cognite-neat 0.87.4__py3-none-any.whl → 0.88.0__py3-none-any.whl

cognite/neat/legacy/graph/loaders/core/labels.py

@@ -1,58 +0,0 @@
-import logging
-import traceback
-from typing import cast
-
-from cognite.client import CogniteClient
-from cognite.client.data_classes import LabelDefinition, LabelDefinitionList
-
-from cognite.neat.legacy.rules.exporters._core import get_labels
-from cognite.neat.legacy.rules.models.rules import Rules
-
-
-def upload_labels(
-    client: CogniteClient,
-    rules: Rules,
-    data_set_id: int,
-    extra_labels: list | None = None,
-    stop_on_exception: bool = False,
-):
-    """Generates labels from transformation rules and upload them to CDF
-
-    Args:
-        client : Instance of CogniteClient
-        transformation_rules : Instance of TransformationRules which contains the labels to upload
-        data_set_id : Id of the dataset to upload the labels to
-        extra_labels : Any additional labels not defined in TransformationRules ,
-                       by default ["historic", "non-historic"]
-        stop_on_exception : If this function fails to stop the process, by default False
-    """
-    if extra_labels is None:
-        extra_labels = []
-
-    try:
-        logging.debug("Fetching existing labels from CDF")
-        # This is to list all labels, not just the ones in the dataset since labels
-        # must have unique external_ids, fixing issue that Daniel encountered
-        if retrieved_labels := client.labels.list(limit=-1):
-            existing_labels = set(retrieved_labels.to_pandas().external_id)
-        else:
-            existing_labels = set()
-        logging.debug(f"Found {len(existing_labels)} existing labels in CDF")
-    except Exception as e:
-        logging.debug("Error fetching existing labels from CDF, no ")
-        traceback.print_exc()
-        if stop_on_exception:
-            raise e
-        existing_labels = set()
-
-    non_existing_labels = set(list(get_labels(rules)) + extra_labels).difference(existing_labels)
-
-    if non_existing_labels:
-        logging.debug(f"Creating total of {len(existing_labels)} new labels in CDF")
-        labels = [
-            LabelDefinition(external_id=label, name=label, data_set_id=data_set_id) for label in non_existing_labels
-        ]
-        res = cast(LabelDefinitionList, client.labels.create(labels))
-        logging.debug(f"Created total of {len(res)} new labels in CDF")
-    else:
-        logging.debug("No new labels created in CDF")

cognite/neat/legacy/graph/loaders/core/models.py

@@ -1,136 +0,0 @@
-from __future__ import annotations
-
-import logging
-from typing import ClassVar
-
-from pydantic import BaseModel, ConfigDict, root_validator, validator
-from rdflib import Namespace
-
-from cognite.neat.legacy.rules.models.rules import METADATA_VALUE_MAX_LENGTH
-
-
-class AssetClassMapping(BaseModel):
-    external_id: str
-    name: str
-    parent_external_id: str | None = None
-    description: str | None = None
-    metadata: dict | None = {}
-
-    @root_validator(pre=True)
-    def create_metadata(cls, values: dict):
-        fields = values.keys()
-
-        # adding metadata key in case if it is missing
-        values["metadata"] = {} if "metadata" not in values else values["metadata"]
-
-        for field in fields:
-            if field not in ["external_id", "name", "parent_external_id", "data_set_id", "metadata", "description"]:
-                values["metadata"][field] = ""
-        return values
-
-
-class AssetTemplate(BaseModel):
-    """This class is used to validate, repair and wrangle rdf asset dictionary according to the
-    expected format of cognite sdk Asset dataclass."""
-
-    external_id_prefix: str | None = None  # convenience field to add prefix to external_ids
-    external_id: str
-    name: str | None = None
-    parent_external_id: str | None = None
-    metadata: dict | None = {}
-    description: str | None = None
-    data_set_id: int | None = None
-
-    @root_validator(pre=True)
-    def preprocess_fields(cls, values: dict):
-        fields = values.keys()
-
-        # Adding metadata key in case if it is missing
-        values["metadata"] = {} if "metadata" not in values else values["metadata"]
-
-        for field in fields:
-            # Enrich: adding any field that is not in the list of expected fields to metadata
-            if field not in [
-                "external_id",
-                "name",
-                "parent_external_id",
-                "data_set_id",
-                "metadata",
-                "description",
-                "external_id_prefix",
-            ]:
-                values["metadata"][field] = values[field]
-
-            # Repair: in case if name/description is list instead of single value list elements are joined
-            elif field in ["name", "description"] and isinstance(values[field], list):
-                msg = f"{values['type']} instance {values['identifier']} property {field} "
-                msg += f"has multiple values {values[field]}, "
-                msg += f"these values will be joined in a single string: {', '.join(values[field])}"
-                logging.info(msg)
-                values[field] = ", ".join(sorted(values[field]))[: METADATA_VALUE_MAX_LENGTH - 1]
-
-            # Repair: in case if external_id or parent_external_id are lists, we take the first value
-            elif field in ["external_id", "parent_external_id"] and isinstance(values[field], list):
-                msg = f"{values['type']} instance {values['identifier']} property {field} "
-                msg += f"has multiple values {values[field]}, "
-                msg += f"only the first one will be used: {values[field][0]}"
-                logging.info(msg)
-                values[field] = values[field][0]
-
-        # Setting asset to be by default active
-        values["metadata"]["active"] = "true"
-
-        # Handling case when the external_id is not provided by defaulting to the original identifier
-        # The original identifier probably has its namespace removed
-        if "external_id" not in fields and "identifier" in fields:
-            values["external_id"] = values["identifier"]
-
-        return values
-
-    @validator("metadata")
-    def to_list_if_comma(cls, value):
-        for key, v in value.items():
-            if isinstance(v, list):
-                value[key] = ", ".join(sorted(v))[: METADATA_VALUE_MAX_LENGTH - 1]
-        return value
-
-    @validator("metadata")
-    def to_str(cls, value):
-        for key, v in value.items():
-            value[key] = str(v)
-        return value
-
-    @validator("external_id", always=True)
-    def add_prefix_to_external_id(cls, value, values):
-        if values["external_id_prefix"]:
-            return values["external_id_prefix"] + value
-        else:
-            return value
-
-    @validator("parent_external_id")
-    def add_prefix_to_parent_external_id(cls, value, values):
-        if values["external_id_prefix"]:
-            return values["external_id_prefix"] + value
-        else:
-            return value
-
-
-class RelationshipDefinition(BaseModel):
-    source_class: str
-    target_class: str
-    property_: str
-    labels: list[str] | None = None
-    target_type: str = "Asset"
-    source_type: str = "Asset"
-    relationship_external_id_rule: str | None = None
-
-
-class RelationshipDefinitions(BaseModel):
-    model_config: ClassVar[ConfigDict] = ConfigDict(
-        populate_by_name=True, str_strip_whitespace=True, arbitrary_types_allowed=True, strict=False
-    )
-
-    data_set_id: int
-    prefix: str
-    namespace: Namespace
-    relationships: dict[str, RelationshipDefinition]