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
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445 | @dataclass
class OPTIMADEDLiteParseStrategy:
"""Parse strategy for JSON.
**Implements strategies**:
- `("parserType", "parser/OPTIMADE/DLite")`
"""
parse_config: OPTIMADEDLiteParseConfig
def initialize(self) -> DLiteSessionUpdate:
"""Initialize strategy.
This method will be called through the `/initialize` endpoint of the OTE-API
Services.
Returns:
An update model of key/value-pairs to be stored in the session-specific
context from services.
"""
return DLiteSessionUpdate(
collection_id=get_collection(
collection_id=self.parse_config.configuration.collection_id
).uuid
)
def get(self) -> OPTIMADEParseResult:
"""Request and parse an OPTIMADE response using OPT.
This method will be called through the strategy-specific endpoint of the
OTE-API Services.
Configuration values provided in `resource_config.configuration` take
precedence over the derived values from `downloadUrl`.
Workflow:
1. Request OPTIMADE response.
2. Parse as an OPTIMADE Python tools (OPT) pydantic response model.
---
The OPTIMADE Structure needs to be parsed into DLite instances inside-out,
meaning the most nested data structures must first be parsed, and then the ones
1 layer up and so on until the most upper layer can be parsed.
Returns:
An update model of key/value-pairs to be stored in the session-specific
context from services.
"""
generic_parse_config = self.parse_config.model_copy(
update={
"parserType": self.parse_config.parserType.replace("/dlite", ""),
"configuration": self.parse_config.configuration.model_copy(
update={
"mediaType": self.parse_config.configuration.get(
"mediaType", ""
).replace("+dlite", "+json")
}
),
}
).model_dump(exclude_unset=True, exclude_defaults=True)
generic_parse_result = OPTIMADEParseStrategy(generic_parse_config).get()
OPTIMADEStructure = dlite.get_instance(str(self.parse_config.entity))
single_entity = "OPTIMADEStructureResource" in OPTIMADEStructure.uri
if not single_entity:
nested_entity_mapping: dict[str, dlite.Instance] = self._get_nested_entity(
OPTIMADEStructure
)
if not (
generic_parse_result.optimade_response
and generic_parse_result.optimade_response_model
):
base_error_message = (
"Could not retrieve response from OPTIMADE parse strategy."
)
LOGGER.error(
"%s\n"
"optimade_response=%r\n"
"optimade_response_model=%r\n"
"session fields=%r",
base_error_message,
generic_parse_result.get("optimade_response"),
generic_parse_result.get("optimade_response_model"),
list(generic_parse_result),
)
raise OPTIMADEParseError(base_error_message)
optimade_response_model_module, optimade_response_model_name = (
generic_parse_result.optimade_response_model
)
# Parse response using the provided model
try:
optimade_response_model: type[OPTIMADEResponse] = getattr(
importlib.import_module(optimade_response_model_module),
optimade_response_model_name,
)
optimade_response = optimade_response_model(
**generic_parse_result.optimade_response
)
except (ImportError, AttributeError) as exc:
base_error_message = "Could not import the response model."
LOGGER.error(
"%s\n"
"ImportError: %s\n"
"optimade_response_model_module=%r\n"
"optimade_response_model_name=%r",
base_error_message,
exc,
optimade_response_model_module,
optimade_response_model_name,
)
raise OPTIMADEParseError(base_error_message) from exc
except ValidationError as exc:
base_error_message = "Could not validate the response model."
LOGGER.error(
"%s\n"
"ValidationError: %s\n"
"optimade_response_model_module=%r\n"
"optimade_response_model_name=%r",
base_error_message,
exc,
optimade_response_model_module,
optimade_response_model_name,
)
raise OPTIMADEParseError(base_error_message) from exc
# Currently, only "structures" entries are supported and handled
if isinstance(optimade_response, StructureResponseMany):
structures: list[StructureResource] = [
(
StructureResource(**entry)
if isinstance(entry, dict)
else entry.model_copy(deep=True)
)
for entry in optimade_response.data
]
elif isinstance(optimade_response, StructureResponseOne):
structures = (
[
(
StructureResource(**optimade_response.data)
if isinstance(optimade_response.data, dict)
else optimade_response.data.model_copy(deep=True)
)
]
if optimade_response.data is not None
else []
)
elif isinstance(optimade_response, Success):
if isinstance(optimade_response.data, dict):
structures = [StructureResource(**optimade_response.data)]
elif isinstance(optimade_response.data, BaseModel):
structures = [StructureResource(**optimade_response.data.model_dump())]
elif isinstance(optimade_response.data, list):
structures = [
(
StructureResource(**entry)
if isinstance(entry, dict)
else StructureResource(**entry.model_dump())
)
for entry in optimade_response.data
]
elif optimade_response.data is None:
structures = []
else:
LOGGER.error(
"Could not determine what to do with `data`. Type %s.",
type(optimade_response.data),
)
raise OPTIMADEParseError("Could not parse `data` entry in response.")
else:
LOGGER.error(
"Got currently unsupported response type %s. Only structures are "
"supported.",
optimade_response_model_name,
)
raise OPTIMADEParseError(
"The DLite OPTIMADE Parser currently only supports structures entities."
)
if not structures:
LOGGER.warning("No structures found in the response.")
return generic_parse_result
# DLite-fy OPTIMADE structures
dlite_collection = get_collection(
collection_id=self.parse_config.configuration.collection_id
)
for structure in structures:
new_structure_attributes: dict[str, Any] = {}
single_entity_dimensions: dict[str, int] = {
"nassemblies": 0,
"nspecies": 0,
}
## For OPTIMADEStructure (multiple) entities
# Most inner layer: assemblies & species
if structure.attributes.assemblies:
if single_entity:
single_entity_dimensions["nassemblies"] = len(
structure.attributes.assemblies
)
new_structure_attributes.update(
{
"assemblies_sites_in_groups": [],
"assemblies_group_probabilities": [],
}
)
else:
new_structure_attributes["assemblies"] = []
for assembly in structure.attributes.assemblies:
if single_entity:
new_structure_attributes["assemblies_sites_in_groups"].append(
";".join(
[
",".join(str(_) for _ in group)
for group in assembly.sites_in_groups
]
)
)
new_structure_attributes[
"assemblies_group_probabilities"
].append(",".join(str(_) for _ in assembly.group_probabilities))
else:
if "attributes.assemblies" not in nested_entity_mapping:
LOGGER.error(
"Could not find entity for 'attributes.assemblies'.\nnested_entity_mapping=%r",
nested_entity_mapping,
)
raise OPTIMADEParseError(
"Could not find entity for 'attributes.assemblies'."
)
dimensions = {
"ngroups": len(assembly.group_probabilities),
"nsites": len(assembly.sites_in_groups),
}
new_structure_attributes["assemblies"].append(
nested_entity_mapping["attributes.assemblies"](
dimensions=dimensions, properties=assembly.model_dump()
)
)
if structure.attributes.species:
if single_entity:
single_entity_dimensions["nspecies"] = len(
structure.attributes.species
)
new_structure_attributes.update(
{
"species_name": [],
"species_chemical_symbols": [],
"species_concentration": [],
"species_mass": [],
"species_original_name": [],
"species_attached": [],
"species_nattached": [],
}
)
else:
new_structure_attributes["species"] = []
for species in structure.attributes.species:
if single_entity:
new_structure_attributes["species_name"].append(species.name)
new_structure_attributes["species_chemical_symbols"].append(
",".join(species.chemical_symbols)
)
new_structure_attributes["species_concentration"].append(
",".join(str(_) for _ in species.concentration)
)
new_structure_attributes["species_mass"].append(
",".join(str(_) for _ in (species.mass or []))
)
new_structure_attributes["species_original_name"].append(
species.original_name or ""
)
new_structure_attributes["species_attached"].append(
",".join(species.attached or [])
)
new_structure_attributes["species_nattached"].append(
",".join(str(_) for _ in (species.nattached or []))
)
else:
if "attributes.species" not in nested_entity_mapping:
LOGGER.error(
"Could not find entity for 'attributes.species'.\nnested_entity_mapping=%r",
nested_entity_mapping,
)
raise OPTIMADEParseError(
"Could not find entity for 'attributes.species'."
)
dimensions = {
"nelements": len(species.chemical_symbols),
"nattached_elements": len(species.attached or []),
}
new_structure_attributes["species"].append(
nested_entity_mapping["attributes.species"](
dimensions=dimensions,
properties=species.model_dump(exclude_none=True),
)
)
# Attributes
new_structure_attributes.update(
structure.attributes.model_dump(
exclude={
"species",
"assemblies",
"nelements",
"nsites",
"structure_features",
},
exclude_unset=True,
exclude_defaults=True,
exclude_none=True,
)
)
for key in list(new_structure_attributes):
if key.startswith("_"):
new_structure_attributes.pop(key)
# Structure features values are Enum values, so we need to convert them to
# their string (true) values
new_structure_attributes["structure_features"] = [
_.value for _ in structure.attributes.structure_features
]
if single_entity:
new_structure_attributes["id"] = structure.id
new_structure_attributes["type"] = structure.type
new_structure = OPTIMADEStructure(
dimensions={
"nelements": structure.attributes.nelements or 0,
"dimensionality": 3,
"nsites": structure.attributes.nsites or 0,
"nstructure_features": len(
structure.attributes.structure_features
),
**single_entity_dimensions,
},
properties=new_structure_attributes,
)
else:
if "attributes" not in nested_entity_mapping:
LOGGER.error(
"Could not find entity for 'attributes'.\nnested_entity_mapping=%r",
nested_entity_mapping,
)
raise OPTIMADEParseError("Could not find entity for 'attributes'.")
new_structure = OPTIMADEStructure(
dimensions={},
properties={
"attributes": nested_entity_mapping["attributes"](
dimensions={
"nelements": structure.attributes.nelements or 0,
"dimensionality": 3,
"nsites": structure.attributes.nsites or 0,
"nspecies": (
len(structure.attributes.species)
if structure.attributes.species
else 0
),
"nstructure_features": len(
structure.attributes.structure_features
),
},
properties=new_structure_attributes,
),
"type": structure.type,
"id": structure.id,
},
)
dlite_collection.add(label=structure.id, inst=new_structure)
update_collection(collection=dlite_collection)
return generic_parse_result
def _get_nested_entity(self, entity: dlite.Instance) -> dict[str, dlite.Instance]:
"""Get nested entity from DLite instance."""
nested_entities: dict[str, dlite.Instance] = {}
for prop in entity.properties["properties"]:
if prop.type == "ref":
nested_entities[prop.name] = dlite.get_instance(prop.ref)
for name, nested_entity in tuple(nested_entities.items()):
futher_nested_entities = self._get_nested_entity(nested_entity)
for nested_name, further_nested_entity in futher_nested_entities.items():
nested_entities[f"{name}.{nested_name}"] = further_nested_entity
return nested_entities
|