Add marda-extractors support for PW and CP input files (#73)

src/qe_tools/exceptions.py

@@ -14,3 +14,9 @@ class InputValidationError(Exception):
     The input data for a calculation did not validate (e.g., missing
     required input data, wrong data, ...)
     """
+
+
+class PathIsNotAFile(OSError):
+    """
+    The path is pointing to an object that is not a valid file.
+    """

src/qe_tools/extractors/__init__.py

@@ -0,0 +1,55 @@
+# -*- coding: utf-8 -*-
+from pathlib import Path
+
+from qe_tools.exceptions import PathIsNotAFile
+from qe_tools.parsers import CpInputFile, PwInputFile
+
+SUPPORTED_PARSERS = [
+    'PW',
+    'CP',
+]
+
+
+def extract(filepath: str, parser: str) -> dict:
+    """Extract QE input file as a dictionary.
+
+    Parameters
+    ----------
+    `filepath` : `str`
+        The path to the file.
+    `parser` : `str`
+        The QE parser type. Supported: ['PW', 'CP']
+
+    Returns
+    -------
+    `dict`
+        The parsed input as a dictionary.
+
+    Raises
+    ------
+    `FileNotFoundError`
+        If the file does not exist.
+    `PathIsNotAFile`
+        If the path does not point to a file.
+    `ValueError`
+        If the parser type is not supported.
+    """
+
+    path = Path(filepath)
+
+    if not path.exists():
+        raise FileNotFoundError(f"'{filepath}' does not exist")
+
+    if not path.is_file():
+        raise PathIsNotAFile(f"'{filepath}' is not a valid file.")
+
+    input_str = path.read_text(encoding='utf-8')
+    parser = parser.upper()
+
+    if parser == 'PW':
+        return PwInputFile(input_str).as_dict()
+
+    if parser == 'CP':
+        return CpInputFile(input_str).as_dict()
+
+    raise ValueError(f"Supported parsers: {SUPPORTED_PARSERS}; given: '{parser}'")

src/qe_tools/parsers/_input_base.py

@@ -207,6 +207,12 @@ def __init__(self, content, *, qe_version=None, validate_species_names=True):
             qe_version=self._qe_version
         )
 
+    def as_dict(self) -> dict:
+        """Return parsed data as dictionary."""
+        return {
+            'structure': self.structure,
+        }
+
 
 def _str2val(valstr):
     """

src/qe_tools/parsers/_pw_input.py

@@ -160,6 +160,14 @@ def __init__(self, content, *, qe_version=None, validate_species_names=True):
         # Parse the K_POINTS card.
         self.k_points = parse_k_points(self._input_txt)
 
+    def as_dict(self) -> dict:
+        """Return parsed data as dictionary."""
+        dictionary = super().as_dict()
+        dictionary.update({
+            'k-points': self.k_points,
+        })
+        return dictionary
+
 
 def parse_k_points(txt):
     """

tests/data/cp.in

@@ -0,0 +1,49 @@
+ &control
+    title = ' Water Molecule ',
+    calculation = 'cp',
+    restart_mode = 'from_scratch',
+    ndr = 51,
+    ndw = 51,
+    nstep  = 100,
+    iprint = 100,
+    isave  = 100,
+    tstress = .TRUE.,
+    tprnfor = .TRUE.,
+    dt    = 5.0d0,
+    etot_conv_thr = 1.d-9,
+    ekin_conv_thr = 1.d-4,
+    prefix = 'h2o'
+    verbosity = 'medium'
+ /
+ &system
+    ibrav = 14,
+    celldm(1) = 12.0,
+    celldm(2) = 1.0,
+    celldm(3) = 1.0,
+    celldm(4) = 0.0,
+    celldm(5) = 0.0,
+    celldm(6) = 0.0,
+    nat  = 3,
+    ntyp = 2,
+    nbnd = 4,
+    ecutwfc = 80.0,
+ /
+ &electrons
+    emass = 400.d0,
+    emass_cutoff = 2.5d0,
+    orthogonalization = 'ortho',
+    electron_dynamics = 'damp',
+    electron_damping = 0.2
+ /
+ &ions
+    ion_dynamics = 'none',
+    ion_radius(1) = 0.8d0,
+    ion_radius(2) = 0.8d0,
+ /
+ATOMIC_SPECIES
+ O 16.0d0 O.blyp-mt.UPF
+ H 1.00d0 H.blyp-vbc.UPF
+ATOMIC_POSITIONS (bohr)
+   O     0.0099    0.0099    0.0000  0 0 0
+   H     1.8325   -0.2243   -0.0001  1 1 1
+   H    -0.2243    1.8325    0.0002  1 1 1

tests/data/extractor_ref/cp.json

@@ -0,0 +1,20 @@
+{
+  "structure": {
+    "positions": [
+      [0.005238854365041, 0.005238854365041, 0.0],
+      [0.9697172347411749, -0.11869444788673698, -5.2917720858999996e-5],
+      [-0.11869444788673698, 0.9697172347411749, 0.00010583544171799999]
+    ],
+    "species": {
+      "names": ["O", "H"],
+      "masses": [16.0, 1.0],
+      "pseudo_file_names": ["O.blyp-mt.UPF", "H.blyp-vbc.UPF"]
+    },
+    "cell": [
+      [6.350126503079999, 0.0, 0.0],
+      [0.0, 6.350126503079999, 0.0],
+      [0.0, 0.0, 6.350126503079999]
+    ],
+    "atom_names": ["O", "H", "H"]
+  }
+}

tests/data/extractor_ref/pw.json

@@ -0,0 +1,21 @@
+{
+  "structure": {
+    "positions": [
+      [0.005238854365041, 0.005238854365041, 0.0],
+      [0.9697172347411749, -0.11869444788673698, -5.2917720858999996e-5],
+      [-0.11869444788673698, 0.9697172347411749, 0.00010583544171799999]
+    ],
+    "species": {
+      "names": ["O", "H"],
+      "masses": [16.0, 1.0],
+      "pseudo_file_names": ["O.blyp-mt.UPF", "H.blyp-vbc.UPF"]
+    },
+    "cell": [
+      [6.350126503079999, 0.0, 0.0],
+      [0.0, 6.350126503079999, 0.0],
+      [0.0, 0.0, 6.350126503079999]
+    ],
+    "atom_names": ["O", "H", "H"]
+  },
+  "k-points": { "type": "gamma" }
+}

tests/data/pw.in

@@ -0,0 +1,27 @@
+ &control
+    calculation = 'relax',
+ /
+ &system
+    ibrav = 1,
+    celldm(1) = 12.0,
+    nat  = 3,
+    ntyp = 2,
+    nbnd = 4,
+    ecutwfc = 80,
+    ecutfock=160,
+    input_dft = 'X3LYP'
+    exxdiv_treatment = 'gygi-baldereschi'
+    x_gamma_extrapolation = .TRUE.
+ /
+ &electrons
+ /
+ &ions
+ /
+ATOMIC_SPECIES
+ O 16.0d0 O.blyp-mt.UPF
+ H 1.00d0 H.blyp-vbc.UPF
+ATOMIC_POSITIONS (bohr)
+   O     0.0099    0.0099    0.0000
+   H     1.8325   -0.2243   -0.0001
+   H    -0.2243    1.8325    0.0002
+K_POINTS gamma

tests/test_extractor.py

@@ -0,0 +1,15 @@
+# -*- coding: utf-8 -*-
+import json
+from pathlib import Path
+
+import pytest
+
+from qe_tools.extractors import extract
+
+
+@pytest.mark.parametrize('parser', ['pw', 'cp'])
+def test_input_dict_extraction(parser: str):
+    datadir = Path(__file__).resolve().parent / 'data'
+    filepath = datadir / f'{parser}.in'
+    refpath = datadir / 'extractor_ref' / f'{parser}.json'
+    assert extract(filepath.as_posix(), parser) == json.loads(refpath.read_text())