Changeset 5fa2ba for src

Timestamp:

Oct 6, 2011, 3:06:17 PM (13 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:

e638f9

Parents:

029bb4

git-author:

Frederik Heber <heber@…> (08/29/11 09:53:53)

git-committer:

Frederik Heber <heber@…> (10/06/11 15:06:17)

Message:

Enhanced PdbParser to read ill-formed pdbs.

• conect entries may now contain 0 as filler (and serial 0 presence is checked).
• ATOM info lines may contain less than 80 chars, then name is parsed for element.
• added new regression test Parser/Pdb/load-various for this.

File:

• src/Parser/PdbParser.cpp (modified) (2 diffs)

src/Parser/PdbParser.cpp

@@ -475 +475 @@
 }
 
+/** read a line starting with key ATOM.
+ *
+ * We check for line's length and parse only up to this value.
+ *
+ * @param atomInfo container to put information in
+ * @param line line containing key ATOM
+ */
 void PdbParser::readPdbAtomInfoContainer(PdbAtomInfoContainer &atomInfo, std::string &line) const
 {
-  LOG(4,"INFO: Parsing token from "+line.substr(0,6)+".");
-  atomInfo.set(PdbKey::token, line.substr(0,6));
-  LOG(4,"INFO: Parsing serial from "+line.substr(6,5)+".");
-  atomInfo.set(PdbKey::serial, line.substr(6,5));
-
-  LOG(4,"INFO: Parsing name from "+line.substr(12,4)+".");
-  atomInfo.set(PdbKey::name, line.substr(12,4));
-  LOG(4,"INFO: Parsing altLoc from "+line.substr(16,1)+".");
-  atomInfo.set(PdbKey::altLoc, line.substr(16,1));
-  LOG(4,"INFO: Parsing resName from "+line.substr(17,3)+".");
-  atomInfo.set(PdbKey::resName, line.substr(17,3));
-  LOG(4,"INFO: Parsing chainID from "+line.substr(21,1)+".");
-  atomInfo.set(PdbKey::chainID, line.substr(21,1));
-  LOG(4,"INFO: Parsing resSeq from "+line.substr(22,4)+".");
-  atomInfo.set(PdbKey::resSeq, line.substr(22,4));
-  LOG(4,"INFO: Parsing iCode from "+line.substr(26,1)+".");
-  atomInfo.set(PdbKey::iCode, line.substr(26,1));
-
-  LOG(4,"INFO: Parsing occupancy from "+line.substr(54,6)+".");
-  atomInfo.set(PdbKey::occupancy, line.substr(54,6));
-  LOG(4,"INFO: Parsing tempFactor from "+line.substr(60,6)+".");
-  atomInfo.set(PdbKey::tempFactor, line.substr(60,6));
-  LOG(4,"INFO: Parsing charge from "+line.substr(78,2)+".");
-  atomInfo.set(PdbKey::charge, line.substr(78,2));
-  LOG(4,"INFO: Parsing element from "+line.substr(76,2)+".");
-  atomInfo.set(PdbKey::element, line.substr(76,2));
+  const size_t length = line.length();
+  if (length < 80)
+    ELOG(2, "PdbParser::readPdbAtomInfoContainer() - pdb is mal-formed, containing less than 80 chars!");
+  if (length >= 6) {
+    LOG(4,"INFO: Parsing token from "+line.substr(0,6)+".");
+    atomInfo.set(PdbKey::token, line.substr(0,6));
+  }
+  if (length >= 11) {
+    LOG(4,"INFO: Parsing serial from "+line.substr(6,5)+".");
+    atomInfo.set(PdbKey::serial, line.substr(6,5));
+    ASSERT(atomInfo.get<int>(PdbKey::serial) != 0,
+        "PdbParser::readPdbAtomInfoContainer() - serial 0 is invalid (filler id for conect entries).");
+  }
+
+  if (length >= 16) {
+    LOG(4,"INFO: Parsing name from "+line.substr(12,4)+".");
+    atomInfo.set(PdbKey::name, line.substr(12,4));
+  }
+  if (length >= 17) {
+    LOG(4,"INFO: Parsing altLoc from "+line.substr(16,1)+".");
+    atomInfo.set(PdbKey::altLoc, line.substr(16,1));
+  }
+  if (length >= 20) {
+    LOG(4,"INFO: Parsing resName from "+line.substr(17,3)+".");
+    atomInfo.set(PdbKey::resName, line.substr(17,3));
+  }
+  if (length >= 22) {
+    LOG(4,"INFO: Parsing chainID from "+line.substr(21,1)+".");
+    atomInfo.set(PdbKey::chainID, line.substr(21,1));
+  }
+  if (length >= 26) {
+    LOG(4,"INFO: Parsing resSeq from "+line.substr(22,4)+".");
+    atomInfo.set(PdbKey::resSeq, line.substr(22,4));
+  }
+  if (length >= 27) {
+    LOG(4,"INFO: Parsing iCode from "+line.substr(26,1)+".");
+    atomInfo.set(PdbKey::iCode, line.substr(26,1));
+  }
+
+  if (length >= 60) {
+    LOG(4,"INFO: Parsing occupancy from "+line.substr(54,6)+".");
+    atomInfo.set(PdbKey::occupancy, line.substr(54,6));
+  }
+  if (length >= 66) {
+    LOG(4,"INFO: Parsing tempFactor from "+line.substr(60,6)+".");
+    atomInfo.set(PdbKey::tempFactor, line.substr(60,6));
+  }
+  if (length >= 80) {
+    LOG(4,"INFO: Parsing charge from "+line.substr(78,2)+".");
+    atomInfo.set(PdbKey::charge, line.substr(78,2));
+  }
+  if (length >= 78) {
+    LOG(4,"INFO: Parsing element from "+line.substr(76,2)+".");
+    atomInfo.set(PdbKey::element, line.substr(76,2));
+  } else {
+    LOG(4,"INFO: Trying to parse alternative element from name "+line.substr(12,4)+".");
+    atomInfo.set(PdbKey::element, line.substr(12,4));
+  }
 }
 
@@ -708 +747 @@
       int otherid = -1;
       PdbAtomInfoContainer::ScanKey(otherid, line.substr(index,5));
-      if (otherid >= 0)
-        ListOfNeighbors.push_back((size_t)otherid);
+      if (otherid > 0)
+        ListOfNeighbors.push_back(otherid);
+      else
+        ELOG(2, "PdbParser::readNeighbors() - discarding conect entry with id 0.");
     } else  {
       break;