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
235
236
237
|
"""Module to define various calculation types as Enums for VASP."""
from __future__ import annotations
from importlib.resources import files as import_resource_files
from itertools import product
from ruamel.yaml import YAML
_BASE_ENUM_PATH = {
"vasp": import_resource_files("emmet.core.vasp"),
"qchem": import_resource_files("emmet.core.qchem"),
}
for code_base in _BASE_ENUM_PATH:
_BASE_ENUM_PATH[code_base] /= "calc_types"
def get_enum_source(
enum_name: str, doc: str, members: dict, enum_class: str = "ValueEnum"
) -> str:
"""Write python-format enum from a dict of members and metadata.
Parameters
-----------
enum_name : str
Name of the enum.
doc : str
Enum docstr
members : dict
The key-value pair indexed members of the enum.
enum_class : str = "ValueEnum"
The name of the enum class.
Returns
--------
str
"""
items = [f"class {enum_name}({enum_class}):", f' """ {doc} """\n']
items += [f' {const} = "{val}"' for const, val in members.items()]
return "\n".join(items)
def string_bulk_replace(string: str, rules: dict[str, str]) -> str:
"""Perform multiple string replacements subject to a set of rules.
Parameters
-----------
string : str
input string
rules : dict[str,str]
A dict of string replacements, with the characters to replace
as keys, and their replacements as values.
Returns
--------
str
"""
for targ_char, rep_char in rules.items():
string = string.replace(targ_char, rep_char)
return string
def generate_vasp_enums_file(enum_file_name: str | None = None) -> None:
"""
Generate VASP enum members from reference yaml data.
Parameters
-----------
enum_file_name : str
Name of the file to write the enums to.
Defaults to _BASE_ENUM_PATH / vasp_enums.json.gz
"""
with open(_BASE_ENUM_PATH["vasp"] / "calc_types.yaml", "r") as config:
_RUN_TASK_TYPE_DATA = YAML().load(config)
_TASK_TYPES = _RUN_TASK_TYPE_DATA.get("TASK_TYPES")
_RUN_TYPES = set(
rt
for functionals in _RUN_TASK_TYPE_DATA.get("RUN_TYPES", {}).values()
for rt in functionals
)
_RUN_TYPES.update(set(f"{rt}+U" for rt in _RUN_TYPES))
_ENUMS = {
"RunType": {
"_".join(rt.split()).replace("+", "_").replace("-", "_"): rt
for rt in _RUN_TYPES
},
"TaskType": {"_".join(tt.split()): tt for tt in _TASK_TYPES},
"CalcType": {
f"{'_'.join(rt.split()).replace('+','_').replace('-','_')}"
f"_{'_'.join(tt.split())}": f"{rt} {tt}"
for rt, tt in product(_RUN_TYPES, _TASK_TYPES)
},
}
docstr = {}
for enum_name in _ENUMS:
rtc_type = enum_name.split("Calc")[-1].split("Type")[0].lower()
if len(rtc_type) > 0:
rtc_type += " "
docstr[enum_name] = f"VASP calculation {rtc_type}types."
enum_file_name = enum_file_name or str(_BASE_ENUM_PATH["vasp"] / "enums.py")
with open(enum_file_name, "w+") as f:
f.write(
"""\"\"\"
Autogenerated Enums for VASP RunType, TaskType, and CalcType.
Do not edit this by hand to add or remove enums.
Instead, edit
dev_scripts/generate_enums.py
and/or
emmet/core/vasp/calc_types/calc_types.yaml
\"\"\"
from emmet.core.utils import ValueEnum, IgnoreCaseEnum
"""
)
enum_order = (
"RunType",
"TaskType",
"CalcType",
)
for ienum, enum_name in enumerate(enum_order):
sorted_enums = {k: _ENUMS[enum_name][k] for k in sorted(_ENUMS[enum_name])}
f.write(
get_enum_source(
enum_name,
docstr[enum_name],
sorted_enums,
enum_class=(
"IgnoreCase"
if enum_name in ["RunType", "CalcType"]
else "Value"
)
+ "Enum",
)
)
f.write("\n\n" if ienum < (len(enum_order) - 1) else "\n")
def generate_qchem_enum_file(enum_file_name: str | None = None) -> None:
"""
Generate QChem enum members from reference yaml data.
Original author, Evan Spotte-Smith <ewcspottesmith@lbl.gov>
Parameters
-----------
enum_file_name : str
Name of the file to write the enums to.
Defaults to _BASE_ENUM_PATH / qchem_enums.json.gz
"""
with open(_BASE_ENUM_PATH["qchem"] / "calc_types.yaml", "r") as config:
_calc_type_meta = YAML().load(config)
_calc_type_meta["FUNCTIONALS"] = [
rt
for functionals in _calc_type_meta["FUNCTIONAL_CLASSES"].values()
for rt in functionals
]
_LOTS = list()
for funct in _calc_type_meta["FUNCTIONALS"]:
for basis in _calc_type_meta["BASIS_SETS"]:
for solv_model in _calc_type_meta["SOLVENT_MODELS"]:
_LOTS.append(f"{funct}/{basis}/{solv_model}")
_lot_str_replacements = {
"+": "_",
"-": "_",
"(": "_",
")": "_",
"/": "_",
"*": "_d",
}
_ENUMS = {
"LevelOfTheory": {
"_".join(string_bulk_replace(lot, _lot_str_replacements).split()): lot
for lot in _LOTS
},
"TaskType": {
"_".join(tt.split()).replace("-", "_"): tt
for tt in _calc_type_meta["TASK_TYPES"]
},
"CalcType": {
(
"_".join(string_bulk_replace(lot, _lot_str_replacements).split())
+ f"_{'_'.join(tt.split()).replace('-', '_')}"
): f"{lot} {tt}"
for lot, tt in product(_LOTS, _calc_type_meta["TASK_TYPES"])
},
}
docstr = {
"LevelOfTheory": "Levels of theory for calculations in Q-Chem.",
"TaskType": "Calculation task types for Q-Chem.",
"CalcType": "Calculation types (LOT + task type) for Q-Chem.",
}
enum_file_name = enum_file_name or str(_BASE_ENUM_PATH["qchem"] / "enums.py")
with open(enum_file_name, "w+") as f:
f.write(
"""\"\"\"
Autogenerated Enums for Q-Chem LevelOfTheory, TaskType, and CalcType.
Do not edit this by hand to add or remove enums.
Instead, edit
dev_scripts/generate_enums.py
and/or
emmet/core/qchem/calc_types/calc_types.yaml
\"\"\"
from emmet.core.utils import ValueEnum
"""
)
enum_order = (
"LevelOfTheory",
"TaskType",
"CalcType",
)
for ienum, enum_name in enumerate(enum_order):
sorted_enums = {k: _ENUMS[enum_name][k] for k in sorted(_ENUMS[enum_name])}
f.write(get_enum_source(enum_name, docstr[enum_name], sorted_enums))
f.write("\n\n" if ienum < (len(enum_order) - 1) else "\n")
if __name__ == "__main__":
generate_vasp_enums_file()
generate_qchem_enum_file()
|
