orto 1.10.0__py3-none-any.whl → 1.11.0__py3-none-any.whl

orto/__version__.py

@@ -1 +1 @@
-__version__ = '1.10.0'
+__version__ = '1.11.0'

orto/cli.py

@@ -1,6 +1,4 @@
 import argparse
-import xyz_py as xyzp
-from xyz_py.atomic import elements as atomic_elements
 import sys
 import pathlib
 import os
@@ -9,14 +7,11 @@ import subprocess
 import csv
 import numpy as np
 import re
-from mmap import mmap, ACCESS_READ
-from shutil import move as shutilmove
-from subto.job import SlurmJob
+from xyz_py.atomic import elements as atomic_elements
 
 from . import job
 from . import utils as ut
 from . import constants as cst
-from . import data as d
 from .exceptions import DataNotFoundError, DataFormattingError
 
 _SHOW_CONV = {
@@ -40,9 +35,9 @@ def extract_coords_func(uargs, save=True):
 
     Parameters
     ----------
-    args : argparser object
+    uargs: argparser object
         command line arguments
-    save : bool, default=True
+    save: bool, default=True
         If True, saves data to file. If False, prints to stdout.
 
     Returns
@@ -50,6 +45,7 @@ def extract_coords_func(uargs, save=True):
         None
     '''
     from . import extractor as oe
+    import xyz_py as xyzp
 
     # Open file and extract coordinates
     labels, coords = oe.get_coords(
@@ -120,7 +116,7 @@ def extract_sf_energies_func(uargs):
         style = doc.styles['Normal']
         font = style.font
         font.name = 'Arial'
-        font.size = Pt(9)
+        font.size = Pt(12)
 
         # For each extracted section, print matrix, vectors, and values
         for it, data in enumerate(all_data):
@@ -154,7 +150,13 @@ def extract_sf_energies_func(uargs):
                     cell.vertical_alignment = WD_ALIGN_VERTICAL.CENTER
                     cell.paragraphs[0].style = 'Normal'
 
-        doc.save(out_name)
+        try:
+            doc.save(out_name)
+        except PermissionError:
+            ut.red_exit(
+                f'Cannot write to {out_name}\n'
+                'is the file open somewhere else?'
+            )
 
     ut.cprint(f'Data written to {out_name}', 'cyan')
 
@@ -191,15 +193,205 @@ def extract_so_energies_func(uargs):
     return
 
 
+def extract_hyperfine_func(uargs, save=True):
+    '''
+    Wrapper for cli call to extract hyperfine
+
+    Parameters
+    ----------
+    uargs: argparser object
+        command line arguments
+    save: bool, default=True
+        If True, saves data to file, else prints to stdout.
+    '''
+
+    from . import extractor as oe
+    from docx import Document
+    from docx.enum.text import WD_ALIGN_PARAGRAPH
+    from docx.enum.table import WD_ALIGN_VERTICAL
+    from docx.shared import Pt
+
+    try:
+        all_data = oe.HyperfineExtractor.extract(uargs.output_file)
+    except (DataFormattingError, ValueError) as e:
+        ut.red_exit(str(e))
+
+    if not save:
+        for data in all_data:
+            for key, val in data.items():
+                print(f'{key}:')
+                print(val)
+        sys.exit(0)
+
+    if uargs.output_format == 'txt':
+        out_name = f'{uargs.output_file.stem}_hyperfine.txt'
+        with open(out_name, 'w') as f:
+            f.write(f'Data from {uargs.output_file}\n')
+            f.write('All values are in MHz')
+            for data in all_data:
+                if len(all_data) > 1:
+                    f.write('=================\n')
+                for key, val in data.items():
+                    f.write(f'{key}:\n')
+                    f.write(str(val).replace('[', '').replace(']', ''))
+                    f.write('\n')
+
+    if uargs.output_format == 'docx':
+        out_name = f'{uargs.output_file.stem}_hyperfine.docx'
+
+        title = 'Hyperfine coupling data from DFT'
+        title += (f'Data from {uargs.output_file}\n')
+
+        # Create document
+        doc = Document()
+
+        doc.add_heading(title, 0)
+
+        # Add style
+        style = doc.styles['Normal']
+        font = style.font
+        font.name = 'Arial'
+        font.size = Pt(12)
+
+        # For each extracted section, print all data
+        for data in all_data:
+            if len(all_data) > 1:
+                doc.add_paragraph(
+                    f'Nucleus: {data['nucleus']}, Isotope: {data['isotope']}'
+                )
+
+            # Full matrix
+            matrix = doc.add_table(rows=5, cols=3)
+
+            matrix.cell(0, 0).merge(
+                matrix.cell(0, 1)
+            ).merge(
+                matrix.cell(0, 2)
+            )
+
+            matrix.cell(0, 0).text = 'Full Hyperfine Tensor / MHz'
+
+            matrix.cell(1, 0).text = '{:.4f}'.format(data['matrix'][0, 0])
+            matrix.cell(2, 0).text = '{:.4f}'.format(data['matrix'][0, 1])
+            matrix.cell(3, 0).text = '{:.4f}'.format(data['matrix'][0, 2])
+
+            matrix.cell(1, 1).text = '{:.4f}'.format(data['matrix'][1, 0])
+            matrix.cell(2, 1).text = '{:.4f}'.format(data['matrix'][1, 1])
+            matrix.cell(3, 1).text = '{:.4f}'.format(data['matrix'][1, 2])
+
+            matrix.cell(1, 2).text = '{:.4f}'.format(data['matrix'][2, 0])
+            matrix.cell(2, 2).text = '{:.4f}'.format(data['matrix'][2, 1])
+            matrix.cell(3, 2).text = '{:.4f}'.format(data['matrix'][2, 2])
+
+            matrix.cell(4, 0).text = 'Isotropic / MHz'
+
+            # Merge three cells for isotropic value
+            matrix.cell(4, 1).merge(
+                matrix.cell(4, 2)
+            )
+            matrix.cell(4, 1).text = f'{data['iso']:.4f}'
+
+            doc.add_paragraph('\n')
+
+            for row in matrix.rows:
+                for cell in row.cells:
+                    cell.paragraphs[0].paragraph_format.alignment = WD_ALIGN_PARAGRAPH.CENTER # noqa
+                    cell.vertical_alignment = WD_ALIGN_VERTICAL.CENTER
+                    cell.paragraphs[0].style = 'Normal'
+
+            # g values and g vectors
+            eigs = doc.add_table(rows=4, cols=4)
+            eigs.cell(0, 1).merge(eigs.cell(0, 1)).merge(eigs.cell(0, 2)).merge(eigs.cell(0, 3)) # noqa
+
+            eigs.cell(0, 0).text = 'Values / MHz'
+            eigs.cell(0, 1).text = 'Vectors'
+
+            eigs.cell(1, 0).text = '{:.4f}'.format(data['values'][0])
+            eigs.cell(2, 0).text = '{:.4f}'.format(data['values'][1])
+            eigs.cell(3, 0).text = '{:.4f}'.format(data['values'][2])
+
+            eigs.cell(1, 1).text = '{:.4f}'.format(data['vectors'][0, 0])
+            eigs.cell(2, 1).text = '{:.4f}'.format(data['vectors'][0, 1])
+            eigs.cell(3, 1).text = '{:.4f}'.format(data['vectors'][0, 2])
+
+            eigs.cell(1, 2).text = '{:.4f}'.format(data['vectors'][1, 0])
+            eigs.cell(2, 2).text = '{:.4f}'.format(data['vectors'][1, 1])
+            eigs.cell(3, 2).text = '{:.4f}'.format(data['vectors'][1, 2])
+
+            eigs.cell(1, 3).text = '{:.4f}'.format(data['vectors'][2, 0])
+            eigs.cell(2, 3).text = '{:.4f}'.format(data['vectors'][2, 1])
+            eigs.cell(3, 3).text = '{:.4f}'.format(data['vectors'][2, 2])
+
+            for row in eigs.rows:
+                for cell in row.cells:
+                    cell.paragraphs[0].paragraph_format.alignment = WD_ALIGN_PARAGRAPH.CENTER # noqa
+                    cell.vertical_alignment = WD_ALIGN_VERTICAL.CENTER
+                    cell.paragraphs[0].style = 'Normal'
+            doc.add_paragraph('\n')
+
+            components = doc.add_table(rows=5, cols=5)
+            components.cell(1, 0).text = 'Fermi Contact'
+            components.cell(2, 0).text = 'Spin Dipole'
+            components.cell(3, 0).text = 'Diamagnetic (Gauge Corr.)'
+            components.cell(4, 0).text = 'Spin-Orbit'
+
+            components.cell(0, 1).text = 'x / MHz'
+            components.cell(0, 2).text = 'y / MHz'
+            components.cell(0, 3).text = 'z / MHz'
+            components.cell(0, 4).text = 'Average / MHz'
+
+            if len(data['fc']):
+                components.cell(1, 1).text = f'{data['fc'][0]:.4f}'
+                components.cell(1, 2).text = f'{data['fc'][1]:.4f}'
+                components.cell(1, 3).text = f'{data['fc'][2]:.4f}'
+                components.cell(1, 4).text = f'{np.mean(data['fc']):.4f}'
+            if len(data['sd']):
+                components.cell(2, 1).text = f'{data['sd'][0]:.4f}'
+                components.cell(2, 2).text = f'{data['sd'][1]:.4f}'
+                components.cell(2, 3).text = f'{data['sd'][2]:.4f}'
+                components.cell(2, 4).text = f'{np.mean(data['sd']):.4f}'
+            if len(data['dia']):
+                components.cell(3, 1).text = f'{data['dia'][0]:.4f}'
+                components.cell(3, 2).text = f'{data['dia'][1]:.4f}'
+                components.cell(3, 3).text = f'{data['dia'][2]:.4f}'
+                components.cell(3, 4).text = f'{np.mean(data['dia']):.4f}'
+            if len(data['orb']):
+                components.cell(4, 1).text = f'{data['orb'][0]:.4f}'
+                components.cell(4, 2).text = f'{data['orb'][1]:.4f}'
+                components.cell(4, 3).text = f'{data['orb'][2]:.4f}'
+                components.cell(4, 4).text = f'{np.mean(data['orb']):.4f}'
+
+            for tab in [matrix, eigs, components]:
+                for row in tab.rows:
+                    for cell in row.cells:
+                        cell.paragraphs[0].paragraph_format.alignment = WD_ALIGN_PARAGRAPH.CENTER # noqa
+                        cell.vertical_alignment = WD_ALIGN_VERTICAL.CENTER
+                        cell.paragraphs[0].style = 'Normal'
+
+            doc.add_page_break()
+
+        try:
+            doc.save(out_name)
+        except PermissionError:
+            ut.red_exit(
+                f'Cannot write to {out_name}\n'
+                'is the file open somewhere else?'
+            )
+
+    ut.cprint(f'Data written to {out_name}', 'cyan')
+
+    return
+
+
 def extract_gmatrix_func(uargs, save=True):
     '''
     Wrapper for cli call to extract gmatrix
 
     Parameters
     ----------
-    args : argparser object
+    uargs: argparser object
         command line arguments
-    save : bool, default=True
+    save: bool, default=True
         If True, saves data to file. If False, prints to stdout.
 
     Returns
@@ -220,6 +412,7 @@ def extract_gmatrix_func(uargs, save=True):
         'dft': oe.GMatrixDFTExtractor
     }
 
+    # Check for linear response hyperfines
     if oe.EPRNMRDetector(uargs.output_file):
         uargs.type = 'dft'
 
@@ -254,7 +447,8 @@ def extract_gmatrix_func(uargs, save=True):
             'total': 'ELECTRONIC G-MATRIX',
             'L': 'ELECTRONIC G-MATRIX: L contribution',
             'S': 'ELECTRONIC G-MATRIX: S contribution',
-            'eff': 'ELECTRONIC G-MATRIX FROM EFFECTIVE HAMILTONIAN'
+            'eff': 'ELECTRONIC G-MATRIX FROM EFFECTIVE HAMILTONIAN',
+            'dft': 'ELECTRONIC G-MATRIX FROM DFT LINEAR RESPONSE'
         }
 
         title = titles[uargs.type]
@@ -268,7 +462,7 @@ def extract_gmatrix_func(uargs, save=True):
         style = doc.styles['Normal']
         font = style.font
         font.name = 'Arial'
-        font.size = Pt(9)
+        font.size = Pt(12)
 
         # For each extracted section, print matrix, vectors, and values
         for it, data in enumerate(all_data):
@@ -330,7 +524,13 @@ def extract_gmatrix_func(uargs, save=True):
                     cell.vertical_alignment = WD_ALIGN_VERTICAL.CENTER
                     cell.paragraphs[0].style = 'Normal'
 
-        doc.save(out_name)
+        try:
+            doc.save(out_name)
+        except PermissionError:
+            ut.red_exit(
+                f'Cannot write to {out_name}\n'
+                'is the file open somewhere else?'
+            )
 
     ut.cprint(f'Data written to {out_name}', 'cyan')
 
@@ -343,13 +543,14 @@ def gen_spden_func(uargs):
 
     Parameters
     ----------
-    uargs : argparser object
+    uargs: argparser object
         User arguments
 
     Returns
     -------
     None
     '''
+    from subto.job import SlurmJob
 
     # Check orca module
     if len(uargs.orca_load):
@@ -423,13 +624,15 @@ def gen_trunc_molden_func(uargs):
 
     Parameters
     ----------
-    uargs : argparser object
+    uargs: argparser object
         User arguments
 
     Returns
     -------
     None
     '''
+    from mmap import mmap, ACCESS_READ
+    from shutil import move as shutilmove
 
     # Read molden file in as binary string
     # and find number of MOs by counting number of
@@ -492,7 +695,7 @@ def gen_job_func(uargs):
 
     Parameters
     ----------
-    uargs : argparser object
+    uargs: argparser object
         User arguments
 
     Returns
@@ -657,7 +860,7 @@ def plot_xes_func(uargs):
 
     Parameters
     ----------
-    uargs : argparser object
+    uargs: argparser object
         User arguments
 
     Returns
@@ -773,7 +976,7 @@ def plot_xas_func(uargs):
 
     Parameters
     ----------
-    uargs : argparser object
+    uargs: argparser object
         User arguments
 
     Returns
@@ -882,10 +1085,10 @@ def plot_abs_func(uargs, save_data_only=False):
 
     Parameters
     ----------
-    uargs : argparser object
+    uargs: argparser object
         User arguments
 
-    save_data_only : bool, default=False
+    save_data_only: bool, default=False
         If True, saves generated spectrum data to file only.
 
     Returns
@@ -897,6 +1100,7 @@ def plot_abs_func(uargs, save_data_only=False):
     import matplotlib.colors as mcolors
     from . import plotter
     from . import extractor as oe
+    from . import data as d
 
     # Change matplotlib font size to be larger
     mpl.rcParams.update({'font.size': 12})
@@ -1106,14 +1310,13 @@ def plot_ir_func(uargs):
 
     Parameters
     ----------
-    uargs : argparser object
+    uargs: argparser object
         User arguments
 
     Returns
     -------
     None
     '''
-    import matplotlib.pyplot as plt
     import matplotlib as mpl
     from . import plotter
     from . import extractor as oe
@@ -1151,7 +1354,7 @@ def distort_func(uargs):
 
     Parameters
     ----------
-    args : argparser object
+    uargs: argparser object
         command line arguments
 
     Returns
@@ -1159,6 +1362,7 @@ def distort_func(uargs):
         None
 
     '''
+    import xyz_py as xyzp
     from . import extractor as oe
 
     # Open file and extract coordinates
@@ -1197,9 +1401,9 @@ def extract_orbs_func(uargs, save=True) -> None:
 
     Parameters
     ----------
-    args : argparser object
+    uargs: argparser object
         command line arguments
-    save : bool, default=True
+    save: bool, default=True
         If True, saves data to file. If False, prints to stdout.
 
     Returns
@@ -1336,7 +1540,7 @@ def extract_orbs_func(uargs, save=True) -> None:
         total = 0.
         for row, val in mo.items():
             if val > uargs.threshold and row[1] in uargs.elements:
-                _output += f'  {row[1]+str(row[0]):5} {row[2]:5} : {val:>5.1f} %\n' # noqa
+                _output += f'  {row[1]+str(row[0]):5} {row[2]:5}: {val:>5.1f} %\n' # noqa
                 total += val
         if len(_output):
             print(f'MO #{mo_num} (Occ={occupancies[mo_num]}, E={energies[mo_num]: .5f}):') # noqa
@@ -1373,9 +1577,9 @@ def extract_freq_func(uargs, save=True):
 
     Parameters
     ----------
-    args : argparser object
+    uargs: argparser object
         command line arguments
-    save : bool, default=True
+    save: bool, default=True
         If True, saves data to file. If False, prints to stdout.
 
     Returns
@@ -1424,14 +1628,15 @@ def extract_pop_func(uargs, save=True) -> None:
 
     Parameters
     ----------
-    uargs : argparser object
+    uargs: argparser object
         User arguments
-    save : bool, default=False
+    save: bool, default=False
         If True, saves data to file. If False, prints to stdout.
     Returns
     -------
         None
     '''
+    import xyz_py as xyzp
     from . import extractor as oe
 
     if uargs.flavour in ['loewdin', 'lowdin']:
@@ -1485,7 +1690,7 @@ def extract_pop_func(uargs, save=True) -> None:
                 _chg = sum([datum[0][labels[ind]] for ind in entity])
                 _spin = sum([datum[1][labels[ind]] for ind in entity])
                 ut.cprint(
-                    f'{entity_name} : {_chg:.4f}  {_spin:.4f}',
+                    f'{entity_name}: {_chg:.4f}  {_spin:.4f}',
                     'cyan'
                 )
 
@@ -1498,7 +1703,7 @@ def plot_susc_func(uargs) -> None:
 
     Parameters
     ----------
-    args : argparser object
+    uargs: argparser object
         command line arguments
 
     Returns
@@ -1610,7 +1815,7 @@ def plot_ailft_func(uargs) -> None:
 
     Parameters
     ----------
-    args : argparser object
+    uargs: argparser object
         command line arguments
 
     Returns
@@ -1696,7 +1901,7 @@ def read_args(arg_list=None):
 
     Parameters
     ----------
-    args : argparser object
+    uargs: argparser object
         command line arguments
 
     Returns
@@ -1791,6 +1996,32 @@ def read_args(arg_list=None):
         help='Number of frequencies to print, default is all'
     )
 
+    extract_hyperfine = extract_parser.add_parser(
+        'hyperfine',
+        description='Extracts hyperfine couplings from Orca output file',
+        usage=ut.cstring(
+            'orto extract hyperfine <output_file> [options]',
+            'cyan'
+        ),
+        formatter_class=argparse.RawTextHelpFormatter
+    )
+    extract_hyperfine._positionals.title = 'Mandatory Arguments'
+    extract_hyperfine.set_defaults(func=extract_hyperfine_func)
+
+    extract_hyperfine.add_argument(
+        'output_file',
+        type=pathlib.Path,
+        help='Path to/Name of Orca output file containing HYPERFINE section'
+    )
+
+    extract_hyperfine.add_argument(
+        '--output_format',
+        type=str,
+        help='Format of outputted data file',
+        choices=['txt', 'docx'],
+        default='txt'
+    )
+
     extract_gmatrix = extract_parser.add_parser(
         'gmatrix',
         description='Extracts coordinates from Orca output file',
@@ -1803,14 +2034,14 @@ def read_args(arg_list=None):
     extract_gmatrix.add_argument(
         'output_file',
         type=pathlib.Path,
-        help='Orca output file name containing G-MATRIX block'
+        help='Path to/Name of Orca output file containing G-MATRIX block'
     )
 
     extract_gmatrix.add_argument(
         '--type',
         type=str,
-        help='Which G-MATRIX block to extract.',
-        choices=['total', 'S', 'L', 'eff'],
+        help='Which G-MATRIX block to extract - if DFT then this option is redundant', # noqa
+        choices=['total', 'S', 'L', 'eff', 'dft'],
         default='total'
     )
 
@@ -2752,9 +2983,30 @@ def read_args(arg_list=None):
     # If argument list is empty then call help function
     print_subprog.set_defaults(func=lambda _: print_subprog.print_help())
 
+    print_hyperfine = print_parser.add_parser(
+        'hyperfine',
+        description='Prints hyperfine couplings from Orca output file',
+        usage=ut.cstring(
+            'orto print hyperfine <output_file> [options]',
+            'cyan'
+        ),
+        formatter_class=argparse.RawTextHelpFormatter
+    )
+    print_hyperfine._positionals.title = 'Mandatory Arguments'
+
+    print_hyperfine.set_defaults(
+        func=lambda x: extract_hyperfine_func(x, save=False)
+    )
+
+    print_hyperfine.add_argument(
+        'output_file',
+        type=pathlib.Path,
+        help='Path to/Name of Orca output file containing HYPERFINE section'
+    )
+
     print_gmatrix = print_parser.add_parser(
         'gmatrix',
-        description='Extracts g matrix from Orca output file',
+        description='Prints g matrix from Orca output file',
         usage=ut.cstring('orto print gmatrix <output_file> [options]', 'cyan'),
         formatter_class=argparse.RawTextHelpFormatter
     )
@@ -2767,7 +3019,7 @@ def read_args(arg_list=None):
     print_gmatrix.add_argument(
         'output_file',
         type=pathlib.Path,
-        help='Orca output file name containing G-MATRIX block'
+        help='Path to/Name of Orca output file containing G-MATRIX block'
     )
 
     print_gmatrix.add_argument(
@@ -2780,7 +3032,7 @@ def read_args(arg_list=None):
 
     print_freq = print_parser.add_parser(
         'freq',
-        description='Prints frequencies',
+        description='Prints frequencies from Orca output file',
         usage=ut.cstring('orto print freq <output_file> [options]', 'cyan'),
         formatter_class=argparse.RawTextHelpFormatter
     )
@@ -2791,7 +3043,7 @@ def read_args(arg_list=None):
     print_freq.add_argument(
         'output_file',
         type=pathlib.Path,
-        help='Orca output file name - must contain Frequencies section'
+        help='Path to/Name of Orca output file containing FREQUENCIES section'
     )
 
     print_freq.add_argument(
@@ -2818,8 +3070,8 @@ def read_args(arg_list=None):
         'output_file',
         type=pathlib.Path,
         help=(
-            'Orca output file name\n'
-            'File must contain one of the following sections\n'
+            'Path to/Name of Orca output file containing\n'
+            'one of the following sections\n'
             '   LOEWDIN ORBITAL-COMPOSITIONS\n'
             '   LOEWDIN REDUCED ORBITAL POPULATIONS PER MO\n'
             '   LOEWDIN ORBITAL POPULATIONS PER MO\n'

orto/extractor.py

@@ -16,7 +16,7 @@ from . import constants as const
 
 def EPRNMRDetector(file_name: str | pathlib.Path) -> bool:
     '''
-    Detects if Orca output file is from EPR/NMR calculation
+    Detects if Orca output file contains an EPRNMR section
     '''
     with open(file_name, 'rb') as f:
         file_content = f.read()
@@ -29,7 +29,7 @@ def EPRNMRDetector(file_name: str | pathlib.Path) -> bool:
 
 class OrcaVersionExtractor(extto.LineExtractor):
     '''
-    Extracts Orca version from output file
+    Extracts Orca version from Orca output file
     '''
 
     # Regex Start Pattern
@@ -235,7 +235,8 @@ class SusceptibilityExtractor(extto.BetweenExtractor):
 
 class ExchangeCouplingExtractor(extto.BetweenExtractor):
     '''
-    Extracts Exchange Coupling Constants and information (J) from output file
+    Extracts Exchange Coupling Constants and information (J) from Orca \n
+    output file
     '''
 
     # Regex Start Pattern
@@ -342,7 +343,7 @@ class ExchangeCouplingExtractor(extto.BetweenExtractor):
 
 class AILFTOrbEnergyExtractor(extto.BetweenExtractor):
     '''
-    Extracts AI-LFT orbital energies from output file
+    Extracts AI-LFT orbital energies from Orca output file
     '''
     # Regex Start Pattern
     START_PATTERN = rb'(?<=The ligand field one electron eigenfunctions:\s-{41})' # noqa
@@ -437,7 +438,7 @@ class AILFTOrbEnergyExtractor(extto.BetweenExtractor):
 class FrequencyExtractor(extto.BetweenExtractor):
     '''
     Extracts Vibrational mode energies, eigenvectors, intensities, \n
-    and irreps from output file
+    and irreps from Orca output file
     '''
 
     # Regex Start Pattern
@@ -665,7 +666,7 @@ class FrequencyExtractor(extto.BetweenExtractor):
 
 class LoewdinPopulationExtractor(extto.BetweenExtractor):
     '''
-    Extracts Loewdin Population Analysis Section from output file
+    Extracts Loewdin Population Analysis Section from Orca output file
     '''
 
     # Regex Start Pattern
@@ -746,7 +747,7 @@ class MullikenPopulationExtractorDensities(LoewdinPopulationExtractor):
     '''
     Extracts Mulliken Population Analysis Section with \n
     MULLIKEN ATOMIC CHARGES AND SPIN DENSITIES header\n
-    from output file
+    from Orca output file`
     '''
 
     # Regex Start Pattern
@@ -759,8 +760,8 @@ class MullikenPopulationExtractorDensities(LoewdinPopulationExtractor):
 class MullikenPopulationExtractorPopulations(LoewdinPopulationExtractor):
     '''
     Extracts Mulliken Population Analysis Section with \n
-    MULLIKEN ATOMIC CHARGES AND SPIN POPULATIONS header
-    from output file
+    MULLIKEN ATOMIC CHARGES AND SPIN POPULATIONS header\n
+    from Orca output file
     '''
 
     # Regex Start Pattern
@@ -772,13 +773,13 @@ class MullikenPopulationExtractorPopulations(LoewdinPopulationExtractor):
 
 class MullikenPopulationExtractor(MullikenPopulationExtractorDensities):
     '''
-    Extracts Mulliken Population Analysis Section from output file
+    Extracts Mulliken Population Analysis Section from Orca output file
     '''
 
 
 class LoewdinCompositionExtractor(extto.BetweenExtractor):
     '''
-    Extracts Loewdin Orbital-Compositions Section from output file\n
+    Extracts Loewdin Orbital-Compositions Section from Orca output file
     '''
 
     # Regex Start Pattern
@@ -2434,9 +2435,176 @@ class SimpleInputExtractor(extto.LineExtractor):
         return _ext.data
 
 
+class HyperfineExtractor(extto.BetweenExtractor):
+    '''
+    Extracts Hyperfine coupling tensor and associated information from Orca\n
+    output file
+    '''
+
+    # Regex Start Pattern
+    START_PATTERN = rb'(?<=-{59}\s Nucleus)'
+
+    # Regex End Pattern
+    END_PATTERN = rb'(?=The A matrix conforms to the)'
+
+    @property
+    def data(self) -> dict[str, NDArray]:
+        '''
+        Hyperfine data:\n
+        A dictionary with keys:\n
+            nucleus\n
+            element\n
+            isotope\n
+            matrix\n
+            values\n
+            vectors\n
+            iso\n
+            fc\n
+            sd\n
+            orb\n
+            dia\n
+        All values are ndarray of floats and have units of MHz
+        '''
+        return self._data
+
+    @staticmethod
+    def _process_block(block: str) -> dict[str, NDArray]:
+        '''
+        Converts single block into data entries described in self.data
+
+        Parameters
+        ----------
+        block: str
+            String block extracted from file
+
+        Returns
+        -------
+        dict[str, NDArray]
+        '''
+
+        def float_triple(list_str: str) -> list[float]:
+            '''
+            Converts string form of three element list to list of floats
+
+            list_str: str
+                String of three float values separated by spaces
+
+            Returns
+            -------
+            list[float]
+                floats in list
+            '''
+
+            if list_str is None:
+                list_float = []
+            else:
+                list_float = [
+                    float(val)
+                    for val in list_str.split()
+                ]
+
+            return list_float
+
+        # Get Nucleus
+        nucleus = block.split(':')[0].lstrip().rstrip()
+        element = ''.join(
+            [
+                letter
+                for letter in nucleus
+                if letter not in '0123456789'
+            ]
+        )
+
+        isotope = int(re.findall(r'Isotope\=\s+(\d+)', block)[0])
+
+        # Get Matrix
+        _matrix = re.findall(
+            r'(\s-?\d+\.\d{4}\s+-?\d+\.\d{4}\s+-?\d+\.\d{4})',
+            block
+        )[:3]
+
+        _fc = re.findall(
+            r'A\(FC\)\s+(-?\d+.\d{4}\s+-?\d+.\d{4}\s+-?\d+.\d{4})',
+            block
+        )
+        fc = float_triple(_fc[0])
+
+        _sd = re.findall(
+            r'A\(SD\)\s+(-?\d+.\d{4}\s+-?\d+.\d{4}\s+-?\d+.\d{4})',
+            block
+        )
+        sd = float_triple(_sd[0])
+
+        _orb = re.findall(
+            r'A\(ORB\)\s+(-?\d+.\d{4}\s+-?\d+.\d{4}\s+-?\d+.\d{4})',
+            block
+        )
+        orb = float_triple(_orb[0])
+
+        _dia = re.findall(
+            r'A\(DIA\)\s+(-?\d+.\d{4}\s+-?\d+.\d{4}\s+-?\d+.\d{4})',
+            block
+        )
+        dia = float_triple(_dia[0])
+
+        # Convert to matrix of floats
+        matrix = np.asarray([
+            [float(v) for v in val.split()]
+            for val in _matrix
+        ])
+
+        if matrix.shape != (3, 3):
+            raise DataFormattingError(
+                'Hyperfine tensor is not the correct shape (3x3)'
+            )
+
+        # Calculate isotropic hyperfine coupling
+        iso = np.trace(matrix) / 3.
+
+        # Diagonalise tensor
+        vals, vecs = la.eigh(matrix)
+
+        # Future - pseudocontact/dipolar?
+        data = {
+            'nucleus': nucleus,
+            'element': element,
+            'isotope': isotope,
+            'matrix': matrix,
+            'values': vals,
+            'vectors': vecs,
+            'iso': iso,
+            'fc': fc,
+            'sd': sd,
+            'dia': dia,
+            'orb': orb,
+        }
+
+        return data
+
+    @classmethod
+    def extract(cls, file_name: str | pathlib.Path) -> list[dict[str, NDArray]]: # noqa
+        '''
+        Convenience method which instantiates class, extracts blocks, and
+        returns processed datasets
+
+        Parameters
+        ----------
+        file_name: str | pathlib.Path
+            File to parse
+
+        Returns
+        -------
+        list[dict[str, NDArray]]
+            Each entry contains processed data, as defined in cls.data
+        '''
+        _ext = cls()
+        _ext(file_name, process=True)
+        return _ext.data
+
+
 class GMatrixDFTExtractor(extto.BetweenExtractor):
     '''
-    Extracts DFT ELECTRONIC G-MATRIX block from output file
+    Extracts DFT ELECTRONIC G-MATRIX block from Orca output file
     '''
 
     # Regex Start Pattern
@@ -2530,7 +2698,7 @@ class GMatrixDFTExtractor(extto.BetweenExtractor):
 
 class GMatrixExtractor(extto.BetweenExtractor):
     '''
-    Extracts ELECTRONIC G-MATRIX block from output file
+    Extracts ELECTRONIC G-MATRIX block from Orca output file
     '''
 
     # Regex Start Pattern
@@ -2620,8 +2788,8 @@ class GMatrixExtractor(extto.BetweenExtractor):
 
 class GMatrixEffectiveExtractor(GMatrixExtractor):
     '''
-    Extracts ELECTRONIC G-MATRIX FROM EFFECTIVE HAMILTONIAN block from output\n
-     file
+    Extracts ELECTRONIC G-MATRIX FROM EFFECTIVE HAMILTONIAN block from Orca\n
+    output file
     '''
     # Regex Start Pattern
     START_PATTERN = rb'(?<=ELECTRONIC G-MATRIX FROM EFFECTIVE HAMILTONIAN\s[\S\s]{46}\s)' # noqa
@@ -2707,7 +2875,8 @@ class GMatrixEffectiveExtractor(GMatrixExtractor):
 
 class GMatrixLExtractor(GMatrixExtractor):
     '''
-    Extracts ELECTRONIC G-MATRIX: L contribution block from output file
+    Extracts ELECTRONIC G-MATRIX: L contribution block from Orca\n
+    output file
     '''
     # Regex Start Pattern
     START_PATTERN = rb'(?<=ELECTRONIC G-MATRIX: L contribution\s[\S\s]{47}\s)'
@@ -2715,7 +2884,8 @@ class GMatrixLExtractor(GMatrixExtractor):
 
 class GMatrixSExtractor(GMatrixExtractor):
     '''
-    Extracts ELECTRONIC G-MATRIX: S contribution block from output file
+    Extracts ELECTRONIC G-MATRIX: S contribution block from Orca\n
+    output file
     '''
     # Regex Start Pattern
     START_PATTERN = rb'(?<=ELECTRONIC G-MATRIX: S contribution\s[\S\s]{47}\s)'
@@ -2723,7 +2893,7 @@ class GMatrixSExtractor(GMatrixExtractor):
 
 class SpinFreeEnergyExtractor(extto.BetweenExtractor):
     '''
-    Extracts Spin-Free TRANSITION ENERGIES block from output file
+    Extracts Spin-Free TRANSITION ENERGIES block from Orca output file
     '''
 
     # Regex Start Pattern
@@ -2814,7 +2984,7 @@ class SpinFreeEnergyExtractor(extto.BetweenExtractor):
 
 class SpinOrbitEnergyExtractor(extto.BetweenExtractor):
     '''
-    Extracts Spin-Orbit Energies block from output file
+    Extracts Spin-Orbit Energies block from Orca output file
     '''
 
     # Regex Start Pattern

{orto-1.10.0.dist-info → orto-1.11.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: orto
-Version: 1.10.0
+Version: 1.11.0
 Summary: A package to make life easier when performing Orca calculations.
 Home-page: https://orto.kragskow.group
 Author: Jon Kragskow
@@ -14,7 +14,7 @@ Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: numpy>=2.1.2
-Requires-Dist: xyz_py>=5.13.1
+Requires-Dist: xyz_py>=5.19.2
 Requires-Dist: matplotlib>=3.9.2
 Requires-Dist: extto>=1.0.1
 Requires-Dist: pandas>=2.2.3

{orto-1.10.0.dist-info → orto-1.11.0.dist-info}/RECORD

@@ -1,17 +1,17 @@
 orto/__init__.py,sha256=IedlltYr3qYZxChNUdz62qogXA9Pos_MUvXdGXqAa0E,41
-orto/__version__.py,sha256=ZXE8njb1SRoMJuadNA6KRGRdfAFsM49XLsgr_fSOXts,23
-orto/cli.py,sha256=XBeO5dTWaZP_mnNA5IR2eZBcnhHEtwW6IuFtLgUPMkA,86309
+orto/__version__.py,sha256=glAkwZsi0Hbv-R1Jbe-2qECv-6AWHNGvlRS_cgbvCTU,23
+orto/cli.py,sha256=l470BgtTLUD2vtWNdMuoY7A1zcW7lzCGBJO-n1YI9_Q,95935
 orto/constants.py,sha256=anxaiTykO8Q_CXliR7zuOAdnXZrQ2-C4ndaviyl7kGc,419
 orto/data.py,sha256=960LHFeG7l626X_WA-8YxvG2toNAsgNvLo86OoYAmBY,14910
 orto/exceptions.py,sha256=D7oNeAEGeJNt5thzt6PaCn5FY6JcbJOWUE1N1LVhhuE,159
-orto/extractor.py,sha256=oqRdDWLaVPIwB4aZ5nrITWexx60hKn0zghACmymwVfM,80618
+orto/extractor.py,sha256=GKCFU7oSawYCYjOizER8e6HSp4bOsyqOxYcTPQHwdjM,84923
 orto/input.py,sha256=uUQV6A-8D0GZpRoY1rKK_aUPmk9kVVTnMzTHuisP5t4,11888
 orto/job.py,sha256=tDiz9omFwinoYJamgz66MZez0Ee9HMhuCIAeHMhXRF8,5916
 orto/plotter.py,sha256=_t9bow6sUMoRAvD6gVFGJTc-_ifW7RmeR0JAPWK_lm4,17799
 orto/utils.py,sha256=GcMZ9uebOSnkPQT_U5O0X49LUtTu8YpXZxEsNKgXNTY,9838
-orto-1.10.0.dist-info/licenses/LICENSE,sha256=46mU2C5kSwOnkqkw9XQAJlhBL2JAf1_uCD8lVcXyMRg,7652
-orto-1.10.0.dist-info/METADATA,sha256=2qdWW5pyurXxTVD-6GXUSvuxZhLJ2BTbkGUtDdPJVoQ,1185
-orto-1.10.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-orto-1.10.0.dist-info/entry_points.txt,sha256=HXenCglMp_03JkN34pK2phkjXK9CFcXTGHKv5QaVY8I,39
-orto-1.10.0.dist-info/top_level.txt,sha256=hQ-z28gTN_FZ2B5Kiwxr_9cUTcCoib9W5HjbkceDXw4,5
-orto-1.10.0.dist-info/RECORD,,
+orto-1.11.0.dist-info/licenses/LICENSE,sha256=46mU2C5kSwOnkqkw9XQAJlhBL2JAf1_uCD8lVcXyMRg,7652
+orto-1.11.0.dist-info/METADATA,sha256=CrxR7SnLc7EfAUvA26nct7SyVxCtFbwiJVw2oy4jNg0,1185
+orto-1.11.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+orto-1.11.0.dist-info/entry_points.txt,sha256=HXenCglMp_03JkN34pK2phkjXK9CFcXTGHKv5QaVY8I,39
+orto-1.11.0.dist-info/top_level.txt,sha256=hQ-z28gTN_FZ2B5Kiwxr_9cUTcCoib9W5HjbkceDXw4,5
+orto-1.11.0.dist-info/RECORD,,