Cleaner base class for parsers.

cp2kparser/__init__.py

@@ -2,5 +2,4 @@
 import cp2kparser.generics.logconfig
 from pint import UnitRegistry
 import os
-ureg = UnitRegistry()
-ureg.load_definitions(os.path.dirname(__file__)+"/unit_registry.txt")
+ureg = UnitRegistry(os.path.dirname(__file__)+"/unit_registry.txt")

cp2kparser/constants.txt

 # Pint constants for NomadParsers
 # source: http://physics.nist.gov/cuu/Constants/Table/allascii.txt
+# Source: http://physics.nist.gov/cuu/Constants/Table/allascii.txt
 
-# Bohr radius
+speed_of_light = 299792458 * meter / second = c
+standard_gravity = 9.806650 * meter / second ** 2 = g_0 = g_n = gravity
+vacuum_permeability = 4 * pi * 1e-7 * newton / ampere ** 2 = mu_0 = magnetic_constant
+vacuum_permittivity = 1 / (mu_0 * c **2 ) = epsilon_0 = electric_constant
+Z_0 = mu_0 * c = impedance_of_free_space = characteristic_impedance_of_vacuum
 bohr = 0.52917721067e-10 m
+
+# 0.000 000 29 e-34
+planck_constant = 6.62606957e-34 J s = h
+hbar = planck_constant / (2 * pi) = ħ
+
+# 0.000 80 e-11
+newtonian_constant_of_gravitation = 6.67384e-11 m^3 kg^-1 s^-2
+
+# 0.000 000 035 e-19
+# elementary_charge = 1.602176565e-19 C = e
+
+# 0.000 0075
+molar_gas_constant = 8.3144621 J mol^-1 K^-1 = R
+
+# 0.000 000 0024 e-3
+fine_structure_constant = 7.2973525698e-3
+
+# 0.000 000 27 e23
+avogadro_number = 6.02214129e23 mol^-1 =N_A
+
+# 0.000 0013 e-23
+boltzmann_constant = 1.3806488e-23 J K^-1 = k
+
+# 0.000 021 e-8
+stefan_boltzmann_constant = 5.670373e-8 W m^-2 K^-4 = σ
+
+# 0.000 0053 e10
+wien_frequency_displacement_law_constant = 5.8789254e10 Hz K^-1
+
+# 0.000 055
+rydberg_constant = 10973731.568539 m^-1
+
+# 0.000 000 40 e-31
+electron_mass = 9.10938291e-31 kg = m_e
+
+# 0.000 000 074 e-27
+neutron_mass = 1.674927351e-27 kg = m_n
+
+# 0.000 000 074 e-27
+proton_mass = 1.672621777e-27 kg = m_p

cp2kparser/implementation/autoparser.py

 import os
 import json
 from cp2kparser.implementation.parser import CP2KParser
+import sys
 
 
 #===============================================================================
@@ -23,16 +24,17 @@ def scan_path_for_files(path):
 
 
 #===============================================================================
-def get_parser(path, test=True):
+def get_parser(path, test_mode=True, stream=sys.stdout):
     files = scan_path_for_files(path)
     json_input = {
         "version": "nomadparsein.json 1.0",
-        "tmpDir": "/home/lauri",
+        "metaInfoFile": os.path.join(os.path.dirname(__file__), 'metainfo.json'),
+        "tmpDir": "/home",
         "metainfoToKeep": [],
         "metainfoToSkip": [],
         "files": files
     }
-    parser = CP2KParser(json.dumps(json_input), test=test)
+    parser = CP2KParser(json.dumps(json_input), test_mode=test_mode, stream=stream)
     return parser
 
 

cp2kparser/implementation/parser.py

@@ -23,10 +23,10 @@ class CP2KParser(NomadParser):
     implementation. For other versions there should be classes that extend from
     this.
     """
-    def __init__(self, input_json_string, stream=sys.stdout, test=False):
+    def __init__(self, input_json_string, stream=sys.stdout, test_mode=False):
 
         # Initialize the base class
-        NomadParser.__init__(self, input_json_string, stream, test)
+        NomadParser.__init__(self, input_json_string, stream, test_mode)
 
         # Engines are created here
         self.csvengine = CSVEngine(self)
@@ -36,6 +36,7 @@ class CP2KParser(NomadParser):
         self.atomsengine = AtomsEngine(self)
 
         self.version_number = None
+        self.implementation = None
         self.input_tree = None
         self.regexs = None
 
@@ -44,6 +45,18 @@ class CP2KParser(NomadParser):
         self.setup_version()
         self.determine_file_ids_post_setup()
 
+    def get_supported_quantities(self):
+        """Inherited from NomadParser.
+        """
+        supported_quantities = []
+        implementation_methods = [method for method in dir(self.implementation) if callable(getattr(self.implementation, method))]
+        for method in implementation_methods:
+            if method.startswith("_Q_"):
+                method = method[3:]
+                supported_quantities.append(method)
+
+        return supported_quantities
+
     def setup_version(self):
         """Inherited from NomadParser.
         """
@@ -75,6 +88,16 @@ class CP2KParser(NomadParser):
             logger.debug("Using default implementation.")
             self.implementation = globals()["CP2KImplementation"](self)
 
+    def start_parsing(self, name):
+        """Inherited from NomadParser.
+        """
+        # Ask the implementation for the quantity
+        function = getattr(self.implementation, "_Q_" + name)
+        if function:
+            return function()
+        else:
+            logger.error("The function for quantity '{}' is not defined".format(name))
+
     def read_part_of_file(self, file_id, size=1024):
         fh = self.get_file_handle(file_id)
         buffer = fh.read(size)
@@ -156,8 +179,9 @@ class CP2KParser(NomadParser):
         the path until only one or zero matches found.
         """
         matches = {}
+        resolvable = [x for x in self.files.iterkeys() if x not in self.file_ids.itervalues()]
 
-        for file_path in self.resolvable:
+        for file_path in resolvable:
             available_parts = self.split_path(file_path)
             searched_parts = self.split_path(path)
             for i_part, part in enumerate(searched_parts):
@@ -193,22 +217,10 @@ class CP2KParser(NomadParser):
 
         return folders
 
-    def start_parsing(self, name):
-        """Inherited from NomadParser. The timing and caching is already
-        implemented in the superclass.
-        """
-        # Ask the implementation for the quantity
-        function = getattr(self.implementation, "_Q_" + name)
-        if function:
-            return function()
-        else:
-            logger.error("The function for quantity '{}' is not defined".format(name))
-
-    def check_quantity_availability(self, name):
-        """Inherited from NomadParser.
-        """
-        #TODO
-        return True
+    def get_all_quantities(self):
+        """Parse all supported quantities."""
+        for method in self.get_supported_quantities:
+            self.get_quantity(method)
 
 
 #===============================================================================
@@ -231,6 +243,25 @@ class CP2KImplementation(object):
         self.atomsengine = parser.atomsengine
         self.input_tree = parser.input_tree
 
+    def decode_cp2k_unit(self, unit):
+        """Given a CP2K unit name, decode it as Pint unit definition.
+        """
+
+        map = {
+            # Length
+            "bohr": ureg.bohr,
+            "m": ureg.meter,
+            "pm": ureg.picometer,
+            "nm": ureg.nanometer,
+            "angstrom": ureg.angstrom,
+        }
+
+        pint_unit = map.get(unit)
+        if pint_unit:
+            return pint_unit
+        else:
+            logger.error("Unknown CP2K unit definition given.")
+
     def _Q_energy_total(self):
         """Return the total energy from the bottom of the input file"""
         result = Result()
@@ -348,26 +379,13 @@ class CP2KImplementation(object):
                 force_array[i_conf, :, :] = i_force_array
                 i_conf += 1
 
-            result.value = force_array
+            result.value_iterable = force_array
             return result
         else:
             logger.debug("Looking for forces in separate force file.")
             iterator = self.csvengine.iread(self.parser.get_file_handle("forces"), columns=(-3, -2, -1), comments=("#", "SUM"), separator=r"\ ATOMIC FORCES in \[a\.u\.\]")
-            forces = []
-            for configuration in iterator:
-                forces.append(configuration)
-            forces = np.array(forces)
-
-            if forces is None:
-                msg = "No force configurations were found when searching an external XYZ force file."
-                logger.warning(msg)
-                result.error_message = msg
-                result.code = ResultCode.fail
-                return result
-            else:
-                if len(forces) != 0:
-                    result.value = forces
-                return result
+            result.value_iterable = iterator
+            return result
 
     def _Q_particle_number(self):
         """Return the number of particles in the system.
@@ -413,13 +431,15 @@ class CP2KImplementation(object):
         return result
 
     def _Q_particle_position(self):
-        """Returns the particle positions (trajectory). Currently returns them
-        as one big object, which is not good because the trajectory can be very
-        large. When the streaming interface is available the coordinates can be
-        streamed to an outputfile.
+        """Returns the particle positions (trajectory).
         """
         result = Result()
 
+        # Determine the unit
+        unit = self.input_tree.get_keyword("MOTION/PRINT/TRAJECTORY/UNIT")
+        unit = unit.lower()
+        result.unit = self.decode_cp2k_unit(unit)
+
         # Read the trajectory
         traj_file = self.parser.get_file_handle("trajectory")
         file_format = self.input_tree.get_keyword("MOTION/PRINT/TRAJECTORY/FORMAT")
@@ -429,13 +449,8 @@ class CP2KImplementation(object):
         }[file_format]
         traj_iter = self.atomsengine.iread(traj_file, format=file_format)
 
-        # Loop through the iterator to get all configurations
-        positions = []
-        for configuration in traj_iter:
-            positions.append(configuration)
-        if positions:
-            result.value = np.array(positions)
-
+        # Return the iterator
+        result.value_iterable = traj_iter
         return result
 
 

cp2kparser/tests/cp2k_2.6.2/run_tests.py

@@ -5,13 +5,15 @@ from cp2kparser.implementation.autoparser import get_parser
 from cp2kparser.engines.cp2kinputenginedata.xmlpreparser import *
 import cProfile
 import pstats
+import cStringIO
 
 
 #===============================================================================
 def getparser(folder):
     path = os.path.dirname(os.path.realpath(__file__))
     path = os.path.join(path, folder)
-    parser = get_parser(path, test=True)
+    dump = cStringIO.StringIO()
+    parser = get_parser(path, test_mode=True, stream=dump)
     return parser
 
 
@@ -22,7 +24,7 @@ class TestFunctionals(unittest.TestCase):
         path = os.path.join(os.path.dirname(os.path.realpath(__file__)), "functionals", folder)
         parser = getparser(path)
         xc = parser.parse_quantity("XC_functional")
-        self.assertEqual(xc.value, result)
+        self.assertEqual(xc, result)
 
     def test_pade(self):
         self.getxc("pade", "LDA_XC_TETER93")
@@ -42,7 +44,7 @@ class TestForces(unittest.TestCase):
 
     def test_forces_in_outputfile_n(self):
         parser = getparser("forces/outputfile/n")
-        forces = parser.parse_quantity("particle_forces").value
+        forces = parser.parse_quantity("particle_forces")
         n_conf = forces.shape[0]
         n_particles = forces.shape[1]
         n_dim = forces.shape[2]
@@ -52,7 +54,7 @@ class TestForces(unittest.TestCase):
 
     def test_forces_in_outputfile_1(self):
         parser = getparser("forces/outputfile/1")
-        forces = parser.parse_quantity("particle_forces").value
+        forces = parser.parse_quantity("particle_forces")
         n_conf = forces.shape[0]
         n_particles = forces.shape[1]
         n_dim = forces.shape[2]
@@ -62,12 +64,12 @@ class TestForces(unittest.TestCase):
 
     def test_forces_in_outputfile_0(self):
         parser = getparser("forces/outputfile/0")
-        forces = parser.parse_quantity("particle_forces").value
+        forces = parser.parse_quantity("particle_forces")
         self.assertEqual(forces, None)
 
     def test_forces_in_singlexyzfile_n(self):
         parser = getparser("forces/singlexyzfile/n")
-        forces = parser.parse_quantity("particle_forces").value
+        forces = parser.parse_quantity("particle_forces")
         n_conf = forces.shape[0]
         n_particles = forces.shape[1]
         n_dim = forces.shape[2]
@@ -77,7 +79,7 @@ class TestForces(unittest.TestCase):
 
     def test_forces_in_singlexyzfile_1(self):
         parser = getparser("forces/singlexyzfile/1")
-        forces = parser.parse_quantity("particle_forces").value
+        forces = parser.parse_quantity("particle_forces")
         n_conf = forces.shape[0]
         n_particles = forces.shape[1]
         n_dim = forces.shape[2]
@@ -87,7 +89,7 @@ class TestForces(unittest.TestCase):
 
     def test_forces_in_singlexyzfile_0(self):
         parser = getparser("forces/singlexyzfile/0")
-        forces = parser.parse_quantity("particle_forces").value
+        forces = parser.parse_quantity("particle_forces")
         self.assertEqual(forces, None)
 
 
@@ -96,42 +98,42 @@ class TestParticleNumber(unittest.TestCase):
 
     def test_input_n(self):
         parser = getparser("particle_number/inputfile/n")
-        n = parser.parse_quantity("particle_number").value
+        n = parser.parse_quantity("particle_number")
         self.assertEqual(n, 2)
 
     def test_input_1(self):
         parser = getparser("particle_number/inputfile/1")
-        n = parser.parse_quantity("particle_number").value
+        n = parser.parse_quantity("particle_number")
         self.assertEqual(n, 1)
 
     def test_input_extra_lines(self):
         parser = getparser("particle_number/inputfile/extra_lines")
-        n = parser.parse_quantity("particle_number").value
+        n = parser.parse_quantity("particle_number")
         self.assertEqual(n, 2)
 
     def test_input_multiplication(self):
         parser = getparser("particle_number/inputfile/multiplication")
-        n = parser.parse_quantity("particle_number").value
+        n = parser.parse_quantity("particle_number")
         self.assertEqual(n, 12)
 
     def test_xyz_n(self):
         parser = getparser("particle_number/xyz/n")
-        n = parser.parse_quantity("particle_number").value
+        n = parser.parse_quantity("particle_number")
         self.assertEqual(n, 2)
 
     def test_xyz_multiplication(self):
         parser = getparser("particle_number/xyz/multiplication")
-        n = parser.parse_quantity("particle_number").value
+        n = parser.parse_quantity("particle_number")
         self.assertEqual(n, 12)
 
     def test_cif_n(self):
         parser = getparser("particle_number/cif/n")
-        n = parser.parse_quantity("particle_number").value
+        n = parser.parse_quantity("particle_number")
         self.assertEqual(n, 2)
 
     def test_pdb_n(self):
         parser = getparser("particle_number/pdb/n")
-        n = parser.parse_quantity("particle_number").value
+        n = parser.parse_quantity("particle_number")
         self.assertEqual(n, 2)
 
 
@@ -140,7 +142,7 @@ class TestTrajectory(unittest.TestCase):
 
     def test_filenames_bare(self):
         parser = getparser("trajectory/filenames/bare")
-        pos = parser.parse_quantity("particle_position").value
+        pos = parser.parse_quantity("particle_position")
         n_conf = pos.shape[0]
         n_particles = pos.shape[1]
         n_dim = pos.shape[2]
@@ -150,7 +152,7 @@ class TestTrajectory(unittest.TestCase):
 
     def test_filenames_dotslash(self):
         parser = getparser("trajectory/filenames/dotslash")
-        pos = parser.parse_quantity("particle_position").value
+        pos = parser.parse_quantity("particle_position")
         n_conf = pos.shape[0]
         n_particles = pos.shape[1]
         n_dim = pos.shape[2]
@@ -160,7 +162,7 @@ class TestTrajectory(unittest.TestCase):
 
     def test_filenames_equals(self):
         parser = getparser("trajectory/filenames/equals")
-        pos = parser.parse_quantity("particle_position").value
+        pos = parser.parse_quantity("particle_position")
         n_conf = pos.shape[0]
         n_particles = pos.shape[1]
         n_dim = pos.shape[2]
@@ -170,7 +172,7 @@ class TestTrajectory(unittest.TestCase):
 
     def test_pdb(self):
         parser = getparser("trajectory/pdb")
-        pos = parser.parse_quantity("particle_position").value
+        pos = parser.parse_quantity("particle_position")
         n_conf = pos.shape[0]
         n_particles = pos.shape[1]
         n_dim = pos.shape[2]
@@ -180,7 +182,7 @@ class TestTrajectory(unittest.TestCase):
 
     def test_xyz(self):
         parser = getparser("trajectory/xyz")
-        pos = parser.parse_quantity("particle_position").value
+        pos = parser.parse_quantity("particle_position")
         n_conf = pos.shape[0]
         n_particles = pos.shape[1]
         n_dim = pos.shape[2]

cp2kparser/unit_registry.txt

-# Default Pint units definition file
+# NomadParser Pint units definition file
 # Based on the International System of Units
 
+# decimal prefixes
+yocto- = 1e-24 = y-
+zepto- = 1e-21 = z-
+atto- =  1e-18 = a-
+femto- = 1e-15 = f-
+pico- =  1e-12 = p-
+nano- =  1e-9  = n-
+micro- = 1e-6  = u- = µ-
+milli- = 1e-3  = m-
+centi- = 1e-2  = c-
+deci- =  1e-1  = d-
+deca- =  1e+1  = da-
+hecto- = 1e2   = h-
+kilo- =  1e3   = k-
+mega- =  1e6   = M-
+giga- =  1e9   = G-
+tera- =  1e12  = T-
+peta- =  1e15  = P-
+exa- =   1e18  = E-
+zetta- = 1e21  = Z-
+yotta- = 1e24  = Y-
+
+# binary_prefixes
+kibi- = 2**10 = Ki-
+mebi- = 2**20 = Mi-
+gibi- = 2**30 = Gi-
+tebi- = 2**40 = Ti-
+pebi- = 2**50 = Pi-
+exbi- = 2**60 = Ei-
+zebi- = 2**70 = Zi-
+yobi- = 2**80 = Yi-
+
+# SI units
+meter = [length] = m = metre
+second = [time] = s = sec
+ampere = [current] = A = amp
+candela = [luminosity] = cd = candle
+kilogram = [mass] = kg
+mole = [substance] = mol
+kelvin = [temperature]; offset: 0 = K = degK
+
 @import constants.txt
 
+# Acceleration
+[acceleration] = [length] / [time] ** 2
+
+# Angle
+radian = [] = rad
+turn = 2 * pi * radian = revolution = cycle = circle
+degree = pi / 180 * radian = deg = arcdeg = arcdegree = angular_degree
+arcminute = arcdeg / 60 = arcmin = arc_minute = angular_minute
+arcsecond = arcmin / 60 =  arcsec = arc_second = angular_second
+steradian = radian ** 2 = sr
+
+# Area
+[area] = [length] ** 2
+are = 100 * m**2
+barn = 1e-28 * m ** 2 = b
+cmil = 5.067075e-10 * m ** 2 = circular_mils
+darcy = 9.869233e-13 * m ** 2
+acre = 4046.8564224 * m ** 2 = international_acre
+hectare = 100 * are = ha
+US_survey_acre = 160 * rod ** 2
+
+# Electromagetism
+esu = 1 * erg**0.5 * centimeter**0.5 = statcoulombs = statC = franklin = Fr
+esu_per_second = 1 * esu / second = statampere
+ampere_turn = 1 * A
+gilbert = 10 / (4 * pi ) * ampere_turn
+coulomb = ampere * second = C
+volt = joule / coulomb = V
+farad = coulomb / volt = F
+ohm = volt / ampere = Ω
+siemens = ampere / volt = S = mho
+weber = volt * second = Wb
+tesla = weber / meter ** 2 = T
+henry = weber / ampere = H
+elementary_charge = 1.602176487e-19 * coulomb = e
+chemical_faraday = 9.64957e4 * coulomb
+physical_faraday = 9.65219e4 * coulomb
+faraday =  96485.3399 * coulomb = C12_faraday
+gamma = 1e-9 * tesla
+gauss = 1e-4 * tesla
+maxwell = 1e-8 * weber = mx
+oersted = 1000 / (4 * pi) * A / m = Oe
+statfarad = 1.112650e-12 * farad = statF = stF
+stathenry = 8.987554e11 * henry = statH = stH
+statmho = 1.112650e-12 * siemens = statS = stS
+statohm = 8.987554e11 * ohm
+statvolt = 2.997925e2 * volt = statV = stV
+unit_pole = 1.256637e-7 * weber
+
+# Energy
+[energy] = [force] * [length]
+joule = newton * meter = J
+erg = dyne * centimeter
+btu = 1.05505585262e3 * joule = Btu = BTU = british_thermal_unit
+electron_volt = 1.60217653e-19 * J = eV
+quadrillion_btu = 10**15 * btu = quad
+thm = 100000 * BTU = therm = EC_therm
+cal = 4.184 * joule = calorie = thermochemical_calorie
+international_steam_table_calorie = 4.1868 * joule
+ton_TNT = 4.184e9 * joule = tTNT
+US_therm = 1.054804e8 * joule
+watt_hour = watt * hour = Wh = watthour
+hartree = 4.35974394e-18 * joule = E_h = hartree_energy
+
 # Force
+[force] = [mass] * [acceleration]
 force_au = hartree / bohr
+newton = kilogram * meter / second ** 2 = N
+dyne = gram * centimeter / second ** 2 = dyn
+force_kilogram = g_0 * kilogram = kgf = kilogram_force = pond
+force_gram = g_0 * gram = gf = gram_force
+force_ounce = g_0 * ounce = ozf = ounce_force
+force_pound = g_0 * lb = lbf = pound_force
+force_ton = 2000 * force_pound = ton_force
+poundal = lb * feet / second ** 2 = pdl
+kip = 1000*lbf
+
+# Frequency
+[frequency] = 1 / [time]
+hertz = 1 / second = Hz = rps
+revolutions_per_minute = revolution / minute = rpm
+counts_per_second = count / second = cps
+
+# Heat
+#RSI = degK * meter ** 2 / watt
+#clo = 0.155 * RSI = clos
+#R_value = foot ** 2 * degF * hour / btu
+
+# Information
+bit = []
+byte = 8 * bit = Bo = octet
+baud = bit / second = Bd = bps
+
+# Irradiance
+peak_sun_hour = 1000 * watt_hour / meter**2 = PSH
+langley = thermochemical_calorie / centimeter**2 = Langley
+
+# Length
+angstrom = 1e-10 * meter = Å = ångström = Å
+inch = 2.54 * centimeter = in = international_inch = inches = international_inches
+foot = 12 * inch = ft = international_foot = feet = international_feet
+mile = 5280 * foot = mi = international_mile
+yard = 3 * feet = yd = international_yard
+mil = inch / 1000 = thou
+parsec = 3.08568025e16 * meter = pc
+light_year = speed_of_light * julian_year = ly = lightyear
+astronomical_unit = 149597870691 * meter = au
+nautical_mile = 1.852e3 * meter = nmi
+printers_point = 127 * millimeter / 360 = point
+printers_pica = 12 * printers_point = pica
+US_survey_foot = 1200 * meter / 3937
+US_survey_yard =  3 * US_survey_foot
+US_survey_mile = 5280 * US_survey_foot = US_statute_mile
+rod = 16.5 * US_survey_foot = pole = perch
+furlong = 660 * US_survey_foot
+fathom = 6 * US_survey_foot
+chain = 66 * US_survey_foot
+barleycorn = inch / 3
+arpentlin = 191.835 * feet
+kayser = 1 / centimeter = wavenumber
+
+# Mass
+dram = oz / 16 = dr = avoirdupois_dram
+ounce = 28.349523125 * gram = oz = avoirdupois_ounce
+pound = 0.45359237 * kilogram = lb = avoirdupois_pound
+stone = 14 * lb = st
+carat = 200 * milligram
+grain = 64.79891 * milligram = gr
+long_hundredweight = 112 * lb
+short_hundredweight = 100 * lb
+metric_ton = 1000 * kilogram = t = tonne
+pennyweight = 24 * gram = dwt
+slug = 14.59390 * kilogram
+troy_ounce = 480 * grain = toz = apounce = apothecary_ounce
+troy_pound = 12 * toz = tlb = appound = apothecary_pound
+drachm = 60 * grain = apdram = apothecary_dram
+atomic_mass_unit = 1.660538782e-27 * kilogram =  u = amu = dalton = Da
+scruple = 20 * grain
+bag = 94 * lb
+ton = 2000 * lb = short_ton