1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
|
#! /usr/bin/env python3
#
# Copyright 2009-2024 The VOTCA Development Team (http://www.votca.org)
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
import argparse
import os
import sys
import time
from pathlib import Path
import lxml.etree as lxml
VERSION = '@PROJECT_VERSION@ #VOTCA_GIT_ID#'
PROGTITLE = 'THE VOTCA::XTP converter basissetfiles'
PROGDESCR = 'Creates votca xml basissetfiles from NWCHEM basissetfiles'
VOTCAHEADER = f"""
==================================================
======== VOTCA (http://www.votca.org) ========
==================================================
{PROGTITLE}
please read and cite: @PROJECT_CITATION@
and submit bugs to @PROJECT_CONTACT@
xtp_basisset, version {VERSION}
"""
def okquit(what: str):
"""Exit gracefully."""
print(what)
sys.exit(0)
def exists(input_file: str) -> Path:
"""Check if the input file exists."""
path = Path(input_file)
if not path.exists():
raise argparse.ArgumentTypeError(f"{input_file} doesn't exist!")
return path
# =============================================================================
# PROGRAM OPTIONS
# =============================================================================
class XtpHelpFormatter(argparse.HelpFormatter):
def _format_usage(self, usage, action, group, prefix):
return VOTCAHEADER
progargs = argparse.ArgumentParser(prog='xtp_basisset',
formatter_class=lambda prog: XtpHelpFormatter(
prog, max_help_position=70),
description=PROGDESCR)
progargs.add_argument('-f', '--input',
dest='input',
required=True,
type=exists,
help='NWchem file containing the basisset or Turbomole folder with element names.')
progargs.add_argument('-o', '--outputvotca',
dest='outputfile',
required=True,
help='Path of votca outputfile')
progargs.add_argument('-t', '--turbomolebasisset',
dest='turbobasis',
default=None,
help='For turbomole specify the basisset that is supposed to be extracted from Files, for auxbasis sets the basisset the aux basisset is supposed to be used for.')
OPTIONS = progargs.parse_args()
def getelemententry(root, element):
for e in root:
# print e.get("name")
if e.get("name") == element:
return e
return lxml.SubElement(root, "element", name=element)
def convertofloat(floatstring: str) -> float:
if "D" in floatstring:
floatstring = floatstring.replace("D", "E")
try:
return float(floatstring)
except ValueError:
print(f"Cannot figure out what '{floatstring}' means")
raise
def turbomolegetcontributions(element, lines, basissetstringlist, basis, shells) -> None:
newbasissets = []
start = False
basissetfound = False
for line in lines:
if line[0] == "#":
continue
elif line in ["\n", "\r\n"]:
continue
elif "$end" in line:
continue
if line[0] == "*" and basissetfound:
# print start
if start:
# print "Breaking"
break
else:
start = True
continue
if line.split()[0] == element:
if line.split()[-1] in basissetstringlist and basissetfound == False:
basissetfound = True
continue
if start and basissetfound:
if "->" in line:
newbasissets.append(line.split()[-1])
continue
entries = line.split()
if len(entries) == 2:
if entries[-1].upper() in shells:
shelltype = entries[-1].upper()
shell = lxml.SubElement(
basis, "shell", type=shelltype, scale="1.0")
else:
constant = lxml.SubElement(
shell, "constant", decay="{:1.6e}".format(convertofloat(entries[0])))
contraction = lxml.SubElement(
constant, "contractions", type=shelltype, factor="{:1.6e}".format(convertofloat(entries[1])))
# contraction.text=" "
else:
print(f"Cannot figure out what line '{line}' means")
sys.exit()
if len(newbasissets) > 0:
turbomolegetcontributions(element, lines, newbasissets, basis, shells)
# =============================================================================
# PARSING NWCHEM FILE
# =============================================================================
basissetname = OPTIONS.input.stem
basis = lxml.Element("basis", name=basissetname)
basis.append(lxml.Comment(
f"Basis set created by xtp_basisset from {OPTIONS.input.name} at {time.strftime('%c')}"))
elements = ['H', 'He', 'Li', 'Be', 'B', 'C', 'N', 'O', 'F', 'Ne', 'Na', 'Mg', 'Al', 'Si', 'P', 'S', 'Cl', 'K', 'Ar', 'Ca', 'Sc', 'Ti', 'V', 'Cr', 'Mn', 'Fe', 'Ni', 'Co', 'Cu', 'Zn', 'Ga', 'Ge', 'As', 'Se', 'Br', 'Kr', 'Rb', 'Sr', 'Y', 'Zr', 'Nb', 'Mo', 'Tc', 'Ru', 'Rh', 'Pd', 'Ag', 'Cd', 'In', 'Sn', 'Sb', 'I', 'Te', 'Xe', 'Cs', 'Ba', 'La', 'Ce', 'Pr',
'Nd', 'Pm', 'Sm', 'Eu', 'Gd', 'Tb', 'Dy', 'Ho', 'Er', 'Tm', 'Yb', 'Lu', 'Hf', 'Ta', 'W', 'Re', 'Os', 'Pt', 'Ir', 'Au', 'Hg', 'Tl', 'Pb', 'Bi', 'Po', 'At', 'Rn', 'Fr', 'Ra', 'Ac', 'Pa', 'Th', 'Np', 'U', 'Am', 'Pu', 'Bk', 'Cm', 'Cf', 'Es', 'Fm', 'Md', 'No', 'Rf', 'Lr', 'Db', 'Bh', 'Sg', 'Mt', 'Ds', 'Rg', 'Hs', 'Uut', 'Uub', 'Uup', 'Uuq', 'Uuh', 'Uuo']
shells = ["S", "P", "D", "F", "G", "H", "I"]
if OPTIONS.input.is_file():
print(f"File {OPTIONS.input} seems to be a NWCHEM file")
keywords = ["BASIS", "end", "basis", "END"]
with open(OPTIONS.input, 'r') as f:
for line in f.readlines():
if line[0] == "#":
continue
elif line in ["\n", "\r\n"]:
element = None
continue
entries = line.split()
if entries[0] in keywords:
element = None
continue
elif entries[0] in elements:
element = getelemententry(basis, entries[0])
shelltype = entries[1]
shell = lxml.SubElement(
element, "shell", type=shelltype, scale="1.0")
elif len(entries) > 1 and shell is not None:
constant = lxml.SubElement(
shell, "constant", decay="{:1.6e}".format(convertofloat(entries[0])))
for contractionfactor, singleshell in zip(entries[1:], shelltype):
contraction = lxml.SubElement(constant, "contractions", type=singleshell, factor="{:1.6e}".format(
convertofloat(contractionfactor)))
# contraction.text=" "
else:
okquit("\nCannot understand line in file:{}".format(line))
elif OPTIONS.input.is_dir():
print(
f"Directory {OPTIONS.input.as_posix()} seems to be a Turbomole folder")
if OPTIONS.turbobasis is None:
progargs.print_help()
okquit(
"\nQuit here, because: Turbomole basisset not set (option -t/--turbomolebasisset)")
for ele in elements:
if os.path.isfile(ele.lower()):
print(f"Opening {ele.lower()}")
with open(ele.lower(), 'r') as f:
lines = f.readlines()
element = getelemententry(basis, ele)
turbomolegetcontributions(
ele.lower(), lines, OPTIONS.turbobasis, element, shells)
else:
print(
f"File {ele.lower()} belonging to {element} not found. Skipping element!")
print(
f"Imported new basisset {basissetname} from {OPTIONS.input.as_posix()} written to file {OPTIONS.outputfile} with xtp_basisset")
with open(OPTIONS.outputfile, 'wb') as f:
f.write(lxml.tostring(basis, pretty_print=True))
|
