Changeset 30f2815 for src/Parser

Timestamp:

Apr 17, 2013, 6:55:54 PM (12 years ago)

Author:

Frederik Heber <heber@…>

Branches:

Action_Thermostats, Add_AtomRandomPerturbation, Add_FitFragmentPartialChargesAction, Add_RotateAroundBondAction, Add_SelectAtomByNameAction, Added_ParseSaveFragmentResults, AddingActions_SaveParseParticleParameters, Adding_Graph_to_ChangeBondActions, Adding_MD_integration_tests, Adding_ParticleName_to_Atom, Adding_StructOpt_integration_tests, AtomFragments, Automaking_mpqc_open, AutomationFragmentation_failures, Candidate_v1.5.4, Candidate_v1.6.0, Candidate_v1.6.1, ChangeBugEmailaddress, ChangingTestPorts, ChemicalSpaceEvaluator, CombiningParticlePotentialParsing, Combining_Subpackages, Debian_Package_split, Debian_package_split_molecuildergui_only, Disabling_MemDebug, Docu_Python_wait, EmpiricalPotential_contain_HomologyGraph, EmpiricalPotential_contain_HomologyGraph_documentation, Enable_parallel_make_install, Enhance_userguide, Enhanced_StructuralOptimization, Enhanced_StructuralOptimization_continued, Example_ManyWaysToTranslateAtom, Exclude_Hydrogens_annealWithBondGraph, FitPartialCharges_GlobalError, Fix_BoundInBox_CenterInBox_MoleculeActions, Fix_ChargeSampling_PBC, Fix_ChronosMutex, Fix_FitPartialCharges, Fix_FitPotential_needs_atomicnumbers, Fix_ForceAnnealing, Fix_IndependentFragmentGrids, Fix_ParseParticles, Fix_ParseParticles_split_forward_backward_Actions, Fix_PopActions, Fix_QtFragmentList_sorted_selection, Fix_Restrictedkeyset_FragmentMolecule, Fix_StatusMsg, Fix_StepWorldTime_single_argument, Fix_Verbose_Codepatterns, Fix_fitting_potentials, Fixes, ForceAnnealing_goodresults, ForceAnnealing_oldresults, ForceAnnealing_tocheck, ForceAnnealing_with_BondGraph, ForceAnnealing_with_BondGraph_continued, ForceAnnealing_with_BondGraph_continued_betteresults, ForceAnnealing_with_BondGraph_contraction-expansion, FragmentAction_writes_AtomFragments, FragmentMolecule_checks_bonddegrees, GeometryObjects, Gui_Fixes, Gui_displays_atomic_force_velocity, ImplicitCharges, IndependentFragmentGrids, IndependentFragmentGrids_IndividualZeroInstances, IndependentFragmentGrids_IntegrationTest, IndependentFragmentGrids_Sole_NN_Calculation, JobMarket_RobustOnKillsSegFaults, JobMarket_StableWorkerPool, JobMarket_unresolvable_hostname_fix, MoreRobust_FragmentAutomation, ODR_violation_mpqc_open, PartialCharges_OrthogonalSummation, PdbParser_setsAtomName, PythonUI_with_named_parameters, QtGui_reactivate_TimeChanged_changes, Recreated_GuiChecks, Rewrite_FitPartialCharges, RotateToPrincipalAxisSystem_UndoRedo, SaturateAtoms_findBestMatching, SaturateAtoms_singleDegree, StoppableMakroAction, Subpackage_CodePatterns, Subpackage_JobMarket, Subpackage_LinearAlgebra, Subpackage_levmar, Subpackage_mpqc_open, Subpackage_vmg, Switchable_LogView, ThirdParty_MPQC_rebuilt_buildsystem, TrajectoryDependenant_MaxOrder, TremoloParser_IncreasedPrecision, TremoloParser_MultipleTimesteps, TremoloParser_setsAtomName, Ubuntu_1604_changes, stable

Children:

69f38a

Parents:

a676f9

git-author:

Frederik Heber <heber@…> (03/14/13 08:38:23)

git-committer:

Frederik Heber <heber@…> (04/17/13 18:55:54)

Message:

MpqcParser now also understands "_n_ atoms geometry" lines.

• optimization throws out an additional id per atom which caused havoc when copy&pasted and parsed so far. Right now, we discard the id, assuming they are simply ascending, throwing exception if something else comes along.
• also added regression test on this.

File:

• src/Parser/MpqcParser.cpp (modified) (6 diffs)

src/Parser/MpqcParser.cpp

@@ -54 +54 @@
 #include "molecule.hpp"
 #include "MoleculeListClass.hpp"
+#include "Parser/Exceptions.hpp"
 #include "World.hpp"
 
@@ -85 +86 @@
   bool MoleculeSection = false;
   bool GeometrySection = false;
+  bool GeometrySection_n = false;
   bool BasisSection = false;
   bool AuxBasisSection = false;
@@ -94 +96 @@
   boost::char_separator<char> whitesep(" \t");
   ConvertTo<double> toDouble;
+  int old_n = -1; // note down the last parsed "n" to ascertain it's ascending
 
   molecule *newmol = World::getInstance().createMolecule();
@@ -102 +105 @@
     file->getline(line, MAXSTRINGSIZE-1);
     std::string linestring(line);
-    if ((linestring.find("atoms geometry") == string::npos) && (linestring.find("}") != string::npos)) {
+    if (((linestring.find("atoms") == string::npos)
+        || (linestring.find("geometry") == string::npos))
+        && (linestring.find("}") != string::npos)) {
       GeometrySection = false;
     }
@@ -113 +118 @@
     if (MoleculeSection) {
       if (GeometrySection) { // we have an atom
+//        LOG(2, "DEBUG: Full line is '" << linestring << "'.");
+        // separate off [..] part
         tokenizer tokens(linestring, sep);
-  //      if (tokens.size() != 2)
-  //        throw MpqcParseException;
-        tokenizer::iterator tok_iter = tokens.begin();
-        ASSERT(tok_iter != tokens.end(),
-            "FormatParser< mpqc >::load() - missing token for MoleculeSection in line "+linestring+"!");
-        std::stringstream whitespacefilter(*tok_iter++);
+        // split part prior to [..] into tokens
+        std::string prior_part(*tokens.begin());
+        tokenizer prefixtokens(prior_part, whitesep);
+        tokenizer::iterator tok_iter = prefixtokens.begin();
+//        LOG(2, "DEBUG: Current tok_iter is " << *tok_iter << ".");
+        if (GeometrySection_n) {
+          ASSERT(tok_iter != prefixtokens.end(),
+              "FormatParser< mpqc >::load() - missing n entry for MoleculeSection in line "
+              +linestring+"!");
+          // if additional n is given, parse and check but discard eventually
+          int n;
+          std::stringstream whitespacefilter(*tok_iter++);
+          whitespacefilter >> ws >> n;
+          if ((old_n != -1) && ((n-1) != old_n))
+            ELOG(2, "n index is not simply ascending by one but "
+                << n-old_n << ", specific ids are lost!");
+          if (old_n >= n) {
+            ELOG(1, "n index is not simply ascending, coordinates might get mixed!");
+            throw ParserException();
+          }
+          old_n = n;
+        }
+        ASSERT(tok_iter != prefixtokens.end(),
+            "FormatParser< mpqc >::load() - missing atoms entry for MoleculeSection in line "
+            +linestring+"!");
+//        LOG(2, "DEBUG: Current tok_iter is " << *tok_iter << ".");
         std::string element;
-        whitespacefilter >> ws >> element;
-        ASSERT(tok_iter != tokens.end(),
-            "FormatParser< mpqc >::load() - missing token for MoleculeSection in line "+linestring+"!");
-        std::string vector = *tok_iter;
+        {
+          std::stringstream whitespacefilter(*tok_iter++);
+          whitespacefilter >> ws >> element;
+        }
+        // split [..] part and parse
+        tok_iter = (++tokens.begin());
+        ASSERT (tok_iter != tokens.end(),
+            "FormatParser< mpqc >::load() - missing geometry entry for MoleculeSection in line "
+            +linestring+"!");
+//        LOG(2, "DEBUG: Current tok_iter is " << *tok_iter << ".");
+        std::string vector(*tok_iter);
         tokenizer vectorcomponents(vector, whitesep);
         Vector X;
-  //      if (vectorcomponents.size() != NDIM)
-  //        throw MpqcParseException;
+//        if (vectorcomponents.size() != NDIM)
+//          throw ParserException();
         tok_iter = vectorcomponents.begin();
         for (int i=0; i<NDIM; ++i) {
+//          LOG(2, "DEBUG: Current tok_iter is " << *tok_iter << ".");
           X[i] = toDouble(*tok_iter++);
         }
@@ -220 +255 @@
       MoleculeSection = true;
     }
-    if (linestring.find("atoms geometry") != string::npos) {
+    if ((linestring.find("atoms") != string::npos)
+        && (linestring.find("geometry") != string::npos)) {
       GeometrySection = true;
+      if (linestring.find("n") != string::npos) // neither atoms nor geometry contains a letter n
+        GeometrySection_n = true;
     }
     if ((linestring.find("basis<GaussianBasisSet>:") != string::npos) && ((linestring.find("abasis<") == string::npos))) {