diff --git a/common/python/nomadcore/md_data_access/MDDataAccess.py b/common/python/nomadcore/md_data_access/MDDataAccess.py
index 905aab1ece8aa4fe2d3d25971d49e001ed9ce132..305ff09521f6dd9fb58a0c3b67f80d675f396616 100644
--- a/common/python/nomadcore/md_data_access/MDDataAccess.py
+++ b/common/python/nomadcore/md_data_access/MDDataAccess.py
@@ -66,7 +66,7 @@ ELEMENTS_MASS_TABLE = {
"Zn" : 65.37000, "Zr" : 91.224
}
-def get_element_name(atomname):
+def get_any_element_name(atomname):
elementlist = ELEMENTS_MASS_TABLE.keys()
# check if the element is in list
# but name is upper- or lower-case
@@ -91,6 +91,31 @@ def get_element_name(atomname):
pass
return None
+def get_element_name(atomname):
+ elementlist = ELEMENTS_MASS_TABLE.keys()
+ # check if the element is in list
+ # but name is upper- or lower-case
+ for name in elementlist:
+ if atomname == name:
+ return name
+ # check if the first two letters define
+ # element name
+ if len(atomname)>1:
+ for name in elementlist:
+ if atomname[0:2] == name:
+ return name
+ if len(atomname)>0:
+ # check if the first letter defines
+ # element name
+ for name in elementlist:
+ if atomname[0:1] == name:
+ return name
+ if len(atomname)<3:
+ return atomname[0:1]
+ else:
+ return get_any_element_name()
+ return None
+
def get_dir_base_extension(file_name):
""" Splits directory, file base and file extensions
@@ -103,75 +128,58 @@ def get_dir_base_extension(file_name):
return file_dir, file_base, file_extension
def pymConvertTopoDict(topoStor, topoPYM):
- if(isinstance(topoPYM, pym.OpenMolfile) or
- isinstance(topoPYM, pym.OpenMolfile.topology)):
- topo = topoPYM
-
- def getseg(seg):
- regex = re.compile(r"^seg_[0-9]+_b")
- if regex.findall(seg.segid):
- segname = bytes(re.sub(r"^seg_[0-9]+_b","",seg.segid).replace("'",""), "utf-8").decode("utf-8")
- else:
- segname = seg.segid
- return [seg.ix,segname]
-
- def getres(res):
- regex = re.compile(r"^b'")
- if isinstance(res.resname, bytes):
- resname = res.resname.decode("utf-8")
- else:
- resname= res.resname
- if regex.findall(resname):
- resname = bytes(re.sub(r"^b","",resname).replace("'",""), "utf-8").decode("utf-8")
- return [res.ix,resname]
-
- def get_atomseg(atom):
- return [atom.segment.ix,atom.segment.segname.decode('utf-8')]
-
- def get_atomres(atom):
- return [atom.resname.decode('utf-8'),atom.resid]
-
- def getatom(atom):
- atmid = atom.ix
- atmname = atom.name.decode('utf-8')
- atmtyp = atom.type.decode('utf-8')
- atmres = atom.resname.decode('utf-8')
- atmresid = atom.resid
- atmsegid = atom.segid
- atm_unique = atmname + "-" + atmtyp
- return [atmid,atm_unique,atmname,atmtyp,atmres,atmresid,atmsegid]
+ """ Function to convert Pymolfile topology info
+ to MDDataAccess
+
+ Pymolfile stores structure data in numpy with following fields
+ (name, type, resname, resid, segid, chain, altloc, insertion,
+ occupancy, bfactor, mass, charge, radius, atomicnumber)
+ Ex.: ['N' 'NH3' 'ASP' '48' 'PRO1' 'P' ' ' ''
+ '0.0' '0.0' '14.007' '-0.3' '0.0' '0']
+ """
+ topo=None
+ if isinstance(topoPYM, pym.OpenMolfile):
+ topo = topoPYM.topology
def getatomall(atom):
- atmid = atom.ix
- atmname = atom.name.decode('utf-8')
- atmtyp = atom.type.decode('utf-8')
- if hasattr(atom, "mass"):
- atmmass = float(atom.mass)
+ atmid=0
+ atmname = atom[0]
+ atmtyp = atom[1]
+ if atom[10]:
+ atmmass = float(atom[10])
else:
atmmass = None
- if hasattr(atom, "resid"):
- atmresid = atom.resid
- atmres = atom.resname.decode('utf-8')
+ if atom[3]:
+ atmresid = atom[3]
+ atmres = atom[2]
else:
atmresid = None
atmres = None
- if hasattr(atom, "segid"):
- atmsegid = atom.segid
+ if atom[4]:
+ atmsegid = atom[4]
else:
atmsegid = None
- if hasattr(atom, "charge"):
- atmchrg = float(atom.charge)
+ if atom[11]:
+ atmchrg = float(atom[11])
else:
atmchrg = None
- if hasattr(atom, "radius"):
- atmrad = float(atom.radius)
+ if atom[12]:
+ atmrad = float(atom[12])
else:
atmrad = None
- if hasattr(atom, "bfactor"):
- atmbfac = float(atom.bfactor)
+ if atom[9]:
+ atmbfac = float(atom[9])
else:
atmbfac = None
- atm_unique = atmname + "-" + atmtyp
+ atm_unique = ''
+ if atmname:
+ atm_unique = atm_unique + atmname
+ if atmtyp:
+ atm_unique = atm_unique + "-" + atmtyp
+ #if atmres:
+ # atm_unique = atm_unique + "-" + atmres
+ #if atmsegid:
+ # atm_unique = atm_unique + "-" + atmsegid
return [atmid,atm_unique,atmname,atmtyp,atmres,atmresid,atmsegid,atmmass,atmchrg,atmrad,atmbfac]
def checkatomsdiff(atom1,atom2,checklist):
@@ -192,63 +200,55 @@ def pymConvertTopoDict(topoStor, topoPYM):
return [getatom(atom1),getatom(atom2)]
def atompairids(atom1,atom2):
- return [getatom(atom1)[0],getatom(atom2)[0]]
-
- segmentList = [getseg(a)[1] for a in topo.segments]
- residueList = [getres(a)[1] for a in topo.residues]
- atomList = [getatomall(a) for a in topo.atoms]
- #atomAllList = [getatomall(a) for a in topo.atoms]
-
- types_list = list(set([a[1] for a in atomList]))
- atom_name_list = [a[2] for a in atomList]
+ return [atom1[0],atom2[0]]
+
+ #chainList = [a[5] if a[5] else '' for a in topo.structure]
+ #segmentList = [a[4] if a[4] else '' for a in topo.structure]
+ #residList = [a[3] if a[3] else None for a in topo.structure]
+ #residueList = [a[2] if a[2] else '' for a in topo.structure]
+ chainList = [a[5] for a in topo.structure]
+ segmentList = [a[4] for a in topo.structure]
+ residList = [a[3] for a in topo.structure]
+ residueList = [a[2] for a in topo.structure]
+ atomList = topo.structure
+ atomAllList = [getatomall(a) for a in topo.structure]
+ count=0
+ for i in range(len(atomAllList)):
+ atomAllList[i][0]=count
+ count+=1
+
+ types_list = list(set([a[1] for a in atomAllList]))
+ atom_name_list = [a[0] for a in topo.structure]
#atom_type_list = [a[3] for a in atomList]
atom_element_list = []
- for atom in atomList:
- try:
- guessed_element = mda.topology.guessers.guess_atom_element(atom[2])
- except (TypeError, ValueError, AttributeError):
- guessed_element = atom[2]
- if guessed_element in ELEMENTS_MASS_TABLE.keys():
- element = guessed_element
+ for atom in topo.structure:
+ if atom[1] in ELEMENTS_MASS_TABLE.keys():
+ element = atom[1]
else:
- element = get_element_name(atom[2])
- #if element is None:
- # element = get_element_name(atom[3])
+ element = get_element_name(atom[1])
if element is None:
- element = atom[2]
+ element = atom[1]
atom_element_list.append(element)
system_name = ''
if segmentList:
system_name = system_name + '-'.join(list(set(segmentList)))
- elif residueList:
+ if residueList:
system_name = system_name + '-'.join(list(set(residueList)))
- attrlist = dir(topo.atoms)
- atom_names = []
- atom_types = []
- atom_masses = []
- atom_radiuses = []
- atom_bfactors = []
- atom_charges = []
- if "names" in attrlist:
- atom_names = topo.atoms.names
- if "types" in attrlist:
- atom_types = topo.atoms.types
- if "masses" in attrlist:
- atom_masses = topo.atoms.masses
- if "charges" in attrlist:
- atom_charges = topo.atoms.charges
- if "radiuses" in attrlist:
- atom_radiuses = topo.atoms.radiuses
- if "bfactors" in attrlist:
- atom_bfactors = topo.atoms.bfactors
- #print("Atom Bonds:",MDdata.topohandler.atoms.bonds)
- #print("Atom Angles:",MDdata.topohandler.atoms.angles)
- #print("Atom Dihedrals:",MDdata.topohandler.atoms.dihedrals)
- #print("Atom Impropers:",MDdata.topohandler.atoms.impropers)
+ atom_all_list = np.asarray(atomAllList)
+ atom_names = atom_all_list[:,2]
+ atom_types = atom_all_list[:,3]
+ atom_masses = atom_all_list[:,7]
+ atom_charges = atom_all_list[:,8]
+ atom_radiuses = atom_all_list[:,9]
+ atom_bfactors = atom_all_list[:,10]
+ #print("Atom Bonds:",topo.bonds)
+ #print("Atom Angles:",topo.angles)
+ #print("Atom Dihedrals:",topo.dihedrals)
+ #print("Atom Impropers:",topo.impropers)
atom_type_dict = {}
@@ -265,20 +265,14 @@ def pymConvertTopoDict(topoStor, topoPYM):
elm = types_list[ielm]
atom_type_dict.update({elm : ielm+1})
typelabelList = []
- for atom in atomList:
+ for atom in atomAllList:
if elm == atom[1]:
- try:
- guessed_element = mda.topology.guessers.guess_atom_element(atom[2])
- except (TypeError, ValueError, AttributeError):
- guessed_element = atom[2]
- if guessed_element in ELEMENTS_MASS_TABLE.keys():
- element = guessed_element
+ if atom[2] in ELEMENTS_MASS_TABLE.keys():
+ element = atom[2]
else:
element = get_element_name(atom[2])
- #if element is None:
- # element = get_element_name(atom[3])
if element is None:
- element = atom[2]
+ element = atom[1]
elementDict.update({elm : element})
atomnameDict.update({elm : atom[2]})
atomtypesDict.update({elm : atom[3]})
@@ -289,7 +283,7 @@ def pymConvertTopoDict(topoStor, topoPYM):
typelabelList.append(atom[0])
atomlabelDict.append(typelabelList)
- for atom in atomList:
+ for atom in atomAllList:
atomlabelList.append([atom[0],atom_type_dict[atom[1]]])
massList = list(massDict.values())
@@ -300,30 +294,36 @@ def pymConvertTopoDict(topoStor, topoPYM):
chargesList = list(chargeDict.values())
bfactorList = list(bfactorDict.values())
- topd = topo.bonds.topDict
- topdk = topd.keys()
+ topbList = np.column_stack((topo.bonds["from"],topo.bonds["to"]))
+ topbNames = []
+ for pair in topbList:
+ topbNames.append(atomAllList[pair[0]-1][1] + '-' + atomAllList[pair[1]-1][1])
+
+ topb=list(set(topbNames))
interNum = 0
interDict = {}
interTypeDict = {}
- for key in topdk:
+ for tb in topb:
bondList = []
typeList = []
noninter = True
- topt = topd[key]
- for b in topt:
- reslist=atom_respairs(b.atoms[0],b.atoms[1])
- atmlist=atompairs(b.atoms[0],b.atoms[1])
- atmidlist=atompairids(b.atoms[0],b.atoms[1])
- bondList.append(atmidlist)
- interDict.update({interNum : bondList})
- if noninter:
- noninter = False
- typeList.extend(list([
- atom_type_dict[atmlist[0][1]],
- atom_type_dict[atmlist[1][1]]
- ]))
- interTypeDict.update({interNum : typeList})
+ bc = 0
+ for b in topbList:
+ topt=atomAllList[b[0]-1][1] + '-' + atomAllList[b[1]-1][1]
+ if topt == tb:
+ reslist=[atomAllList[b[0]-1][4],atomAllList[b[1]-1][4]]
+ atmlist=[atomAllList[b[0]-1],atomAllList[b[1]-1]]
+ atmidlist=[b[0]-1,b[1]-1]
+ bondList.append(atmidlist)
+ interDict.update({interNum : bondList})
+ if noninter:
+ noninter = False
+ typeList.extend(list([
+ atom_type_dict[atmlist[0][1]],
+ atom_type_dict[atmlist[1][1]]
+ ]))
+ interTypeDict.update({interNum : typeList})
interNum += 1
# for ielm in range(len(atom_type_list)-1):
@@ -960,6 +960,9 @@ class MDDataAccess(object):
self.natoms = None
self.topology = None # Main storage for topology data
self.trajectory = None # Main storage for trajectory data
+ self.inputcoords = None
+ self.outputcoords = None
+ self.trajtype = None
self.forcefield = None # Main storage for force field parameters
self.thermostats = None # Main storage for thermodynamical quantities
# and properties such as energies, temperatures
@@ -971,6 +974,8 @@ class MDDataAccess(object):
self.set_defaults()
self.init_topo()
self.init_traj()
+ self.init_incoord()
+ self.init_outcoord()
self.init_thermo()
def set_defaults(self):
@@ -995,6 +1000,26 @@ class MDDataAccess(object):
self.trajfile = None # File name of the trajectory file with path if needed
self.trajectory = None
+ def init_incoord(self):
+ self.incoord_natoms = None
+ self.incoordformat = None # Format type of trajectory file
+ self.incoordhandler = None # The object parsing the trajectory file
+ self.incoordplugin = None # The object parsing the trajectory file
+ self.incoorditer = None # The object parsing the trajectory file
+ self.incoordcode = None # To explicitly define the parsing library (pymolfile, mdtraj, ASE ...) for trajectory files
+ self.incoordfile = None # File name of the trajectory file with path if needed
+ self.inputpositions = None
+
+ def init_outcoord(self):
+ self.outcoord_natoms = None
+ self.outcoordformat = None # Format type of output file
+ self.outcoordhandler = None # The object parsing the output file
+ self.outcoordplugin = None # The plugin parsing the output file
+ self.outcoorditer = None # The iteration at the output file
+ self.outcoordcode = None # To explicitly define the parsing library (pymolfile, mdtraj, ASE ...) for the files
+ self.outcoordfile = None # File name of the file with path if needed
+ self.outputpositions = None
+
def init_thermo(self):
self.thermofile = None # File name of the thermostat file with path if needed
self.thermoformat = None # Format type of topology file
@@ -1007,6 +1032,8 @@ class MDDataAccess(object):
self.set_defaults()
self.init_topo()
self.init_traj()
+ self.init_incoord()
+ self.init_outcoord()
self.init_thermo()
def set_topo(self, filename, fileformat=None):
@@ -1017,6 +1044,14 @@ class MDDataAccess(object):
self.trajfile = filename
self.trajformat = fileformat
+ def set_incoord(self, filename, fileformat=None):
+ self.incoordfile = filename
+ self.incoordformat = fileformat
+
+ def set_outcoord(self, filename, fileformat=None):
+ self.outcoordfile = filename
+ self.outcoordformat = fileformat
+
def set_thermo(self, filename, fileformat=None):
self.thermofile = filename
self.thermoformat = fileformat
@@ -1027,10 +1062,10 @@ class MDDataAccess(object):
if self.topohandler is None:
if self.topofile:
- self.check_topology_format_support()
+ self.check_topology_format_support("traj")
if self.trajhandler is None:
- self.check_trajectory_format_support()
+ self.check_trajectory_format_support("traj")
return self.trajhandler
@@ -1044,6 +1079,26 @@ class MDDataAccess(object):
return self.topohandler
+ def load_incoord(self):
+ """Loads the file handles for coordinates only
+ """
+
+ if self.incoordhandler is None:
+ if self.incoordfile:
+ self.check_trajectory_format_support("input")
+
+ return self.incoordhandler
+
+ def load_outcoord(self):
+ """Loads the file handles for coordinates only
+ """
+
+ if self.outcoordhandler is None:
+ if self.outcoordfile:
+ self.check_trajectory_format_support("output")
+
+ return self.outcoordhandler
+
def load_thermo(self):
"""Loads the file handles for topology only
"""
@@ -1195,35 +1250,53 @@ class MDDataAccess(object):
else:
return True
- def check_trajectory_format_support(self):
+ def check_trajectory_format_support(self, filetype):
"""Check if the given format is supported.
"""
- trajfilename = os.path.basename(self.trajfile)
- if self.trajformat is None:
- file_format = self.get_file_format(self.trajfile, self.trajformat)
- self.trajformat = file_format
+ if "input" in filetype:
+ chkfile = self.incoordfile
+ chkformat = self.incoordformat
+ self.trajtype = "input"
+ elif "output" in filetype:
+ chkfile = self.outcoordfile
+ chkformat = self.outcoordformat
+ self.trajtype = "output"
+ else:
+ chkfile = self.trajfile
+ chkformat = self.trajformat
+ self.trajtype = "traj"
+
+ numatoms=None
+ chkfilename = os.path.basename(chkfile)
+ if chkformat is None:
+ file_format = self.get_file_format(chkfile, chkformat)
+ chkformat = file_format
+ if "input" in filetype:
+ self.incoordformat = file_format
+ elif "output" in filetype:
+ self.outcoordformat = file_format
+ else:
+ self.trajformat = file_format
else:
- file_format = self.trajformat
+ file_format = chkformat
usedefault=True
- molfile_traj=None
# Use the given order to check topology
if self.interfaceorder:
for interface in self.interfaceorder:
if "pymolfile" in interface:
- filetrajformat = re.sub('[.]', '', self.trajformat)
+ filetrajformat = re.sub('[.]', '', chkformat)
trajhandler_check = None
if self.topohandler is not None:
- self.natoms = self.get_natoms_from_topo(topocode="pymolfile")
+ numatoms = self.get_natoms_from_topo(topocode="pymolfile")
if(isinstance(self.topohandler, pym.OpenMolfile)
or isinstance(self.topohandler, pym.OpenMolfile.topology)):
- molfile_traj = pym.OpenMolfile(self.trajfile, file_format=filetrajformat, topology=self.topohandler, silent=False)
- elif self.natoms is not None:
- if self.natoms > 0:
- molfile_traj = pym.OpenMolfile(self.trajfile, file_format=filetrajformat, natoms=self.natoms, silent=False)
- if molfile_traj is not None:
- if molfile_traj.trajectory is not None:
- trajhandler_check = molfile_traj
+ molfile_traj = pym.OpenMolfile(chkfile, file_format=filetrajformat, topology=self.topohandler, silent=False)
+ elif numatoms is not None:
+ if numatoms > 0:
+ molfile_traj = pym.OpenMolfile(chkfile, file_format=filetrajformat, natoms=numatoms, silent=False)
+ if molfile_traj.trajectory is not None:
+ trajhandler_check = molfile_traj
if trajhandler_check:
trajhandler = None
trajhandler = self.pymolfile_iread(trajhandler_check)
@@ -1231,17 +1304,41 @@ class MDDataAccess(object):
if self.interfacematch:
if interface in self.topocode:
usedefault=False
- self.trajhandler = trajhandler
- self.trajcode = "pymolfile"
- self.trajplugin = molfile_traj
+ if "input" in filetype:
+ self.incoordhandler = trajhandler
+ self.incoordcode = "pymolfile"
+ self.incoordplugin = molfile_traj
+ self.incoord_natoms = numatoms
+ elif "output" in filetype:
+ self.outcoordhandler = trajhandler
+ self.outcoordcode = "pymolfile"
+ self.outcoordplugin = molfile_traj
+ self.outcoord_natoms = numatoms
+ else:
+ self.trajhandler = trajhandler
+ self.trajcode = "pymolfile"
+ self.trajplugin = molfile_traj
+ self.natoms = numatoms
break
else:
trajhandler = None
else:
usedefault=False
- self.trajhandler = trajhandler
- self.trajcode = "pymolfile"
- self.trajplugin = molfile_traj
+ if "input" in filetype:
+ self.incoordhandler = trajhandler
+ self.incoordcode = "pymolfile"
+ self.incoordplugin = molfile_traj
+ self.incoord_natoms = numatoms
+ elif "output" in filetype:
+ self.outcoordhandler = trajhandler
+ self.outcoordcode = "pymolfile"
+ self.outcoordplugin = molfile_traj
+ self.outcoord_natoms = numatoms
+ else:
+ self.trajhandler = trajhandler
+ self.trajcode = "pymolfile"
+ self.trajplugin = molfile_traj
+ self.natoms = numatoms
break
if "mdtraj" in interface:
trajhandler_check = None
@@ -1257,43 +1354,97 @@ class MDDataAccess(object):
if self.interfacematch:
if interface in self.topocode:
usedefault=False
- self.trajhandler = trajhandler
- self.trajcode = "mdtraj"
+ if "input" in filetype:
+ self.incoordhandler = trajhandler
+ self.incoordcode = "mdtraj"
+ self.incoord_natoms = numatoms
+ elif "output" in filetype:
+ self.outcoordhandler = trajhandler
+ self.outcoordcode = "mdtraj"
+ self.outcoord_natoms = numatoms
+ else:
+ self.trajhandler = trajhandler
+ self.trajcode = "mdtraj"
+ self.natoms = numatoms
break
else:
trajhandler = None
else:
usedefault=False
- self.trajhandler = trajhandler
- self.trajcode = "mdtraj"
+ if "input" in filetype:
+ self.incoordhandler = trajhandler
+ self.incoordcode = "mdtraj"
+ self.incoord_natoms = numatoms
+ elif "output" in filetype:
+ self.outcoordhandler = trajhandler
+ self.outcoordcode = "mdtraj"
+ self.outcoord_natoms = numatoms
+ else:
+ self.trajhandler = trajhandler
+ self.trajcode = "mdtraj"
+ self.natoms = numatoms
break
if "mdanalysis" in interface:
mdanalysis_format = re.sub('[.]', '', file_format)
mdanalysis_format = mdanalysis_format.upper()
- print(mdanalysis_format)
if self.topohandler is not None:
# if the topology handler is a MDAnalysis universe,
# we may try replacing the trajectory data in it.
if isinstance(self.topohandler, mda_u.Universe):
try:
- self.topohandler.load_new(self.trajfile, format=mdanalysis_format)
- self.trajhandler = self.mdanalysis_iread(mdanalysis_handler=self.topohandler.trajectory)
- self.trajcode = "mdanalysis"
+ trajhandler = None
+ self.topohandler.load_new(chkfile, format=mdanalysis_format)
+ trajhandler = self.mdanalysis_iread(mdanalysis_handler=self.topohandler.trajectory)
+ if "input" in filetype:
+ self.incoordhandler = trajhandler
+ self.incoordcode = "mdanalysis"
+ self.incoord_natoms = numatoms
+ elif "output" in filetype:
+ self.outcoordhandler = trajhandler
+ self.outcoordcode = "mdanalysis"
+ self.outcoord_natoms = numatoms
+ else:
+ self.trajhandler = trajhandler
+ self.trajcode = "mdanalysis"
+ self.natoms = numatoms
usedefault=False
break
except (AttributeError, IOError, OSError, ValueError, TypeError):
try:
universe = mda_u.Universe(self.topohandler, self.trajfile, format=mdanalysis_format)
+ trajhandler = None
if isinstance(universe, mda_u.Universe):
self.topohandler = universe
- self.trajhandler = self.mdanalysis_iread(mdanalysis_handler=universe.trajectory)
- self.trajcode = "mdanalysis"
+ trajhandler = self.mdanalysis_iread(mdanalysis_handler=universe.trajectory)
+ if "input" in filetype:
+ self.incoordhandler = trajhandler
+ self.incoordcode = "mdanalysis"
+ self.incoord_natoms = numatoms
+ elif "output" in filetype:
+ self.outcoordhandler = trajhandler
+ self.outcoordcode = "mdanalysis"
+ self.outcoord_natoms = numatoms
+ else:
+ self.trajhandler = trajhandler
+ self.trajcode = "mdanalysis"
+ self.natoms = numatoms
usedefault=False
break
elif self.is_class_of_module(universe,
mda_c.Trajectory, mda_coordinates_modules):
- self.trajhandler = self.mdanalysis_iread(mdanalysis_handler=universe.trajectory)
- self.trajcode = "mdanalysis"
+ trajhandler = self.mdanalysis_iread(mdanalysis_handler=universe.trajectory)
+ if "input" in filetype:
+ self.incoordhandler = trajhandler
+ self.incoordcode = "mdanalysis"
+ self.incoord_natoms = numatoms
+ elif "output" in filetype:
+ self.outcoordhandler = trajhandler
+ self.outcoordcode = "mdanalysis"
+ self.outcoord_natoms = numatoms
+ else:
+ self.trajhandler = trajhandler
+ self.trajcode = "mdanalysis"
+ self.natoms = numatoms
usedefault=False
break
#except (AttributeError, IOError, OSError, ValueError, TypeError):
@@ -1312,31 +1463,79 @@ class MDDataAccess(object):
if self.interfacematch:
if interface in self.topocode:
self.topohandler = universe
- self.trajhandler = self.mdanalysis_iread(mdanalysis_handler=universe)
- self.trajcode = "mdanalysis"
+ trajhandler = None
+ trajhandler = self.mdanalysis_iread(mdanalysis_handler=universe)
+ if "input" in filetype:
+ self.incoordhandler = trajhandler
+ self.incoordcode = "mdanalysis"
+ self.incoord_natoms = numatoms
+ elif "output" in filetype:
+ self.outcoordhandler = trajhandler
+ self.outcoordcode = "mdanalysis"
+ self.outcoord_natoms = numatoms
+ else:
+ self.trajhandler = trajhandler
+ self.trajcode = "mdanalysis"
+ self.natoms = numatoms
usedefault=False
break
else:
universe = None
else:
self.topohandler = universe
- self.trajhandler = self.mdanalysis_iread(mdanalysis_handler=universe)
- self.trajcode = "mdanalysis"
+ trajhandler = None
+ trajhandler = self.mdanalysis_iread(mdanalysis_handler=universe)
+ if "input" in filetype:
+ self.incoordhandler = trajhandler
+ self.incoordcode = "mdanalysis"
+ self.incoord_natoms = numatoms
+ elif "output" in filetype:
+ self.outcoordhandler = trajhandler
+ self.outcoordcode = "mdanalysis"
+ self.outcoord_natoms = numatoms
+ else:
+ self.trajhandler = trajhandler
+ self.trajcode = "mdanalysis"
+ self.natoms = numatoms
usedefault=False
break
elif self.is_class_of_module(universe,
mda_c.Trajectory, mda_coordinates_modules):
if self.interfacematch:
if interface in self.topocode:
- self.trajhandler = self.mdanalysis_iread(mdanalysis_handler=universe)
- self.trajcode = "mdanalysis"
+ trajhandler = None
+ trajhandler = self.mdanalysis_iread(mdanalysis_handler=universe)
+ if "input" in filetype:
+ self.incoordhandler = trajhandler
+ self.incoordcode = "mdanalysis"
+ self.incoord_natoms = numatoms
+ elif "output" in filetype:
+ self.outcoordhandler = trajhandler
+ self.outcoordcode = "mdanalysis"
+ self.outcoord_natoms = numatoms
+ else:
+ self.trajhandler = trajhandler
+ self.trajcode = "mdanalysis"
+ self.natoms = numatoms
usedefault=False
break
else:
universe = None
else:
- self.trajhandler = self.mdanalysis_iread(mdanalysis_handler=universe)
- self.trajcode = "mdanalysis"
+ trajhandler = None
+ trajhandler = self.mdanalysis_iread(mdanalysis_handler=universe)
+ if "input" in filetype:
+ self.incoordhandler = trajhandler
+ self.incoordcode = "mdanalysis"
+ self.incoord_natoms = numatoms
+ elif "output" in filetype:
+ self.outcoordhandler = trajhandler
+ self.outcoordcode = "mdanalysis"
+ self.outcoord_natoms = numatoms
+ else:
+ self.trajhandler = trajhandler
+ self.trajcode = "mdanalysis"
+ self.natoms = numatoms
usedefault=False
break
except (AttributeError, IOError, OSError, ValueError, TypeError):
@@ -1352,15 +1551,35 @@ class MDDataAccess(object):
if self.interfacematch:
if interface in self.topocode:
usedefault=False
- self.trajhandler = trajhandler
- self.trajcode = "ase"
+ if "input" in filetype:
+ self.incoordhandler = trajhandler
+ self.incoordcode = "ase"
+ self.incoord_natoms = numatoms
+ elif "output" in filetype:
+ self.outcoordhandler = trajhandler
+ self.outcoordcode = "ase"
+ self.outcoord_natoms = numatoms
+ else:
+ self.trajhandler = trajhandler
+ self.trajcode = "ase"
+ self.natoms = numatoms
break
else:
trajhandler = None
else:
usedefault=False
- self.trajhandler = trajhandler
- self.trajcode = "ase"
+ if "input" in filetype:
+ self.incoordhandler = trajhandler
+ self.incoordcode = "ase"
+ self.incoord_natoms = numatoms
+ elif "output" in filetype:
+ self.outcoordhandler = trajhandler
+ self.outcoordcode = "ase"
+ self.outcoord_natoms = numatoms
+ else:
+ self.trajhandler = trajhandler
+ self.trajcode = "ase"
+ self.natoms = numatoms
break
else:
trajhandler = None
@@ -1369,43 +1588,70 @@ class MDDataAccess(object):
if self.interfacematch:
if interface in self.topocode:
usedefault=False
- self.trajhandler = trajhandler
- self.trajcode = "ase"
+ if "input" in filetype:
+ self.incoordhandler = trajhandler
+ self.incoordcode = "ase"
+ self.incoord_natoms = numatoms
+ elif "output" in filetype:
+ self.outcoordhandler = trajhandler
+ self.outcoordcode = "ase"
+ self.outcoord_natoms = numatoms
+ else:
+ self.trajhandler = trajhandler
+ self.trajcode = "ase"
+ self.natoms = numatoms
break
else:
trajhandler = None
else:
usedefault=False
- self.trajhandler = trajhandler
- self.trajcode = "ase"
+ if "input" in filetype:
+ self.incoordhandler = trajhandler
+ self.incoordcode = "ase"
+ self.incoord_natoms = numatoms
+ elif "output" in filetype:
+ self.outcoordhandler = trajhandler
+ self.outcoordcode = "ase"
+ self.outcoord_natoms = numatoms
+ else:
+ self.trajhandler = trajhandler
+ self.trajcode = "ase"
+ self.natoms = numatoms
break
- elif self.UserSuppliedInterface:
- if isinstance(self.UserSuppliedInterface, MDDataAccess.UserSuppliedInterface):
- if self.UserSuppliedInterface.name in interface:
- trajhandler = None
- trajhandler = self.UserSuppliedInterface.trajectory_support(self.trajfile, file_format=file_format)
- if trajhandler:
- if self.interfacematch:
- if interface in self.topocode:
+ elif hasattr(self, "UserSuppliedInterface"):
+ if self.UserSuppliedInterface is not None:
+ if isinstance(self.UserSuppliedInterface, MDDataAccess.UserSuppliedInterface):
+ if self.UserSuppliedInterface.name in interface:
+ trajhandler = None
+ trajhandler = self.UserSuppliedInterface.trajectory_support(self.trajfile, file_format=file_format)
+ if trajhandler:
+ if self.interfacematch:
+ if interface in self.topocode:
+ usedefault=False
+ self.trajhandler = trajhandler
+ self.trajcode = self.UserSuppliedInterface.name
+ break
+ else:
+ trajhandler = None
+ else:
usedefault=False
self.trajhandler = trajhandler
self.trajcode = self.UserSuppliedInterface.name
break
- else:
- trajhandler = None
- else:
- usedefault=False
- self.trajhandler = trajhandler
- self.trajcode = self.UserSuppliedInterface.name
- break
if usedefault:
- if self.trajhandler is None:
- filetrajformat = re.sub('[.]', '', self.trajformat)
+ if "input" in filetype:
+ trajhandler = self.incoordhandler
+ elif "output" in filetype:
+ trajhandler = self.outcoordhandler
+ else:
+ trajhandler = self.trajhandler
+ if trajhandler is None:
+ filetrajformat = re.sub('[.]', '', chkformat)
# First check whether pymolfile has support for the file type
trajhandler_check = None
if self.topohandler is not None:
- self.natoms = self.get_natoms_from_topo(topocode=self.topocode)
+ numatoms = self.get_natoms_from_topo(topocode=self.topocode)
try:
pymHasTopo = getattr(pym.OpenMolfile, "topology")
except AttributeError:
@@ -1418,52 +1664,104 @@ class MDDataAccess(object):
else:
topoIsPymTopo = False
if(isinstance(self.topohandler, pym.OpenMolfile) or topoIsPymTopo):
- molfile_traj = pym.OpenMolfile(self.trajfile, file_format=filetrajformat, topology=self.topohandler, silent=False)
- elif self.natoms is not None:
- if self.natoms > 0:
- molfile_traj = pym.OpenMolfile(self.trajfile, file_format=filetrajformat, natoms=self.natoms, silent=False)
- if molfile_traj is not None:
- if molfile_traj.trajectory is not None:
- trajhandler_check = molfile_traj
+ molfile_traj = pym.OpenMolfile(chkfile, file_format=filetrajformat, topology=self.topohandler, silent=False)
+ elif numatoms is not None:
+ if numatoms > 0:
+ molfile_traj = pym.OpenMolfile(chkfile, file_format=filetrajformat, natoms=numatoms, silent=False)
+ if molfile_traj.trajectory is not None:
+ trajhandler_check = molfile_traj
if trajhandler_check:
trajhandler = None
trajhandler = self.pymolfile_iread(trajhandler_check)
if trajhandler:
if self.interfacematch:
if "pymolfile" in self.topocode:
- self.trajhandler = trajhandler
- self.trajcode = "pymolfile"
- self.trajplugin = molfile_traj
+ if "input" in filetype:
+ self.incoordhandler = trajhandler
+ self.incoordcode = "pymolfile"
+ self.incoordplugin = molfile_traj
+ self.incoord_natoms = numatoms
+ elif "output" in filetype:
+ self.outcoordhandler = trajhandler
+ self.outcoordcode = "pymolfile"
+ self.outcoordplugin = molfile_traj
+ self.outcoord_natoms = numatoms
+ else:
+ self.trajhandler = trajhandler
+ self.trajcode = "pymolfile"
+ self.trajplugin = molfile_traj
+ self.natoms = numatoms
else:
trajhandler = None
else:
- self.trajhandler = trajhandler
- self.trajcode = "pymolfile"
- self.trajplugin = molfile_traj
+ if "input" in filetype:
+ self.incoordhandler = trajhandler
+ self.incoordcode = "pymolfile"
+ self.incoordplugin = molfile_traj
+ self.incoord_natoms = numatoms
+ elif "output" in filetype:
+ self.outcoordhandler = trajhandler
+ self.outcoordcode = "pymolfile"
+ self.outcoordplugin = molfile_traj
+ self.outcoord_natoms = numatoms
+ else:
+ self.trajhandler = trajhandler
+ self.trajcode = "pymolfile"
+ self.trajplugin = molfile_traj
+ self.natoms = numatoms
else:
- if self.natoms is not None:
- if self.natoms > 0:
- molfile_traj = pym.OpenMolfile(self.trajfile, file_format=filetrajformat, natoms=self.natoms, silent=False)
- if molfile_traj is not None:
- if molfile_traj.trajectory is not None:
- trajhandler_check = molfile_traj
+ if numatoms is not None:
+ if numatoms > 0:
+ molfile_traj = pym.OpenMolfile(chkfile, file_format=filetrajformat, natoms=numatoms, silent=False)
+ if molfile_traj.trajectory is not None:
+ trajhandler_check = molfile_traj
if trajhandler_check:
trajhandler = None
trajhandler = self.pymolfile_iread(trajhandler_check)
if trajhandler:
if self.interfacematch:
if interface in self.topocode:
- self.trajhandler = trajhandler
- self.trajcode = "pymolfile"
- self.trajplugin = molfile_traj
+ if "input" in filetype:
+ self.incoordhandler = trajhandler
+ self.incoordcode = "pymolfile"
+ self.incoordplugin = molfile_traj
+ self.incoord_natoms = numatoms
+ elif "output" in filetype:
+ self.outcoordhandler = trajhandler
+ self.outcoordcode = "pymolfile"
+ self.outcoordplugin = molfile_traj
+ self.outcoord_natoms = numatoms
+ else:
+ self.trajhandler = trajhandler
+ self.trajcode = "pymolfile"
+ self.trajplugin = molfile_traj
+ self.natoms = numatoms
else:
trajhandler = None
else:
- self.trajhandler = trajhandler
- self.trajcode = "pymolfile"
- self.trajplugin = molfile_traj
+ if "input" in filetype:
+ self.incoordhandler = trajhandler
+ self.incoordcode = "pymolfile"
+ self.incoordplugin = molfile_traj
+ self.incoord_natoms = numatoms
+ elif "output" in filetype:
+ self.outcoordhandler = trajhandler
+ self.outcoordcode = "pymolfile"
+ self.outcoordplugin = molfile_traj
+ self.outcoord_natoms = numatoms
+ else:
+ self.trajhandler = trajhandler
+ self.trajcode = "pymolfile"
+ self.trajplugin = molfile_traj
+ self.natoms = numatoms
- if self.trajhandler is None:
+ if "input" in filetype:
+ trajhandler = self.incoordhandler
+ elif "output" in filetype:
+ trajhandler = self.outcoordhandler
+ else:
+ trajhandler = self.trajhandler
+ if trajhandler is None:
# Second,check whether MDtraj has support for the file type
# trajhandler_check = mdt_FormatRegistry.loaders[file_format]
try:
@@ -1486,97 +1784,205 @@ class MDDataAccess(object):
trajhandler = None
if self.interfacematch:
if "mdtraj" in self.topocode:
- self.trajhandler = self.mdtraj_iread(mdtraj_handler=trajhandler_check)
- self.trajcode = "mdtraj"
+ trajhandler = self.mdtraj_iread(mdtraj_handler=trajhandler_check)
+ else:
+ trajhandler = self.mdtraj_iread(mdtraj_handler=trajhandler_check)
+ if "input" in filetype:
+ self.incoordhandler = trajhandler
+ self.incoordcode = "mdtraj"
+ self.incoord_natoms = numatoms
+ elif "output" in filetype:
+ self.outcoordhandler = trajhandler
+ self.outcoordcode = "mdtraj"
+ self.outcoord_natoms = numatoms
else:
- self.trajhandler = self.mdtraj_iread(mdtraj_handler=trajhandler_check)
+ self.trajhandler = trajhandler
self.trajcode = "mdtraj"
+ self.natoms = numatoms
# If MDTraj does not have support for the format
# or can not load the trajectory, use MDAnalysis or ASE.
- if self.trajhandler is None:
+ if "input" in filetype:
+ trajhandler = self.incoordhandler
+ elif "output" in filetype:
+ trajhandler = self.outcoordhandler
+ else:
+ trajhandler = self.trajhandler
+ if trajhandler is None:
mdanalysis_format = re.sub('[.]', '', file_format)
if self.topohandler is not None:
if isinstance(self.topohandler, mda_u.Universe):
try:
- self.topohandler.load_new(self.trajfile, format=mdanalysis_format)
- self.trajhandler = self.mdanalysis_iread(mdanalysis_handler=self.topohandler)
- self.trajcode = "mdanalysis"
+ self.topohandler.load_new(chkfile, format=mdanalysis_format)
+ trajhandler = self.mdanalysis_iread(mdanalysis_handler=self.topohandler)
+ if "input" in filetype:
+ self.incoordhandler = trajhandler
+ self.incoordcode = "mdanalysis"
+ self.incoord_natoms = numatoms
+ elif "output" in filetype:
+ self.outcoordhandler = trajhandler
+ self.outcoordcode = "mdanalysis"
+ self.outcoord_natoms = numatoms
+ else:
+ self.trajhandler = trajhandler
+ self.trajcode = "mdanalysis"
+ self.natoms = numatoms
except (AttributeError, IOError, OSError, ValueError, TypeError):
try:
universe = mda_u.Universe(self.topohandler, self.trajfile, format=mdanalysis_format)
if isinstance(universe, mda_u.Universe):
self.topohandler = universe
- self.trajhandler = self.mdanalysis_iread(mdanalysis_handler=universe)
- self.trajcode = "mdanalysis"
+ trajhandler = self.mdanalysis_iread(mdanalysis_handler=universe)
+ if "input" in filetype:
+ self.incoordhandler = trajhandler
+ self.incoordcode = "mdanalysis"
+ self.incoord_natoms = numatoms
+ elif "output" in filetype:
+ self.outcoordhandler = trajhandler
+ self.outcoordcode = "mdanalysis"
+ self.outcoord_natoms = numatoms
+ else:
+ self.trajhandler = trajhandler
+ self.trajcode = "mdanalysis"
+ self.natoms = numatoms
elif self.is_class_of_module(self.universe,
mda_c.Trajectory, mda_coordinates_modules):
- self.trajhandler = self.mdanalysis_iread(mdanalysis_handler=universe)
- self.trajcode = "mdanalysis"
+ trajhandler = self.mdanalysis_iread(mdanalysis_handler=universe)
+ if "input" in filetype:
+ self.incoordhandler = trajhandler
+ self.incoordcode = "mdanalysis"
+ self.incoord_natoms = numatoms
+ elif "output" in filetype:
+ self.outcoordhandler = trajhandler
+ self.outcoordcode = "mdanalysis"
+ self.outcoord_natoms = numatoms
+ else:
+ self.trajhandler = trajhandler
+ self.trajcode = "mdanalysis"
+ self.natoms = numatoms
except (AttributeError, IOError, OSError, ValueError, TypeError):
pass
try:
universe = mda_u.Universe(self.trajfile, format=mdanalysis_format)
if isinstance(universe, mda_u.Universe):
+ trajhandler = None
if self.interfacematch:
if "mdanalysis" in self.topocode:
self.topohandler = universe
- self.trajhandler = self.mdanalysis_iread(mdanalysis_handler=universe)
- self.trajcode = "mdanalysis"
+ trajhandler = self.mdanalysis_iread(mdanalysis_handler=universe)
+ if "input" in filetype:
+ self.incoordhandler = trajhandler
+ self.incoordcode = "mdanalysis"
+ self.incoord_natoms = numatoms
+ elif "output" in filetype:
+ self.outcoordhandler = trajhandler
+ self.outcoordcode = "mdanalysis"
+ self.outcoord_natoms = numatoms
+ else:
+ self.trajhandler = trajhandler
+ self.trajcode = "mdanalysis"
+ self.natoms = numatoms
else:
universe = None
else:
self.topohandler = universe
- self.trajhandler = self.mdanalysis_iread(mdanalysis_handler=universe)
- self.trajcode = "mdanalysis"
+ trajhandler = self.mdanalysis_iread(mdanalysis_handler=universe)
+ if "input" in filetype:
+ self.incoordhandler = trajhandler
+ self.incoordcode = "mdanalysis"
+ self.incoord_natoms = numatoms
+ elif "output" in filetype:
+ self.outcoordhandler = trajhandler
+ self.outcoordcode = "mdanalysis"
+ self.outcoord_natoms = numatoms
+ else:
+ self.trajhandler = trajhandler
+ self.trajcode = "mdanalysis"
+ self.natoms = numatoms
elif self.is_class_of_module(self.universe,
mda_c.Trajectory, mda_coordinates_modules):
+ trajhandler = None
+ trajcode = None
if self.interfacematch:
if "mdanalysis" in self.topocode:
- self.trajhandler = self.mdanalysis_iread(mdanalysis_handler=universe)
- self.trajcode = "mdanalysis"
+ trajhandler = self.mdanalysis_iread(mdanalysis_handler=universe)
+ trajcode = "mdanalysis"
else:
universe = None
else:
- self.trajhandler = self.mdanalysis_iread(mdanalysis_handler=universe)
- self.trajcode = "mdanalysis"
+ trajhandler = self.mdanalysis_iread(mdanalysis_handler=universe)
+ trajcode = "mdanalysis"
+ if "input" in filetype:
+ self.incoordhandler = trajhandler
+ self.incoordcode = trajcode
+ self.incoord_natoms = numatoms
+ elif "output" in filetype:
+ self.outcoordhandler = trajhandler
+ self.outcoordcode = trajcode
+ self.outcoord_natoms = numatoms
+ else:
+ self.trajhandler = trajhandler
+ self.trajcode = trajcode
+ self.natoms = numatoms
except (AttributeError, IOError, OSError, ValueError, TypeError):
pass
- if self.trajhandler is None:
+ if "input" in filetype:
+ trajhandler = self.incoordhandler
+ elif "output" in filetype:
+ trajhandler = self.outcoordhandler
+ else:
+ trajhandler = self.trajhandler
+ if trajhandler is None:
ase_support = None
ase_support = self.get_ase_format_support(file_format)
# May still have chance that ASE can recognize the
# format with its filetype checking function
if ase_support is None:
- ase_support = ase_io.formats.filetype(self.trajfile)
+ ase_support = ase_io.formats.filetype(chkfile)
trajhandler = None
- trajhandler = self.ase_iread(self.trajfile, fileformat=ase_support)
+ trajhandler = self.ase_iread(chkfile, fileformat=ase_support)
if trajhandler:
+ trajcode=None
if self.interfacematch:
if "ase" in self.topocode:
- self.trajhandler = trajhandler
- self.trajcode = "ase"
+ trajcode = "ase"
else:
trajhandler = None
else:
- self.trajhandler = trajhandler
- self.trajcode = "ase"
+ trajcode = "ase"
else:
trajhandler = None
- trajhandler = self.ase_iread(self.trajfile, fileformat=file_format)
+ trajhandler = self.ase_iread(chkfile, fileformat=file_format)
+ trajcode=None
if trajhandler:
if self.interfacematch:
if "ase" in self.topocode:
- self.trajhandler = trajhandler
- self.trajcode = "ase"
+ trajcode = "ase"
else:
trajhandler = None
else:
- self.trajhandler = trajhandler
- self.trajcode = "ase"
-
- if self.trajhandler is None:
+ trajcode = "ase"
+ if "input" in filetype:
+ self.incoordhandler = trajhandler
+ self.incoordcode = trajcode
+ self.incoord_natoms = numatoms
+ elif "output" in filetype:
+ self.outcoordhandler = trajhandler
+ self.outcoordcode = trajcode
+ self.outcoord_natoms = numatoms
+ else:
+ self.trajhandler = trajhandler
+ self.trajcode = trajcode
+ self.natoms = numatoms
+
+ if "input" in filetype:
+ trajhandler = self.incoordhandler
+ elif "output" in filetype:
+ trajhandler = self.outcoordhandler
+ else:
+ trajhandler = self.trajhandler
+ if trajhandler is None:
return False
else:
return True
@@ -1596,6 +2002,46 @@ class MDDataAccess(object):
finally:
del iterator_object
+ def incoord_iread(self):
+ """Returns an iterator that goes through the given file one
+ configuration at a time.
+ """
+ try:
+ iterator_object = iter(self.incoordhandler)
+ try:
+ while True:
+ try:
+ self.incoorditer = next(iterator_object)
+ return self.incoorditer
+ except ValueError:
+ pass
+ except StopIteration:
+ pass
+ finally:
+ del iterator_object
+ except TypeError:
+ pass
+
+ def outcoord_iread(self):
+ """Returns an iterator that goes through the given file one
+ configuration at a time.
+ """
+ try:
+ iterator_object = iter(self.outcoordhandler)
+ try:
+ while True:
+ try:
+ self.outcoorditer = next(iterator_object)
+ return self.outcoorditer
+ except ValueError:
+ pass
+ except StopIteration:
+ pass
+ finally:
+ del iterator_object
+ except TypeError:
+ pass
+
def topology_iread(self):
"""Returns an iterator that goes through the given trajectory file one
configuration at a time.
@@ -1795,7 +2241,7 @@ class MDDataAccess(object):
# configurations from it. Should be checked at some point.
handler = None
try:
- handler = ase_io.iread(file_name, index=":", format=file_format)
+ handler = ase_io.iread(filename, index=":", format=fileformat)
except (AttributeError, IOError, OSError,
ValueError, ImportError, ModuleNotFoundError):
return
@@ -1809,24 +2255,31 @@ class MDDataAccess(object):
def pymolfile_iread(self, traj_handler=None):
"""Returns the iterator for pymolfile trajectory
"""
+ if "input" in self.trajtype:
+ traj = self.inputcoords
+ elif "output" in self.trajtype:
+ traj = self.outputcoords
+ else:
+ traj = self.trajectory
+
if traj_handler.trajectory is not None:
while True:
positions = traj_handler.trajectory.iread()
if positions is not None:
- if self.trajectory is None:
- self.trajectory = MDDataTrajectory()
+ if traj is None:
+ traj = MDDataTrajectory()
if "has_velocities" in positions:
if positions["has_velocities"]>0:
- self.trajectory.velocities = positions["velocities"]
+ traj.velocities = positions["velocities"]
if("A" in positions and
"B" in positions and
"C" in positions):
- self.trajectory.unitcell_lengths = np.asarray(
+ traj.unitcell_lengths = np.asarray(
[positions["A"],positions["B"],positions["C"]])
if("alpha" in positions and
"beta" in positions and
"gamma" in positions):
- self.trajectory.unitcell_angles = np.asarray(
+ traj.unitcell_angles = np.asarray(
[positions["alpha"],positions["beta"],positions["gamma"]])
if("A" in positions and "B" in positions and
"C" in positions and "alpha" in positions and
@@ -1854,13 +2307,19 @@ class MDDataAccess(object):
lz = math.sqrt(cxz)
else:
lz = c if c>0 else 1.0
- self.trajectory.unitcell_vectors = np.zeros((3,3))
- self.trajectory.unitcell_vectors[0][0] = lx if lx != 0 else 1.0
- self.trajectory.unitcell_vectors[0][1] = xy
- self.trajectory.unitcell_vectors[0][2] = xz
- self.trajectory.unitcell_vectors[1][1] = ly if ly != 0 else 1.0
- self.trajectory.unitcell_vectors[1][2] = yz
- self.trajectory.unitcell_vectors[2][2] = lz
+ traj.unitcell_vectors = np.zeros((3,3))
+ traj.unitcell_vectors[0][0] = lx if lx != 0 else 1.0
+ traj.unitcell_vectors[0][1] = xy
+ traj.unitcell_vectors[0][2] = xz
+ traj.unitcell_vectors[1][1] = ly if ly != 0 else 1.0
+ traj.unitcell_vectors[1][2] = yz
+ traj.unitcell_vectors[2][2] = lz
+ if "input" in self.trajtype:
+ self.inputcoords = traj
+ elif "output" in self.trajtype:
+ self.outputcoords = traj
+ else:
+ self.trajectory = traj
yield positions["coords"]
else:
return None
@@ -1911,61 +2370,80 @@ class MDDataAccess(object):
# Must use the low level MDTraj API to open files without topology.
# mdtraj_supported_format = FormatRegistry.loaders[self.fileformat]
+ if "input" in self.trajtype:
+ traj = self.inputcoords
+ trajformat = self.incoordformat
+ trajfile = self.incoordfile
+ chunk = 1
+ elif "output" in self.trajtype:
+ traj = self.outputcoords
+ trajformat = self.outcoordformat
+ trajfile = self.outcoordfile
+ chunk = 1
+ else:
+ traj = self.trajectory
+ trajformat = self.trajformat
+ trajfile = self.trajfile
+ chunk = self.trajchunk
+
if mdtraj_handler is not None:
- if self.trajchunk == 0:
+ if chunk == 0:
try:
- loader = mdt_FormatRegistry.loaders[self.trajformat]
+ loader = mdt_FormatRegistry.loaders[trajformat]
except KeyError:
return
# If chunk was 0 then we want to avoid filetype-specific code
# in case of undefined behavior in various file parsers.
# TODO: this will first apply stride, then skip!
- if self.trajformat not in mdt_TOPOLOGY_EXTS:
+ if trajformat not in mdt_TOPOLOGY_EXTS:
topkwargs = kwargs.copy()
topkwargs['top'] = self.topohandler
# standard_names is a valid keyword argument only for files containing topologies
topkwargs.pop('standard_names', None)
- positions = loader(self.trajfile, **topkwargs)
+ positions = loader(trajfile, **topkwargs)
else:
- positions = loader(self.trajfile)
+ positions = loader(trajfile)
for pos in positions:
yield pos
- elif self.trajformat in ('.pdb', '.pdb.gz'):
+ elif trajformat in ('.pdb', '.pdb.gz'):
# the PDBTrajectoryFile class doesn't follow the standard API. Fixing it here
try:
- loader = mdt_FormatRegistry.loaders[self.trajformat]
+ loader = mdt_FormatRegistry.loaders[trajformat]
except KeyError:
return
t = loader(filename)
- for i in range(0, len(t), self.trajchunk):
- positions = t[i:i+self.trajchunk]
+ for i in range(0, len(t), chunk):
+ positions = t[i:i+chunk]
for pos in positions:
yield pos
else:
if self.topohandler is None:
n_atoms_set=None
- if self.trajformat in ('.crd', '.mdcrd'):
+ if trajformat in ('.crd', '.mdcrd'):
return
else:
- if "mdtraj" in self.topocode:
- n_atoms_set=self.topohandler.n_atoms
- elif "mdanalysis" in self.topocode:
- n_atoms_set=len(self.topohandler.atoms)
- elif "ase" in self.topocode:
- if isinstance(self.topohandler, ase.Atoms):
- n_atoms_set=len(self.topohandler.get_positions())
- else:
- n_atoms_set=None
+ #if "pymolfile" in self.topocode:
+ # n_atoms_set=self.topohandler.n_atoms
+ #elif "mdtraj" in self.topocode:
+ # n_atoms_set=self.topohandler.n_atoms
+ #elif "mdanalysis" in self.topocode:
+ # n_atoms_set=len(self.topohandler.atoms)
+ #elif "ase" in self.topocode:
+ # if isinstance(self.topohandler, ase.Atoms):
+ # n_atoms_set=len(self.topohandler.get_positions())
+ # else:
+ n_atoms_set = None
+ n_atoms_set = self.get_natoms_from_topo(self.topocode)
try:
with (lambda x: mdtraj_handler(x, n_atoms=n_atoms_set)
- if self.trajformat in ('.crd', '.mdcrd')
- else mdtraj_handler(self.trajfile, mode="r"))(self.trajfile) as f:
+ if trajformat in ('.crd', '.mdcrd')
+ else mdtraj_handler(trajfile, mode="r"))(trajfile) as f:
empty = False
while not empty:
- if self.trajformat not in mdt_TOPOLOGY_EXTS:
- data = f.read_as_traj(self.topohandler, n_frames=self.trajchunk)
+ if trajformat not in mdt_TOPOLOGY_EXTS:
+ data = f.read_as_traj(self.topohandler, n_frames=chunk)
else:
- data = f.read_as_traj(n_frames=self.trajchunk)
+ data = f.read_as_traj(n_frames=chunk)
if isinstance(data, tuple):
positions = data[0]
else:
@@ -2014,6 +2492,36 @@ class MDDataAccess(object):
if self.atompositions is not None:
return fileFormat
+ def incoordFileHandler(self, filename, fileformatlist=None, interfacelist=None):
+ self.init_incoord()
+ self.set_incoord(filename)
+ self.interfaceorder = interfacelist
+ incoord_loaded = self.load_incoord()
+ self.inputpositions = self.incoord_iread()
+ if self.inputpositions is None:
+ for fileformat in fileformatlist:
+ self.init_incoord()
+ self.set_incoord(filename, fileformat)
+ incoord_loaded = self.load_incoord()
+ self.inputpositions = self.incoord_iread()
+ if self.inputpositions is not None:
+ return fileFormat
+
+ def outcoordFileHandler(self, filename, fileformatlist=None, interfacelist=None):
+ self.init_outcoord()
+ self.set_outcoord(filename)
+ self.interfaceorder = interfacelist
+ outcoord_loaded = self.load_outcoord()
+ self.outputpositions = self.outcoord_iread()
+ if self.outputpositions is None:
+ for fileformat in fileformatlist:
+ self.init_outcoord()
+ self.set_outcoord(filename, fileformat)
+ outcoord_loaded = self.load_outcoord()
+ self.outputpositions = self.outcoord_iread()
+ if self.outputpositions is not None:
+ return fileFormat
+
def thermoFileHandler(self, filename, fileformatlist=None, interfacelist=None):
self.init_thermo()
self.set_thermo(filename)
@@ -2033,76 +2541,128 @@ class MDDataAccess(object):
def initializeFileHandlers(self, parser_ui):
# Files will be loaded using their extensions initially.
# If this fails, the fileFormat lists will be used in loading process.
- self.access_ui = parser_ui
topoformat = None
trajformat = None
- for fileItem in self.access_ui.fileDict:
+ self.atompositions = None
+ self.topohandler = None
+ self.thermohandler = None
+ self.forcefieldhandler = None
+ for fileItem in parser_ui.fileDict:
fileformatlist = None
interfacelist = None
- if (self.access_ui.fileDict[fileItem].fileSupplied and
- self.access_ui.fileDict[fileItem].activeInfo):
- filename = self.access_ui.fileDict[fileItem].fileName
- fileformatlist = self.access_ui.fileDict[fileItem].fileFormat
- interfacelist = self.access_ui.fileDict[fileItem].fileInterface
- # First, check topology file
- if 'topology' in self.access_ui.fileDict[fileItem].infoPurpose:
+ if (parser_ui.fileDict[fileItem].fileSupplied and
+ parser_ui.fileDict[fileItem].activeInfo):
+ filename = parser_ui.fileDict[fileItem].fileName
+ fileformatlist = parser_ui.fileDict[fileItem].fileFormat
+ interfacelist = parser_ui.fileDict[fileItem].fileInterface
+ if 'topology' in parser_ui.fileDict[fileItem].infoPurpose:
topoformat = self.topologyFileHandler(filename, fileformatlist, interfacelist)
- # Second, check trajectory file
- if 'trajectory' in self.access_ui.fileDict[fileItem].infoPurpose:
+ if 'inputcoordinates' in parser_ui.fileDict[fileItem].infoPurpose:
+ incoordformat = self.incoordFileHandler(filename, fileformatlist, interfacelist)
+ if 'outputcoordinates' in parser_ui.fileDict[fileItem].infoPurpose:
+ outcoordformat = self.outcoordFileHandler(filename, fileformatlist, interfacelist)
+ if 'trajectory' in parser_ui.fileDict[fileItem].infoPurpose:
trajformat = self.trajectoryFileHandler(filename, fileformatlist, interfacelist)
- # Third, check thermostat file
- if 'thermostats' in self.access_ui.fileDict[fileItem].infoPurpose:
+ if 'thermostats' in parser_ui.fileDict[fileItem].infoPurpose:
thermoformat = self.thermoFileHandler(filename, fileformatlist, interfacelist)
- # Last, check force filed file
- if 'forcefield' in self.access_ui.fileDict[fileItem].infoPurpose:
+ if 'forcefield' in parser_ui.fileDict[fileItem].infoPurpose:
forcefieldformat = self.forcefieldFileHandler(filename, fileformatlist, interfacelist)
- if self.atompositions is not None:
- self.set_TrajectoryData()
if self.topohandler is not None:
- self.set_TopologyData()
+ parser_ui.topology = self.set_TopologyData()
+ if self.inputpositions is not None:
+ parser_ui.inputcoords = self.set_InputData()
+ if self.outputpositions is not None:
+ parser_ui.outputcoords = self.set_OutputData()
+ if self.atompositions is not None:
+ parser_ui.trajectory = self.set_TrajectoryData()
if self.thermohandler is not None:
- self.set_ThermoData()
+ parser_ui.thermostats = self.set_ThermoData()
+ parser_ui.thermoDict = parser_ui.thermostats.thermoDict
if self.forcefieldhandler is not None:
- self.set_ForceFieldData()
+ #self.set_ForceFieldData()
+ pass
def set_TopologyData(self):
self.topology = MDDataTopology()
self.topology.filename = self.topofile
self.topology.topoDict = {}
- if ("pymolfile" in self.topocode and
- "pymolfile" in self.trajcode):
- self.topology = pymConvertTopoDict(self.topology, self.trajhandler.Topology)
if "pymolfile" in self.topocode:
self.topology = pymConvertTopoDict(self.topology, self.topohandler)
- if ("mdtraj" in self.topocode and
- "mdtraj" in self.trajcode):
- self.topology = mdtConvertTopoDict(self.topology, self.trajhandler.get_topology())
+ if(self.trajcode and not self.topology):
+ if ("pymolfile" in self.topocode and
+ "pymolfile" in self.trajcode):
+ self.topology = pymConvertTopoDict(self.topology, self.trajhandler.Topology)
if "mdtraj" in self.topocode:
self.topology = mdtConvertTopoDict(self.topology, self.topohandler)
+ if(self.trajcode and not self.topology):
+ if ("mdtraj" in self.topocode and
+ "mdtraj" in self.trajcode):
+ self.topology = mdtConvertTopoDict(self.topology, self.trajhandler.get_topology())
if "mdanalysis" in self.topocode:
self.topology = mdaConvertTopoDict(self.topology, self.topohandler)
- self.access_ui.topology = self.topology
+ return self.topology
def trajgen(self):
- if self.trajectory.frame_no == 0:
+ if self.trajectory.frame_no == -1:
self.trajectory.natoms = self.natoms
+ self.trajectory.frame_no += 1
return self.atompositions
else:
self.atompositions = self.iread()
self.trajectory.natoms = self.natoms
- if self.atompositions:
+ if self.atompositions is not None:
self.trajectory.frame_no += 1
return self.atompositions
+ def incoordgen(self):
+ if self.inputcoords.frame_no == -1:
+ self.inputcoords.natoms = self.incoord_natoms
+ return self.inputpositions
+ else:
+ self.inputpositions = self.incoord_iread()
+ self.inputcoords.natoms = self.incoord_natoms
+ if self.inputpositions is not None:
+ self.inputcoords.frame_no += 1
+ return self.inputpositions
+
+ def outcoordgen(self):
+ if self.outputcoords.frame_no == -1:
+ self.outputcoords.natoms = self.outcoord_natoms
+ return self.outputpositions
+ else:
+ self.outputpositions = self.outcoord_iread()
+ self.outputcoords.natoms = self.outcoord_natoms
+ if self.outputpositions is not None:
+ self.outputcoords.frame_no += 1
+ return self.outputpositions
+
def set_TrajectoryData(self):
if self.trajectory is None:
self.trajectory = MDDataTrajectory()
self.trajectory.filename = self.trajfile
self.trajectory.nsteps = self.set_nsteps()
- self.trajectory.frame_no = 0
+ self.trajectory.frame_no = -1
self.trajectory.trajDict = None
self.trajectory.positions = self.trajgen
- self.access_ui.trajectory = self.trajectory
+ return self.trajectory
+
+ def set_InputData(self):
+ if self.inputcoords is None:
+ self.inputcoords = MDDataTrajectory()
+ self.inputcoords.frame_no = -1
+ self.inputcoords.nsteps = 1
+ self.inputcoords.filename = self.incoordfile
+ self.inputcoords.positions = self.incoordgen
+ return self.inputcoords
+
+ def set_OutputData(self):
+ if self.outputcoords is None:
+ self.outputcoords = MDDataTrajectory()
+ self.outputcoords.frame_no = -1
+ self.outputcoords.nsteps = 1
+ self.outputcoords.filename = self.outcoordfile
+ self.outputcoords.positions = self.outcoordgen
+ return self.outputcoords
def set_ThermoData(self):
try:
@@ -2185,8 +2745,7 @@ class MDDataAccess(object):
yield step
self.thermostats.iread = thermogen(self)
- self.access_ui.thermostats = self.thermostats
- self.access_ui.thermoDict = self.thermostats.thermoDict
+ return self.thermostats
def get_natoms_from_topo(self, topocode=None):
"""Read the first configuration of the coordinate file to extract the
@@ -2204,7 +2763,7 @@ class MDDataAccess(object):
elif "mdanalysis" in topocode:
n_atoms = len(self.topohandler.atoms)
elif "ase" in topocode:
- n_atoms = len(self.trajiter)
+ n_atoms = len(self.topohandler.get_positions())
return n_atoms
def get_natoms_from_traj(self, trajcode=None):
diff --git a/common/python/nomadcore/metainfo_storage/MetaInfoStorage.py b/common/python/nomadcore/metainfo_storage/MetaInfoStorage.py
index 8fab71d6a86eb978555ca62a96a5446760e2ca99..a91655c330de0b837b52295ce85c1dd245da7b73 100644
--- a/common/python/nomadcore/metainfo_storage/MetaInfoStorage.py
+++ b/common/python/nomadcore/metainfo_storage/MetaInfoStorage.py
@@ -284,7 +284,7 @@ class Container(object):
if "lookupdict" in item:
needFetchVal = False
if "test" in firstdepend:
- updateValue, localdict = self.checkTestsDicts(item, localdict)
+ storeValue, updateValue, localdict = self.checkTestsDicts(item, localdict)
elif "assign" in firstdepend:
updateValue = firstdepend["assign"]
elif "value" in firstdepend:
@@ -304,7 +304,7 @@ class Container(object):
else:
needFetchVal = False
if "test" in firstdepend:
- updateValue, localdict = self.checkTestsAttr(item, localdict)
+ storeValue, updateValue, localdict = self.checkTestsAttr(item, localdict)
elif "assign" in firstdepend:
updateValue = firstdepend["assign"]
elif "value" in firstdepend:
@@ -373,6 +373,8 @@ class Container(object):
newUpdateValue = updateValue
elif is_number(updateValue):
newUpdateValue = eval(valtype+"("+str(updateValue)+")")
+ else:
+ newUpdateValue = updateValue
else:
# I hope you know what you are doing
try:
@@ -450,8 +452,9 @@ class Container(object):
if eval(str(checkval) + deptest[1]):
depmeet += 1
if depmeet == len(deptests):
+ storeValue = False
if 'assign' in depdict:
- return depdict['assign'], localdict
+ return storeValue, depdict['assign'], localdict
elif 'value' in depdict:
if depdict['value'] in localdict:
checkval = localdict[depdict['value']]
@@ -459,8 +462,18 @@ class Container(object):
accessName, checkval = self.findNameInLookupDict(depdict['value'],
item.lookupdict)
localdict.update({depdict['value'] : checkval})
- return checkval, localdict
- return None, localdict
+ return storeValue, checkval, localdict
+ elif "store" in depdict:
+ itemdepval = depdict["store"]
+ storeValue = True
+ if itemdepval in localdict:
+ checkval = localdict[itemdepval]
+ else:
+ accessName, checkval = self.findNameInLookupDict(itemdepval, item.lookupdict)
+ localdict.update({itemdepval : checkval})
+ print("PRINTING: metainfo, store:",storeValue, checkval)
+ return storeValue, checkval, localdict
+ return False, None, localdict
def checkTestsAttr(self, item, localdict):
for depdict in item["depends"]:
diff --git a/common/python/nomadcore/smart_parser/SmartParserCommon.py b/common/python/nomadcore/smart_parser/SmartParserCommon.py
index 38b191a5bbd6fd450713a22ef39296db95be48e1..ba30130218a3d754cd41a92673e04ecb1a33c47d 100644
--- a/common/python/nomadcore/smart_parser/SmartParserCommon.py
+++ b/common/python/nomadcore/smart_parser/SmartParserCommon.py
@@ -5,7 +5,7 @@ from nomadcore.caching_backend import CachingLevel
from nomadcore.simple_parser import mainFunction
from nomadcore.simple_parser import SimpleMatcher as SM
from nomadcore.metainfo_storage.MetaInfoStorage import COMMON_META_INFO_PATH, PUBLIC_META_INFO_PATH
-import nomadcore.metainfo_storage.MetaInfoStorage as mStore
+from nomadcore.metainfo_storage import MetaInfoStorage as mStore
from nomadcore.metainfo_storage.MetaInfoStorage import strcleaner, strisinstance, literal_eval
from nomadcore.smart_parser.SmartParserDictionary import getDict_MetaStrInDict, getList_MetaStrInDict, get_unitDict
from contextlib import contextmanager
@@ -287,6 +287,7 @@ class ParserBase(object):
lastLine = parser.fIn.fInLine
else:
lastLine = entryline
+ #print("PRINTING: dictionary_parser:",lastLine)
parserDict = {
"firstLine" : 0,
"storedLines" : '',
@@ -299,10 +300,17 @@ class ParserBase(object):
dicttype = True
readdict = True
keyMapper = None
+ updatefunc = None
+ updateattrs = None
+ updateconvert = None
+ cntrlattrs = None
+ preprocess = None
+ postprocess = None
parsercntrlattr = None
parsercntrlin = None
lookupdict = None
lookupvals = None
+ checkdict = {}
if "dictionary" in parserOptions.keys():
if isinstance(parserOptions["dictionary"], dict):
dictionary = parserOptions["dictionary"]
@@ -317,6 +325,29 @@ class ParserBase(object):
readdict = False
if "keyMapper" in parserOptions.keys():
keyMapper = parserOptions["keyMapper"] if isinstance(parserOptions["keyMapper"], dict) else None
+ if "updatefunc" in parserOptions.keys():
+ if isinstance(parserOptions["updatefunc"], str):
+ if 'max' in parserOptions["updatefunc"]:
+ updatefunc = np.amax
+ updateconvert = float
+ if 'min' in parserOptions["updatefunc"]:
+ updatefunc = np.amin
+ updateconvert = float
+ else:
+ updatefunc = parserOptions["updatefunc"]
+ if "updateattrs" in parserOptions:
+ updateattrs = parserOptions["updateattrs"]
+ if "controlattrs" in parserOptions:
+ cntrlattrs = parserOptions["controlattrs"]
+ if cntrlattrs:
+ for cntrla in cntrlattrs:
+ if hasattr(self,cntrla):
+ checkdict.update({cntrla:getattr(self,cntrla)})
+ #print("PRINTING 0 checkdict:",checkdict)
+ if "preprocess" in parserOptions.keys():
+ preprocess = parserOptions["preprocess"]
+ if "postprocess" in parserOptions.keys():
+ postprocess = parserOptions["postprocess"]
if "lookupdict" in parserOptions:
lookupdict = getattr(self,parserOptions["lookupdict"])
if "parsercntrlattr" in parserOptions:
@@ -334,7 +365,6 @@ class ParserBase(object):
mNameDict = getattr(self, matchNameDict)
-
if dictionary is not None:
if dicttype:
dictionaryStr = getDict_MetaStrInDict(dictionary)
@@ -368,24 +398,92 @@ class ParserBase(object):
v = val[elementid]
else:
v = val
+ if preprocess is not None:
+ v = preprocess(cName,v)
+ if updatefunc is not None:
+ if updateconvert is None:
+ v=updatefunc(v)
+ else:
+ vallist=[]
+ if mNameDict[key].value is not None:
+ vallist.append(updateconvert(mNameDict[key].value))
+ if v is not None:
+ vallist.append(updateconvert(v))
+ if not vallist:
+ pass
+ else:
+ v=updatefunc(np.asarray(vallist))
+ if postprocess is not None:
+ v = postprocess(cName,v)
if key in list(parser.lastMatch.keys()):
parser.lastMatch[key]=v
else:
mNameDict[key].value=v
mNameDict[key].activeInfo=True
+ if isinstance(updateattrs,(tuple,list)):
+ for uattr in updateattrs:
+ if(uattr == cNewName and hasattr(self,cNewName)):
+ setattr(self,uattr,v)
+ #print("PRINTING: self update2:",uattr,v)
else:
val = mNameDict[key].value
+ #print("PRINTING: dict key val:",key,val)
if isinstance(val, (list,tuple,np.ndarray)):
v = val[elementid]
else:
v = val
+ if preprocess is not None:
+ #v = preprocess(v)
+ v = preprocess(cName,v)
+ if updatefunc is not None:
+ vallist=[]
+ if dicttype:
+ if dictionary[dictionaryStr[cNewName]].value is not None:
+ vallist.append(updateconvert(
+ dictionary[dictionaryStr[cNewName]].value
+ ))
+ else:
+ if dictionary[cNewName] is not None:
+ vallist.append(updateconvert(
+ dictionary[cNewName]
+ ))
+ if v is not None:
+ vallist.append(updateconvert(v))
+ if not vallist:
+ pass
+ else:
+ #print("PRINTING: vallist:",vallist)
+ v=updatefunc(np.asarray(vallist))
+ if postprocess is not None:
+ v = postprocess(cName,v)
if dicttype:
dictionary[dictionaryStr[cNewName]].value=v
+ #print("PRINTING: update key val:",dictionaryStr[cNewName],v)
else:
dictionary[cNewName]=v
+ #print("PRINTING: update key val:",cNewName,v)
anythingmatched = True
+ if readdict:
+ pass
+ else:
+ setattr(self,parserOptions["dictionary"],dictionary)
+ if isinstance(updateattrs,(tuple,list)):
+ for dk,dv in dictionary.items():
+ for uattr in updateattrs:
+ if(uattr == dk and hasattr(self,uattr)):
+ setattr(self,uattr,dv)
+ #print("PRINTING: self uupdate2:",uattr,dv)
+
+ cntrlcheck = False
+ if cntrlattrs:
+ for cntrla in cntrlattrs:
+ if hasattr(self,cntrla):
+ #print("PRINTING getattr checkdict:",cntrla,getattr(self,cntrla),checkdict[cntrla])
+ if getattr(self,cntrla)==checkdict[cntrla]:
+ cntrlcheck = True
+ break
- if anythingmatched:
+ if cntrlcheck:
# We have matched keywords to update at sections
# if the active sections are defined
cntrlDict = None
@@ -425,13 +523,12 @@ class ParserBase(object):
addname = addname + str(parserDict["parserID"])
secDict.update({addname:True})
setattr(self,parserOptions["controlsave"],secDict)
- setattr(self,parserOptions["lookupdict"],cntrlDict)
- if readdict is False:
- setattr(self,parserOptions["dictionary"],dictionary)
+ setattr(self,parserOptions["controldict"],cntrlDict)
parserSuccess = True
if(mNameDict is not None and updateMatchDict):
setattr(self, matchNameDict, mNameDict)
+ #print("PRINTING: dict Md step:",self.MDcurrentstep)
return lastLine, parserSuccess
def readline_control_parser(self, parser, stopOnMatchStr, quitOnMatchStr, metaNameStart, matchNameList,
@@ -452,8 +549,8 @@ class ParserBase(object):
controlattr = None
controlnextattr = None
controllast = None
- controlskip = None
- controlin = None
+ controlskip = []
+ controlin = []
controlwait = None
controlcounter = 0
controldict = None
@@ -482,8 +579,10 @@ class ParserBase(object):
controlin = parserOptions["controlin"]
if("controlskip" in parserOptions and
controlin is not None):
- controlskip = [controlin[cs] for cs in parserOptions[
- "controlskip"] if cs < len(controlin)]
+ controlskip = [
+ controlin[cs] for cs in parserOptions[
+ "controlskip"] if cs < len(controlin)
+ ]
if "controlwait" in parserOptions:
if lookupdict:
if parserOptions["controlwait"] in lookupdict:
@@ -523,16 +622,29 @@ class ParserBase(object):
if waitatlineRe.findall(lastLine):
continuenewline = False
else:
- if controlattr in controlwait:
+ if controlwait is not None:
+ if controlattr in controlwait:
+ continuenewline = True
+ else:
continuenewline = True
else:
- if controlattr in controlwait:
- continuenewline = True
+ if controlwait is not None:
+ if controlattr in controlwait:
+ continuenewline = True
+ #else:
+ # continuenewline = True
if continuenewline is False:
- if controlattr in controlwait:
+ if controlwait is not None:
+ if controlattr in controlwait:
+ continuenewline = True
+ else:
continuenewline = True
+
+ #print("PRINTING nextlogsteps, MDnextstep, targetstep:",controlwait,controlnextattr,controlcounter)
+ #print("PRINTING continuenewline:",continuenewline)
if continuenewline:
+ #print("PRINTING: readline_control lastLine:",lastLine)
parserSuccess=True
lastLine = parser.fIn.readline()
else:
@@ -588,18 +700,23 @@ class ParserBase(object):
"numStoredLines" : 0,
"parserID" : parserID,
}
+ if parsername is None:
+ parsername = "section_control_parser_"+str(parserID)
+ sectionopenname = parsername + "_open"
+ sectionclosename = parsername + "_close"
+ #print("PRINTING: section_control "+parsername)
parserSuccess = False
backend = parser.backend
sectionname = None
sectionopen = False
sectionopenattr = None
sectionopenin = None
+ sectionopenrecord = None
sectionclose = False
sectioncloseattr = None
sectionclosein = None
+ sectioncloserecord = None
lookupdict = None
- openlookupvals = None
- closelookupvals = None
activatesection = None
if "sectionname" in parserOptions:
sectionname = parserOptions["sectionname"]
@@ -611,28 +728,48 @@ class ParserBase(object):
sectionopenattr = getattr(self,parserOptions["sectionopenattr"])
if "sectionopenin" in parserOptions:
if lookupdict:
- sectionopenin = parserOptions["sectionopenin"]
- if sectionopenin in lookupdict:
- openlookupvals = lookupdict[sectionopenin]
+ if parserOptions["sectionopenin"] in lookupdict:
+ sectionopenin = lookupdict[parserOptions["sectionopenin"]]
else:
if isinstance(parserOptions["sectionopenin"], str):
sectionopenin = getattr(self,parserOptions["sectionopenin"])
else:
sectionopenin = parserOptions["sectionopenin"]
+ if sectionopenin is not None:
+ if lookupdict:
+ if sectionopenname in lookupdict:
+ sectionopenrecord = lookupdict[sectionopenname]
+ else:
+ sectionopenrecord = getattr(self,sectionopenname)
+ if sectionopenrecord is None:
+ #print("PRINTING: section open record setup")
+ sectionopenrecord = dict()
+ for item in sectionopenin:
+ sectionopenrecord.update({str(item):False})
if "sectionclose" in parserOptions:
sectionclose = parserOptions["sectionclose"]
if "sectioncloseattr" in parserOptions:
sectioncloseattr = getattr(self,parserOptions["sectioncloseattr"])
if "sectionclosein" in parserOptions:
if lookupdict:
- sectionclosein = parserOptions["sectionclosein"]
- if sectionclosein in lookupdict:
- closelookupvals = lookupdict[sectionclosein]
+ if parserOptions["sectionclosein"] in lookupdict:
+ sectionclosein = lookupdict[parserOptions["sectionclosein"]]
else:
if isinstance(parserOptions["sectionclosein"], str):
sectionclosein = getattr(self,parserOptions["sectionclosein"])
else:
sectionclosein = parserOptions["sectionclosein"]
+ if sectionclosein is not None:
+ if lookupdict:
+ if sectionclosename in lookupdict:
+ sectioncloserecord = lookupdict[sectionclosename]
+ else:
+ sectioncloserecord = getattr(self,sectionclosename)
+ if sectioncloserecord is None:
+ #print("PRINTING: section close record setup")
+ sectioncloserecord = dict()
+ for item in sectionclosein:
+ sectioncloserecord.update({str(item):False})
if "activatesection" in parserOptions:
if lookupdict:
if parserOptions["activatesection"] in lookupdict:
@@ -640,25 +777,42 @@ class ParserBase(object):
if sectionname:
activate = False
+ #print("PRINTING: sectionname activatesection:",sectionname,activatesection)
if activatesection is not None:
if sectionname in activatesection:
activate = activatesection[sectionname]
if activate:
+ #print("PRINTING: activate:",activate)
+ #print("PRINTING: open record dict:",sectionopenrecord)
+ #print("PRINTING: close record dict:",sectioncloserecord)
if(sectionopen is not None and
sectionopenattr is not None and
- openlookupvals is not None):
- if sectionopenattr in openlookupvals:
- parserSuccess = True
- gIndex = backend.openSection(sectionname)
- self.secGIndexDict.update({sectionname : [1, gIndex]})
+ sectionopenrecord is not None):
+ #print("PRINTING: section open:",str(sectionopenattr))
+ if str(sectionopenattr) in sectionopenrecord:
+ if sectionopenrecord[str(sectionopenattr)] is False:
+ parserSuccess = True
+ gIndex = backend.openSection(sectionname)
+ self.secGIndexDict.update({sectionname : [1, gIndex]})
+ sectionopenrecord[str(sectionopenattr)] = True
if(sectionclose is not None and
sectioncloseattr is not None and
- closelookupvals is not None):
- if sectioncloseattr in closelookupvals:
- if self.secGIndexDict[sectionname][0]:
- parserSuccess = True
- backend.closeSection(sectionname, self.secGIndexDict[sectionname][1])
- self.secGIndexDict.update({sectionname : [0, gIndex]})
+ sectioncloserecord is not None):
+ #print("PRINTING: section close:",str(sectioncloseattr))
+ if str(sectioncloseattr) in sectioncloserecord:
+ if sectioncloserecord[str(sectioncloseattr)] is False:
+ if self.secGIndexDict[sectionname][0]:
+ parserSuccess = True
+ backend.closeSection(sectionname, self.secGIndexDict[sectionname][1])
+ self.secGIndexDict.update({sectionname : [0, gIndex]})
+ sectioncloserecord[str(sectioncloseattr)] = True
+
+ if lookupdict:
+ lookupdict.update({sectionopenname:sectionopenrecord})
+ lookupdict.update({sectionclosename:sectioncloserecord})
+ else:
+ setattr(self,sectionopenname,sectionopenrecord)
+ setattr(self,sectionclosename,sectioncloserecord)
if parserSuccess:
if activatesection is not None:
@@ -666,38 +820,7 @@ class ParserBase(object):
activatesection[sectionname] = False
lookupdict.update({parserOptions["activatesection"] : activatesection})
setattr(self,parserOptions["lookupdict"],lookupdict)
-
-
-# stopOnMatch = False
-# if(stopOnMatchStr is None or "AlwaysStop" in stopOnMatchStr):
-# stopOnMatch = True
-# else:
-# stopOnMatchRe = re.compile(stopOnMatchStr)
-# if stopOnMatchRe.findall(lastLine):
-# stopOnMatch = True
-# if self.firstLine==0:
-# if stopOnFirstLine:
-# stopOnMatch = True
-# else:
-# stopOnMatch = False
-# if(quitOnMatchStr is None or "AlwaysStop" in quitOnMatchStr):
-# stopOnMatch = True
-# else:
-# quitOnMatchRe = re.compile(quitOnMatchStr)
-# if quitOnMatchRe.findall(lastLine):
-# stopOnMatch = True
-# if stopOnMatch is False:
-# while True:
-# lastLine = self.peekline(parser)
-# parserDict.update({"firstLine" : parserDict["firstLine"] + 1})
-# if not lastLine:
-# break
-# else:
-# if stopOnMatchRe.findall(lastLine):
-# stopOnMatch = True
-# break
-# else:
-# lastLine = parser.fIn.readline()
+ #print("PRINTING: Success sectionname activatesection:",sectionname,activatesection)
return lastLine, parserSuccess
@@ -713,6 +836,7 @@ class ParserBase(object):
headerList = None if header is not True, values will be assigned to
titles in the headerList in order as seen in line
"""
+ #print("PRINTING: table_store lastLine:",lastLine)
tableStartRe = None
if "tablestartsat" in parserOptions:
tableStartRe = re.compile(parserOptions["tablestartsat"])
@@ -740,24 +864,38 @@ class ParserBase(object):
# the table properties
header = False
wrap = False
- storeLines = 1
+ storeLines = 0
lineFilter = None
headerList = None
+ headerListCheck = None
+ headersave = None
skipLines = 0
if "header" in parserOptions.keys():
header = parserOptions["header"] if (parserOptions["header"] is not None or
parserOptions["header"] is not False) else False
+ if "headersave" in parserOptions.keys():
+ if parserOptions["headersave"]:
+ headersave = getattr(self, parserOptions["headersave"])
+ else:
+ headersave = None
if "headerList" in parserOptions.keys():
- headerList = parserOptions["headerList"] if parserOptions["headerList"] else None
+ if parserOptions["headerList"]:
+ headerListCheck = getattr(self, parserOptions["headerList"])
+ if headerListCheck is not None:
+ headerList = headerListCheck
+ else:
+ headerList = parserOptions["headerList"]
+ else:
+ headerList = None
if "wrap" in parserOptions.keys():
wrap = parserOptions["wrap"] if parserOptions["wrap"] else False
if "tablelines" in parserOptions.keys():
- storeLines = parserOptions["tablelines"] if parserOptions["tablelines"]>0 else 1
+ storeLines = parserOptions["tablelines"] if parserOptions["tablelines"]>0 else 0
if "lineFilter" in parserOptions.keys():
lineFilter = parserOptions["lineFilter"] if isinstance(parserOptions["lineFilter"], dict) else None
if "skiplines" in parserOptions.keys():
skipLines = parserOptions["skiplines"]
- if (skipLines>0 and skipLines>=parserDict["firstLine"]):
+ if (skipLines>0 and skipLines>parserDict["firstLine"]):
linenum = -1
else:
linenum = parserDict["numStoredLines"]
@@ -765,6 +903,10 @@ class ParserBase(object):
parserDict.update({"storedLines" : parserDict["storedLines"] + conv_str(lastLine)})
linenum += 1
parserDict.update({"numStoredLines" : linenum})
+ if storeLines == 0:
+ parserDict.update({"storedLines" : conv_str(lastLine)})
+ linenum = 0
+ parserDict.update({"numStoredLines" : linenum})
mNameDict = getattr(self, matchNameDict)
@@ -795,7 +937,12 @@ class ParserBase(object):
vlist.extend(line.split())
else:
if headerList is not None:
- hlist.extend(headerList)
+ if isinstance(headerList, (tuple, list)):
+ hlist.extend(headerList)
+ elif isinstance(headerList, dict):
+ hlist.extend(headerList.keys())
+ elif isinstance(headerList, str):
+ hlist.extend(headerList.split())
vlist.extend(line.split())
lcount += 1
# Reconvert to original
@@ -806,18 +953,27 @@ class ParserBase(object):
hitem = hitem.replace(v, k)
tmplist.append(hitem)
hlist = tmplist
+ #print("PRINTING table_parser lcount:hlist:vlist:",lcount,hlist,vlist)
anythingmatched = False
# Search for dictionary keys
- for cName, key in getDict_MetaStrInDict(mNameDict).items():
- if cName in hlist:
- v=vlist[hlist.index(cName)]
- if key in list(parser.lastMatch.keys()):
- parser.lastMatch[key]=v
- else:
- mNameDict[key].value=v
- mNameDict[key].activeInfo=True
+ if vlist:
+ for cName, key in getDict_MetaStrInDict(mNameDict).items():
+ if cName in hlist:
+ v=vlist[hlist.index(cName)]
+ #print("PRINTING table_parser save:",cName,v)
+ if key in list(parser.lastMatch.keys()):
+ parser.lastMatch[key]=v
+ else:
+ mNameDict[key].value=v
+ mNameDict[key].activeInfo=True
+ anythingmatched = True
+ else:
+ if(header is not None and headersave is not None):
+ for cName in hlist:
+ headersave.update({cName : None})
anythingmatched = True
if anythingmatched:
+ #print("PRINTING table_parser header:",headersave)
# We have matched keywords to update at sections
# if the active sections are defined
cntrlDict = None
@@ -857,7 +1013,7 @@ class ParserBase(object):
addname = addname + str(parserDict["parserID"])
secDict.update({addname:True})
setattr(self,parserOptions["controlsave"],secDict)
- setattr(self,parserOptions["lookupdict"],cntrlDict)
+ setattr(self,parserOptions["controldict"],cntrlDict)
linenum = 0
parserDict.update({"numStoredLines" : linenum})
@@ -870,6 +1026,8 @@ class ParserBase(object):
if(mNameDict is not None and updateMatchDict):
setattr(self, matchNameDict, mNameDict)
+ if(headersave is not None and anythingmatched is True):
+ setattr(self, parserOptions["headersave"], headersave)
return False, parserDict
def table_parser(self, parser, stopOnMatchStr, quitOnMatchStr, metaNameStart, matchNameList,
@@ -879,6 +1037,7 @@ class ParserBase(object):
lastLine = parser.fIn.fInLine
else:
lastLine = entryline
+ #print("PRINTING table_parser:",lastLine)
parserDict = {
"firstLine" : 0,
"storedLines" : '',
@@ -886,6 +1045,7 @@ class ParserBase(object):
"parserID" : parserID,
"parserSuccess" : False,
}
+ #print("PRINTING: table_parser:",parsername,lastLine)
updateLastLine = False
parsercontinue = True
parsercntrlattr = None
@@ -975,6 +1135,7 @@ class ParserBase(object):
# if self.MD is not True:
# newLine = parser.fIn.readline()
# lastLine = ' = '.join([ "%s" % str(line) for line in zip(lastLine, newLine)])
+ anythingmatched = False
mNameDict = getattr(self, matchNameDict)
for cName, key in getDict_MetaStrInDict(mNameDict).items():
if onlyCaseSensitive is not True:
@@ -990,9 +1151,9 @@ class ParserBase(object):
if mNameDict[key].replaceDict:
replaceDict = mNameDict[key].replaceDict
else:
- replaceDict = None
+ replaceDict = None
if mNameDict[key].subFunc:
- if isinstance(subFunc, str):
+ if isinstance(mNameDict[key].subFunc, str):
subFunc = getattr(self,mNameDict[key].subFunc)
else:
subFunc = mNameDict[key].subFunc
@@ -1001,13 +1162,13 @@ class ParserBase(object):
if mNameDict[key].addAsList:
addAsList = mNameDict[key].addAsList
else:
- addAsList = None
+ addAsList = None
if mNameDict[key].appendToList:
appendToList = getattr(self,mNameDict[key].appendToList)
else:
appendToList = None
if 'EOL' in matchWith:
- matchThisParsy = re.compile(r"(?:%s)\s*(?:=|:)\s*(?:'|\")?"
+ matchThisParsy = re.compile(r"(?:%s)\s*(?:\s|=|:)\s*(?:'|\")?"
"(?P<%s>.*)(?:'|\")?\s*,?"
% (cText, key))
elif 'UD' in matchWith:
@@ -1061,6 +1222,49 @@ class ParserBase(object):
mNameDict[k].value=v
mNameDict[k].activeInfo=True
parserDict.update({"parserSuccess" : True})
+ anythingmatched = True
+ if appendToList is not None:
+ setattr(self, mNameDict[key].appendToList, appendToList)
+ if anythingmatched:
+ # We have matched keywords to update at sections
+ # if the active sections are defined
+ cntrlDict = None
+ cntrlsec = None
+ cntrlsave = None
+ if "controldict" in parserOptions:
+ cntrlDict = getattr(self,parserOptions["controldict"])
+ if "controlsections" in parserOptions:
+ cntrlsec = parserOptions["controlsections"]
+ if "controlsave" in parserOptions:
+ if cntrlDict:
+ if parserOptions["controlsave"] in cntrlDict:
+ secDict = {}
+ cntrlsave = cntrlDict[parserOptions["controlsave"]]
+ if isinstance(cntrlsave,dict):
+ secDict = cntrlsave
+ if cntrlsec is not None:
+ for sec in cntrlsec:
+ secDict.update({sec:True})
+ else:
+ addname = "table_store"
+ if parserDict["parserID"] is not None:
+ addname = addname + str(parserDict["parserID"])
+ secDict.update({addname:True})
+ cntrlDict.update({parserOptions["controlsave"]:secDict})
+ else:
+ secDict = {}
+ cntrlsave = getattr(self,parserOptions["controlsave"])
+ if isinstance(cntrlsave,dict):
+ secDict = cntrlsave
+ if cntrlsec is not None:
+ for sec in cntrlsec:
+ secDict.update({sec:True})
+ else:
+ addname = "table_store"
+ if parserDict["parserID"] is not None:
+ addname = addname + str(parserDict["parserID"])
+ secDict.update({addname:True})
+ setattr(self,parserOptions["controlsave"],secDict)
if(mNameDict is not None and updateMatchDict):
setattr(self, matchNameDict, mNameDict)
@@ -1073,6 +1277,7 @@ class ParserBase(object):
lastLine = parser.fIn.fInLine
else:
lastLine = entryline
+ #print("PRINTING: name_list:",lastLine)
parserDict = {
"firstLine" : 0,
"storedLines" : lastLine,
@@ -1080,8 +1285,11 @@ class ParserBase(object):
"parserSuccess" : False,
}
self.firstLine = 0
+ updateLastLine = False
# Check the captured line has Fortran namelist variables and store them.
# Continue search and store until the line matches with stopOnMatch.
+ if "movetostopline" in parserOptions:
+ updateLastLine = parserOptions["movetostopline"]
stopOnMatchRe = re.compile(stopOnMatchStr)
quitOnMatchRe = None
if quitOnMatchStr is not None:
@@ -1109,6 +1317,8 @@ class ParserBase(object):
onlyCaseSensitive, stopOnFirstLine,
parserDict, parserOptions)
if rtn:
+ if updateLastLine:
+ lastLine = parser.fIn.readline()
break
else:
lastLine = parser.fIn.readline()
diff --git a/common/python/nomadcore/smart_parser/SmartParserDictionary.py b/common/python/nomadcore/smart_parser/SmartParserDictionary.py
index 6434b71f045d4c039090379fd948061a6189a155..de28fbd70fbbe725a251d348b9ff7236fe630267 100644
--- a/common/python/nomadcore/smart_parser/SmartParserDictionary.py
+++ b/common/python/nomadcore/smart_parser/SmartParserDictionary.py
@@ -293,7 +293,13 @@ def isMetaStrInDict(nameStr, sourceDict):
Meta name strings are not actual meta names but
used as the keywords in the parsing.
"""
- return [k for k,v in sourceDict.items() if nameStr in v.matchStr][0]
+ val = None
+ for k,v in sourceDict.items():
+ if nameStr in v.matchStr:
+ val = k
+ break
+ return val
+ #return [k for k,v in sourceDict.items() if nameStr in v.matchStr][0]
def getDict_MetaStrInDict(sourceDict, nameList=None):
"""Returns a dict that includes all meta name