference data XML persistence.
39 * \author Teemu Murtola <teemu.murtola@gmail.com>
40 * \author Mark Abraham <mark.j.abraham@gmail.com>
41 * \ingroup module_testutils
45 #include "refdata_xml.h"
49 #include "gromacs/utility/exceptions.h"
51 #include "testutils/testexceptions.h"
53 #include "refdata_impl.h"
63 //! XML version declaration used when writing the reference data.
64 const char* const c_VersionDeclarationString = "xml version=\"1.0\"";
65 //! XML stylesheet declaration used for writing the reference data.
66 const char* const c_StyleSheetDeclarationString =
67 "xml-stylesheet type=\"text/xsl\" href=\"referencedata.xsl\"";
68 //! Name of the root element in reference data XML files.
69 const char* const c_RootNodeName = "ReferenceData";
70 //! Name of the XML attribute used to store identifying strings for reference data elements.
71 const char* const c_IdAttrName = "Name";
75 /********************************************************************
82 //! Convenience typedef
83 typedef tinyxml2::XMLDocument* XMLDocumentPtr;
84 //! Convenience typedef
85 typedef tinyxml2::XMLNode* XMLNodePtr;
86 //! Convenience typedef
87 typedef tinyxml2::XMLElement* XMLElementPtr;
88 //! Convenience typedef
89 typedef tinyxml2::XMLText* XMLTextPtr;
91 //! \name Helper functions for XML reading
94 void readEntry(XMLNodePtr node, ReferenceDataEntry* entry);
96 XMLNodePtr getCDataChildNode(XMLNodePtr node)
98 XMLNodePtr cdata = node->FirstChild();
99 while (cdata != nullptr && cdata->ToText() != nullptr && !cdata->ToText()->CData())
101 cdata = cdata->NextSibling();
106 bool hasCDataContent(XMLNodePtr node)
108 return getCDataChildNode(node) != nullptr;
111 //! Return a node convertible to text, either \c childNode or its first such sibling.
112 XMLNodePtr getNextTextChildNode(XMLNodePtr childNode)
114 // Note that when reading, we don't have to care if it is in a
115 // CDATA section, or not.
116 while (childNode != nullptr)
118 if (childNode->ToText() != nullptr)
122 childNode = childNode->NextSibling();
127 //! Return the concatenation of all the text children of \c node, including multiple CDATA children.
128 std::string getValueFromLeafElement(XMLNodePtr node)
132 XMLNodePtr childNode = getNextTextChildNode(node->FirstChild());
133 while (childNode != nullptr)
135 value += std::string(childNode->Value());
137 childNode = getNextTextChildNode(childNode->NextSibling());
140 if (hasCDataContent(node))
142 // Prepare to strip the convenience newline added in
143 // createElementContents, when writing CDATA content for
145 if (value.empty() || value[0] != '\n')
147 GMX_THROW(TestException("Invalid string block in reference data"));
155 //! Make a new entry from \c element.
156 ReferenceDataEntry::EntryPointer createEntry(XMLElementPtr element)
158 const char* id = element->Attribute(c_IdAttrName);
159 ReferenceDataEntry::EntryPointer entry(new ReferenceDataEntry(element->Value(), id));
163 //! Read the child entries of \c parentElement and transfer the contents to \c entry
164 void readChildEntries(XMLNodePtr parentElement, ReferenceDataEntry* entry)
166 XMLElementPtr childElement = parentElement->FirstChildElement();
167 while (childElement != nullptr)
169 ReferenceDataEntry::EntryPointer child(createEntry(childElement));
170 readEntry(childElement, child.get());
171 entry->addChild(move(child));
172 childElement = childElement->NextSiblingElement();
176 //! Return whether \c node has child XML elements (rather than text content).
177 bool isCompoundElement(XMLNodePtr node)
179 return node->FirstChildElement() != nullptr;
182 //! Read \c element and transfer the contents to \c entry
183 void readEntry(XMLNodePtr element, ReferenceDataEntry* entry)
185 if (isCompoundElement(element))
187 readChildEntries(element, entry);
189 else if (hasCDataContent(element))
191 entry->setTextBlockValue(getValueFromLeafElement(element));
195 entry->setValue(getValueFromLeafElement(element));
204 ReferenceDataEntry::EntryPointer readReferenceDataFile(const std::string& path)
206 tinyxml2::XMLDocument document;
207 document.LoadFile(path.c_str());
208 if (document.Error())
210 const char* errorStr1 = document.GetErrorStr1();
211 const char* errorStr2 = document.GetErrorStr2();
212 std::string errorString("Error was ");
215 errorString += errorStr1;
219 errorString += errorStr2;
221 if (!errorStr1 && !errorStr2)
223 errorString += "not specified.";
225 GMX_THROW(TestException("Reference data not parsed successfully: " + path + "\n."
226 + errorString + "\n"));
228 XMLElementPtr rootNode = document.RootElement();
229 if (rootNode == nullptr)
231 GMX_THROW(TestException("Reference data is empty: " + path));
233 if (std::strcmp(rootNode->Value(), c_RootNodeName) != 0)
235 GMX_THROW(TestException("Invalid root node type in " + path));
238 ReferenceDataEntry::EntryPointer rootEntry(ReferenceDataEntry::createRoot());
239 readEntry(rootNode, rootEntry.get());
244 /********************************************************************
251 //! \name Helper functions for XML writing
254 void createElementAndContents(XMLElementPtr parentElement, const ReferenceDataEntry& entry);
256 void setIdAttribute(XMLElementPtr element, const std::string& id)
260 element->SetAttribute(c_IdAttrName, id.c_str()); // If this fails, it throws std::bad_alloc
264 XMLElementPtr createElement(XMLElementPtr parentElement, const ReferenceDataEntry& entry)
266 XMLElementPtr element = parentElement->GetDocument()->NewElement(entry.type().c_str());
267 parentElement->InsertEndChild(element);
268 setIdAttribute(element, entry.id()); // If this fails, it throws std::bad_alloc
272 void createChildElements(XMLElementPtr parentElement, const ReferenceDataEntry& entry)
274 const ReferenceDataEntry::ChildList& children(entry.children());
275 ReferenceDataEntry::ChildIterator child;
276 for (child = children.begin(); child != children.end(); ++child)
278 createElementAndContents(parentElement, **child);
282 /*! \brief Handle \c input intended to be written as CDATA
284 * This method searches for any ']]>' sequences embedded in \c input,
285 * because this must always end a CDATA field. If any are found, it
286 * breaks the string so that instead multiple CDATA fields will be
287 * written with that token sequence split across the fields. Note that
288 * tinyxml2 does not handle such things itself.
290 * This is an edge case that is unimportant for GROMACS refdata, but
291 * it is preferable to know that the infrastructure won't break.
293 std::vector<std::string> breakUpAnyCdataEndTags(const std::string& input)
295 std::vector<std::string> strings;
296 std::size_t startPos = 0;
301 endPos = input.find("]]>", startPos);
302 if (endPos != std::string::npos)
304 // We found an embedded CDATA end tag, so arrange to split it into multiple CDATA blocks
307 strings.push_back(input.substr(startPos, endPos));
309 } while (endPos != std::string::npos);
314 void createElementContents(XMLElementPtr element, const ReferenceDataEntry& entry)
316 // TODO: Figure out if \r and \r\n can be handled without them
317 // changing to \n in the roundtrip.
318 if (entry.isCompound())
320 createChildElements(element, entry);
322 else if (entry.isTextBlock())
324 // An extra newline is written in the beginning to make lines align
325 // in the output xml (otherwise, the first line would be off by the length
326 // of the starting CDATA tag).
327 const std::string adjustedValue = "\n" + entry.value();
328 std::vector<std::string> cdataStrings = breakUpAnyCdataEndTags(adjustedValue);
329 for (auto const& s : cdataStrings)
331 XMLTextPtr textNode = element->GetDocument()->NewText(s.c_str());
332 textNode->SetCData(true);
333 element->InsertEndChild(textNode);
338 XMLTextPtr textNode = element->GetDocument()->NewText(entry.value().c_str());
339 element->InsertEndChild(textNode);
343 void createElementAndContents(XMLElementPtr parentElement, const ReferenceDataEntry& entry)
345 XMLElementPtr element = createElement(parentElement, entry);
346 createElementContents(element, entry);
349 XMLElementPtr createRootElement(XMLDocumentPtr document)
351 XMLElementPtr rootElement = document->NewElement(c_RootNodeName);
352 document->InsertEndChild(rootElement);
361 void writeReferenceDataFile(const std::string& path, const ReferenceDataEntry& rootEntry)
363 // TODO: Error checking
364 tinyxml2::XMLDocument document;
366 tinyxml2::XMLDeclaration* declaration = document.NewDeclaration(c_VersionDeclarationString);
367 document.InsertEndChild(declaration);
369 declaration = document.NewDeclaration(c_StyleSheetDeclarationString);
370 document.InsertEndChild(declaration);
372 XMLElementPtr rootElement = createRootElement(&document);
373 createChildElements(rootElement, rootEntry);
375 if (document.SaveFile(path.c_str()) != tinyxml2::XML_NO_ERROR)
377 GMX_THROW(TestException("Reference data saving failed in " + path));