First version of Gaussian parser including geometry

parser/parser-gaussian/parser_gaussian.py

 import setup_paths
 from nomadcore.simple_parser import mainFunction, SimpleMatcher as SM
 from nomadcore.local_meta_info import loadJsonFile, InfoKindEl
-import os, sys, json
+from nomadcore.caching_backend import CachingLevel
+import os, sys, json, logging
+import numpy as np
 
 # description of the input
 mainFileDescription = SM(
@@ -10,14 +12,40 @@ mainFileDescription = SM(
     startReStr = "",
     subMatchers = [
         SM(name = 'newRun',
-           startReStr = r"\s*# SampleParser #\s*",
+           startReStr = r"\s*Entering Link 1 ",
            repeats = True,
            required = True,
            forwardMatch = True,
-           sections   = ['section_run'],
+           sections   = ['section_run','section_method'],
            subMatchers = [
                SM(name = 'header',
-                  startReStr = r"\s*# SampleParser #\s*")
+                  startReStr = r"\s*Entering Link 1 ",
+                  subMatchers = [
+                      SM(r"\s*Cite this work as:"),
+                      SM(r"\s*Gaussian [0-9]+, Revision [A-Za-z0-9.]*,"),
+                      SM(r"\s\*\*\*\*\*\*\*\*\*\*\*\**"),
+                      SM(r"\s*(?P<program_name>Gaussian)\s*(?P<program_version>[0-9]*:\s.*)")
+                      ]
+              ),
+               SM(name = 'globalparams',
+                  startReStr = r"\s*%\w*=",
+                  subFlags = SM.SubFlags.Unordered,
+                  forwardMatch = True,
+                  subMatchers = [
+                      SM(r"\s*%[Cc]hk=(?P<gaussian_chk_file>[A-Za-z0-9.]*)"),
+                      SM(r"\s*%[Mm]em=(?P<gaussian_memory>[A-Za-z0-9.]*)"),
+                      SM(r"\s*%[Nn][Pp]roc=(?P<gaussian_number_of_processors>[A-Za-z0-9.]*)"),
+                      ]
+              ),
+               SM(name = 'geometry_charge_multiplicity',
+	          sections  = ['section_system_description','gaussian_section_geometry'],
+		  startReStr = r"\s*Symbolic Z-matrix:",
+                      subMatchers = [
+		      SM(r"\s*Charge =\s*(?P<total_charge>[-+0-9]+) Multiplicity =\s*(?P<target_multiplicity>[0-9]+)"),
+                      SM(r"\s*(?P<gaussian_atom_label>\w+)\s+(?P<gaussian_atom_x_coord__angstrom>[-+0-9EeDd.]+)\s+(?P<gaussian_atom_y_coord__angstrom>[-+0-9EeDd.]+)\s+(?P<gaussian_atom_z_coord__angstrom>[-+0-9EeDd.]+)",
+			repeats = True)
+                      ]),
+               SM(r"\s*NAtoms=")
            ])
 ])
 
@@ -33,23 +61,36 @@ parserInfo = {
 class GaussianParserContext(object):
     """main place to keep the parser status, open ancillary files,..."""
     def __init__(self):
-        self.scfIterNr = 0
+        pass
 
-    # just examples, you probably want to remove the following two triggers
+    def startedParsing(self, path, parser):
+        self.parser = parser
 
-    def onClose_section_single_configuration_calculation(self, backend, gIndex, section):
-        """trigger called when section_single_configuration_calculation is closed"""
-        #backend.addValue("", self.scfIterNr)
-        logging.getLogger("nomadcore.parsing").info("closing section_single_configuration_calculation gIndex %d %s", gIndex, section.simpleValues)
-        self.scfIterNr = 0
-
-    def onClose_section_scf_iteration(self, backend, gIndex, section):
-        """trigger called when section_scf_iteration is closed"""
-        logging.getLogger("nomadcore.parsing").info("closing section_scf_iteration bla gIndex %d %s", gIndex, section.simpleValues)
-        self.scfIterNr += 1
+    def onClose_gaussian_section_geometry(self, backend, gIndex, section):
+	xCoord = section["gaussian_atom_x_coord"]
+	yCoord = section["gaussian_atom_y_coord"]
+        zCoord = section["gaussian_atom_z_coord"]
+	labels = section["gaussian_atom_label"]
+	logging.error("x:%s",xCoord)
+        logging.error("y:%s",yCoord)
+        logging.error("z:%s",zCoord)
+        logging.error("labels:%s",labels)
+        atom_positions = np.zeros((len(xCoord),3), dtype=float)
+	for i in range(len(xCoord)):
+	    atom_positions[i,0] = xCoord[i]
+            atom_positions[i,1] = yCoord[i]
+            atom_positions[i,2] = zCoord[i]
+	backend.addArrayValues("atom_position", atom_positions)
+	backend.addValue("atom_label", labels)
 
 # which values to cache or forward (mapping meta name -> CachingLevel)
-cachingLevelForMetaName = {}
+cachingLevelForMetaName = {
+	"gaussian_atom_x_coord": CachingLevel.Cache,
+        "gaussian_atom_y_coord": CachingLevel.Cache,
+        "gaussian_atom_z_coord": CachingLevel.Cache,
+	"gaussian_atom_label": CachingLevel.Cache,
+	"gaussian_section_geometry": CachingLevel.Ignore,
+}
 
 if __name__ == "__main__":
     mainFunction(mainFileDescription, metaInfoEnv, parserInfo,

test/examples/Al.inp

+%mem=24000000
+#B1B95/6-31G** 
+
+atom calc
+casno=7429905
+method=55
+basis=3
+
+0 2
+Al
+

test/examples/ZnO10pbe.dat

+%chk=ZnO10pbe
+%mem=1500mb
+%nproc=12
+#p pbepbe/6-31G* td(singlets,nstates=10) 
+
+ZnO 10
+
+0 1
+O        3.25422625       1.27930585      -2.54529614 
+Zn        2.24859735      -0.44790645      -2.74547013 
+O        3.22448354      -2.01425234      -3.19002709 
+Zn        3.40374636      -1.80554341      -5.20959503 
+O        5.25270943      -2.29560427      -5.24774549 
+Zn        5.99419054      -0.54286846      -5.22935256 
+O        6.28848283      -0.42881245      -3.16157625 
+Zn        5.12324614      -1.93265943      -3.19033674 
+Zn        4.96040891       0.94341796      -3.28777063 
+O        5.13698492       1.15172617      -5.30695890 
+Zn        0.60201850      -0.16611529      -5.28308763 
+O        2.30611968      -0.50267796      -6.02913818 
+Zn        3.31139087       1.22419605      -5.82287052 
+O       -0.72661336       1.20584185      -5.41057105 
+Zn       -0.43367086       1.32094499      -3.34238586 
+O        0.42394706      -0.37365245      -3.26432151 
+Zn        2.15599088       2.58444037      -3.36102890 
+O        0.30716576       3.07376050      -3.32446397 
+Zn        0.43812201       2.71026983      -5.38146546 
+O        2.33665319       2.79214294      -5.38100795
+