from collections.abc import Hashable
from dataclasses import dataclass, field
from datetime import datetime
from typing import (
    Any,
    Dict,
    FrozenSet,
    Iterator,
    List,
    Optional,
    Set,
    Tuple,
    Type,
    TypeVar,
    Union,
)

from dbt_common.exceptions import CompilationError, DbtRuntimeError
from dbt_common.utils import deep_merge, filter_null_values

from dbt.adapters.contracts.relation import (
    ComponentName,
    HasQuoting,
    FakeAPIObject,
    Path,
    Policy,
    RelationConfig,
    RelationType,
)
from dbt.adapters.relation_configs import (
    RelationConfigBase,
    RelationConfigValidationMixin,
    RelationConfigValidationRule,
)
from dbt.adapters.exceptions import (
    ApproximateMatchError,
    MultipleDatabasesNotAllowedError,
)
from dbt.adapters.utils import classproperty


Self = TypeVar("Self", bound="BaseRelation")
SerializableIterable = Union[Tuple, FrozenSet]


@dataclass
class EventTimeFilter(FakeAPIObject):
    field_name: str
    start: Optional[datetime] = None
    end: Optional[datetime] = None


@dataclass(frozen=True, eq=False, repr=False)
class FunctionConfig(RelationConfigBase, RelationConfigValidationMixin):
    language: str
    type: str
    runtime_version: Optional[str] = None
    entry_point: Optional[str] = None

    def _validate_runtime_version(self) -> bool:
        if self.language == "python":
            return self.runtime_version is not None
        else:
            return True

    def _validate_entry_point(self) -> bool:
        if self.language == "python":
            return self.entry_point is not None
        else:
            return True

    @property
    def validation_rules(self) -> Set[RelationConfigValidationRule]:
        return {
            RelationConfigValidationRule(
                validation_check=self.language != "" and self.language is not None,
                validation_error=DbtRuntimeError("A `language` is required for functions"),
            ),
            RelationConfigValidationRule(
                validation_check=self.type != "" and self.type is not None,
                validation_error=DbtRuntimeError("A `type` is required for functions"),
            ),
            RelationConfigValidationRule(
                validation_check=self.language != "python" or self.runtime_version is not None,
                validation_error=DbtRuntimeError(
                    "A `runtime_version` is required for python functions"
                ),
            ),
            RelationConfigValidationRule(
                validation_check=self.language != "python" or self.entry_point is not None,
                validation_error=DbtRuntimeError(
                    "An `entry_point` is required for python functions"
                ),
            ),
        }


@dataclass(frozen=True, eq=False, repr=False)
class BaseRelation(FakeAPIObject, Hashable):
    path: Path
    type: Optional[RelationType] = None
    quote_character: str = '"'
    # Python 3.11 requires that these use default_factory instead of simple default
    # ValueError: mutable default <class 'dbt.contracts.relation.Policy'> for field include_policy is not allowed: use default_factory
    include_policy: Policy = field(default_factory=lambda: Policy())
    quote_policy: Policy = field(default_factory=lambda: Policy())
    dbt_created: bool = False
    limit: Optional[int] = None
    event_time_filter: Optional[EventTimeFilter] = None
    require_alias: bool = (
        True  # used to govern whether to add an alias when render_limited is called
    )
    catalog: Optional[str] = None

    # register relation types that can be renamed for the purpose of replacing relations using stages and backups
    # adding a relation type here also requires defining the associated rename macro
    # e.g. adding RelationType.View in dbt-postgres requires that you define:
    # include/postgres/macros/relations/view/rename.sql::postgres__get_rename_view_sql()
    renameable_relations: SerializableIterable = field(default_factory=frozenset)

    # register relation types that are atomically replaceable, e.g. they have "create or replace" syntax
    # adding a relation type here also requires defining the associated replace macro
    # e.g. adding RelationType.View in dbt-postgres requires that you define:
    # include/postgres/macros/relations/view/replace.sql::postgres__get_replace_view_sql()
    replaceable_relations: SerializableIterable = field(default_factory=frozenset)

    def _is_exactish_match(self, field: ComponentName, value: str) -> bool:
        if self.dbt_created and self.quote_policy.get_part(field) is False:
            return self.path.get_lowered_part(field) == value.lower()
        else:
            return self.path.get_part(field) == value

    @classmethod
    def _get_field_named(cls, field_name):
        for f, _ in cls._get_fields():
            if f.name == field_name:
                return f
        # this should be unreachable
        raise ValueError(f"BaseRelation has no {field_name} field!")

    def __eq__(self, other):
        if not isinstance(other, self.__class__):
            return False
        return self.to_dict(omit_none=True) == other.to_dict(omit_none=True)

    @classmethod
    def get_default_quote_policy(cls) -> Policy:
        return cls._get_field_named("quote_policy").default_factory()

    @classmethod
    def get_default_include_policy(cls) -> Policy:
        return cls._get_field_named("include_policy").default_factory()

    def get(self, key, default=None):
        """Override `.get` to return a metadata object so we don't break
        dbt_utils.
        """
        if key == "metadata":
            return {"type": self.__class__.__name__}
        return super().get(key, default)

    def matches(
        self,
        database: Optional[str] = None,
        schema: Optional[str] = None,
        identifier: Optional[str] = None,
    ) -> bool:
        search = filter_null_values(
            {
                ComponentName.Database: database,
                ComponentName.Schema: schema,
                ComponentName.Identifier: identifier,
            }
        )

        if not search:
            # nothing was passed in
            raise DbtRuntimeError("Tried to match relation, but no search path was passed!")

        exact_match = True
        approximate_match = True

        for k, v in search.items():
            if not self._is_exactish_match(k, v):
                exact_match = False
            if str(self.path.get_lowered_part(k)).strip(self.quote_character) != v.lower().strip(
                self.quote_character
            ):
                approximate_match = False

        if approximate_match and not exact_match:
            target = self.create(database=database, schema=schema, identifier=identifier)
            raise ApproximateMatchError(target, self)

        return exact_match

    def replace_path(self, **kwargs):
        return self.replace(path=self.path.replace(**kwargs))

    def quote(
        self: Self,
        database: Optional[bool] = None,
        schema: Optional[bool] = None,
        identifier: Optional[bool] = None,
    ) -> Self:
        policy = filter_null_values(
            {
                ComponentName.Database: database,
                ComponentName.Schema: schema,
                ComponentName.Identifier: identifier,
            }
        )

        new_quote_policy = self.quote_policy.replace_dict(policy)
        return self.replace(quote_policy=new_quote_policy)

    def include(
        self: Self,
        database: Optional[bool] = None,
        schema: Optional[bool] = None,
        identifier: Optional[bool] = None,
    ) -> Self:
        policy = filter_null_values(
            {
                ComponentName.Database: database,
                ComponentName.Schema: schema,
                ComponentName.Identifier: identifier,
            }
        )

        new_include_policy = self.include_policy.replace_dict(policy)
        return self.replace(include_policy=new_include_policy)

    def information_schema(self, view_name=None) -> "InformationSchema":
        # some of our data comes from jinja, where things can be `Undefined`.
        if not isinstance(view_name, str):
            view_name = None

        # Kick the user-supplied schema out of the information schema relation
        # Instead address this as <database>.information_schema by default
        info_schema = InformationSchema.from_relation(self, view_name)
        return info_schema.incorporate(path={"schema": None})

    def information_schema_only(self) -> "InformationSchema":
        return self.information_schema()

    def without_identifier(self) -> "BaseRelation":
        """Return a form of this relation that only has the database and schema
        set to included. To get the appropriately-quoted form the schema out of
        the result (for use as part of a query), use `.render()`. To get the
        raw database or schema name, use `.database` or `.schema`.

        The hash of the returned object is the result of render().
        """
        return self.include(identifier=False).replace_path(identifier=None)

    def _render_iterator(
        self,
    ) -> Iterator[Tuple[Optional[ComponentName], Optional[str]]]:
        for key in ComponentName:  # type: ignore
            path_part: Optional[str] = None
            if self.include_policy.get_part(key):
                path_part = self.path.get_part(key)
                if path_part is not None and self.quote_policy.get_part(key):
                    path_part = self.quoted(path_part)
            yield key, path_part

    def render(self) -> str:
        # if there is nothing set, this will return the empty string.
        return ".".join(part for _, part in self._render_iterator() if part is not None)

    def _render_subquery_alias(self, namespace: str) -> str:
        """Some databases require an alias for subqueries (postgres, mysql) for all others we want to avoid adding
        an alias as it has the potential to introduce issues with the query if the user also defines an alias.
        """
        if self.require_alias:
            return f" _dbt_{namespace}_subq_{self.table}"
        return ""

    def _render_limited_alias(
        self,
    ) -> str:
        return self._render_subquery_alias(namespace="limit")

    def render_limited(self) -> str:
        rendered = self.render()
        if self.limit is None:
            return rendered
        elif self.limit == 0:
            return f"(select * from {rendered} where false limit 0){self._render_limited_alias()}"
        else:
            return f"(select * from {rendered} limit {self.limit}){self._render_limited_alias()}"

    def render_event_time_filtered(self, rendered: Optional[str] = None) -> str:
        rendered = rendered or self.render()
        if self.event_time_filter is None:
            return rendered

        filter = self._render_event_time_filtered(self.event_time_filter)
        if not filter:
            return rendered

        return f"(select * from {rendered} where {filter}){self._render_subquery_alias(namespace='et_filter')}"

    def _render_event_time_filtered(self, event_time_filter: EventTimeFilter) -> str:
        """
        Returns "" if start and end are both None
        """
        filter = ""
        if event_time_filter.start and event_time_filter.end:
            filter = f"{event_time_filter.field_name} >= '{event_time_filter.start}' and {event_time_filter.field_name} < '{event_time_filter.end}'"
        elif event_time_filter.start:
            filter = f"{event_time_filter.field_name} >= '{event_time_filter.start}'"
        elif event_time_filter.end:
            filter = f"{event_time_filter.field_name} < '{event_time_filter.end}'"

        return filter

    def quoted(self, identifier):
        return "{quote_char}{identifier}{quote_char}".format(
            quote_char=self.quote_character,
            identifier=identifier,
        )

    @staticmethod
    def add_ephemeral_prefix(name: str):
        return f"__dbt__cte__{name}"

    @classmethod
    def create_ephemeral_from(
        cls: Type[Self],
        relation_config: RelationConfig,
        limit: Optional[int] = None,
        event_time_filter: Optional[EventTimeFilter] = None,
    ) -> Self:
        # Note that ephemeral models are based on the identifier, which will
        # point to the model's alias if one exists and otherwise fall back to
        # the filename. This is intended to give the user more control over
        # the way that the CTE name is constructed
        identifier = cls.add_ephemeral_prefix(relation_config.identifier)
        return cls.create(
            type=cls.CTE,
            identifier=identifier,
            limit=limit,
            event_time_filter=event_time_filter,
        ).quote(identifier=False)

    @classmethod
    def create_from(
        cls: Type[Self],
        quoting: HasQuoting,
        relation_config: RelationConfig,
        **kwargs: Any,
    ) -> Self:
        quote_policy = kwargs.pop("quote_policy", {})

        config_quoting = relation_config.quoting_dict
        config_quoting.pop("column", None)

        catalog_name = (
            relation_config.catalog_name
            if hasattr(relation_config, "catalog_name")
            else relation_config.config.get("catalog", None)  # type: ignore
        )

        # precedence: kwargs quoting > relation config quoting > base quoting > default quoting
        quote_policy = deep_merge(
            cls.get_default_quote_policy().to_dict(omit_none=True),
            quoting.quoting,
            config_quoting,
            quote_policy,
        )

        return cls.create(
            database=relation_config.database,
            schema=relation_config.schema,
            identifier=relation_config.identifier,
            quote_policy=quote_policy,
            catalog_name=catalog_name,
            **kwargs,
        )

    @classmethod
    def create(
        cls: Type[Self],
        database: Optional[str] = None,
        schema: Optional[str] = None,
        identifier: Optional[str] = None,
        type: Optional[RelationType] = None,
        **kwargs,
    ) -> Self:
        kwargs.update(
            {
                "path": {
                    "database": database,
                    "schema": schema,
                    "identifier": identifier,
                },
                "type": type,
            }
        )
        return cls.from_dict(kwargs)

    @classmethod
    def scd_args(cls: Type[Self], primary_key: Union[str, List[str]], updated_at) -> List[str]:
        scd_args = []
        if isinstance(primary_key, list):
            scd_args.extend(primary_key)
        else:
            scd_args.append(primary_key)
        scd_args.append(updated_at)
        return scd_args

    @property
    def can_be_renamed(self) -> bool:
        return self.type in self.renameable_relations

    @property
    def can_be_replaced(self) -> bool:
        return self.type in self.replaceable_relations

    def __repr__(self) -> str:
        return "<{} {}>".format(self.__class__.__name__, self.render())

    def __hash__(self) -> int:
        return hash(self.render())

    def __str__(self) -> str:
        # TODO: This function seems to have more if's than it needs to. We should see if we can simplify it.
        if self.is_function:
            # If it's a function we skip all special rendering logic and just return the raw render
            rendered = self.render()
        else:
            rendered = self.render() if self.limit is None else self.render_limited()

            # Limited subquery is wrapped by the event time filter subquery, and not the other way around.
            # This is because in the context of resolving limited refs, we care more about performance than reliably producing a sample of a certain size.
            if self.event_time_filter:
                rendered = self.render_event_time_filtered(rendered)

        return rendered

    @property
    def database(self) -> Optional[str]:
        return self.path.database

    @property
    def schema(self) -> Optional[str]:
        return self.path.schema

    @property
    def identifier(self) -> Optional[str]:
        return self.path.identifier

    @property
    def table(self) -> Optional[str]:
        return self.path.identifier

    # Here for compatibility with old Relation interface
    @property
    def name(self) -> Optional[str]:
        return self.identifier

    @property
    def is_table(self) -> bool:
        return self.type == RelationType.Table

    @property
    def is_cte(self) -> bool:
        return self.type == RelationType.CTE

    @property
    def is_view(self) -> bool:
        return self.type == RelationType.View

    @property
    def is_materialized_view(self) -> bool:
        return self.type == RelationType.MaterializedView

    @property
    def is_pointer(self) -> bool:
        return self.type == RelationType.PointerTable

    @property
    def is_function(self) -> bool:
        return self.type == RelationType.Function

    @classproperty
    def Table(cls) -> str:
        return str(RelationType.Table)

    @classproperty
    def CTE(cls) -> str:
        return str(RelationType.CTE)

    @classproperty
    def View(cls) -> str:
        return str(RelationType.View)

    @classproperty
    def External(cls) -> str:
        return str(RelationType.External)

    @classproperty
    def MaterializedView(cls) -> str:
        return str(RelationType.MaterializedView)

    @classproperty
    def PointerTable(cls) -> str:
        return str(RelationType.PointerTable)

    @classproperty
    def Function(cls) -> str:
        return str(RelationType.Function)

    @classproperty
    def get_relation_type(cls) -> Type[RelationType]:
        return RelationType

    def get_function_config(self, model: Dict[str, Any]) -> Optional[FunctionConfig]:
        # TODO: We shouldn't have to check the model.resource_type here. We should be alble to do self.is_function instead.
        # However, somehow when we get here self.type is None, and thus self.is_function is False.
        if model.get("resource_type") == "function":
            return FunctionConfig(
                language=model.get("language", ""),
                type=model.get("config", {}).get("type", ""),
                runtime_version=model.get("config", {}).get("runtime_version", None),
                entry_point=model.get("config", {}).get("entry_point", None),
            )
        else:
            return None

    def get_function_macro_name(self, config: FunctionConfig) -> str:
        return f"{config.type}_function_{config.language}"


Info = TypeVar("Info", bound="InformationSchema")


@dataclass(frozen=True, eq=False, repr=False)
class InformationSchema(BaseRelation):
    information_schema_view: Optional[str] = None

    def __post_init__(self):
        if not isinstance(self.information_schema_view, (type(None), str)):
            raise CompilationError("Got an invalid name: {}".format(self.information_schema_view))

    @classmethod
    def get_path(cls, relation: BaseRelation, information_schema_view: Optional[str]) -> Path:
        return Path(
            database=relation.database,
            schema=relation.schema,
            identifier="INFORMATION_SCHEMA",
        )

    @classmethod
    def get_include_policy(
        cls,
        relation,
        information_schema_view: Optional[str],
    ) -> Policy:
        return relation.include_policy.replace(
            database=relation.database is not None,
            schema=False,
            identifier=True,
        )

    @classmethod
    def get_quote_policy(
        cls,
        relation,
        information_schema_view: Optional[str],
    ) -> Policy:
        return relation.quote_policy.replace(
            identifier=False,
        )

    @classmethod
    def from_relation(
        cls: Type[Info],
        relation: BaseRelation,
        information_schema_view: Optional[str],
    ) -> Info:
        include_policy = cls.get_include_policy(relation, information_schema_view)
        quote_policy = cls.get_quote_policy(relation, information_schema_view)
        path = cls.get_path(relation, information_schema_view)
        return cls(
            type=RelationType.View,  # type: ignore
            path=path,
            include_policy=include_policy,
            quote_policy=quote_policy,
            information_schema_view=information_schema_view,
        )

    def _render_iterator(self):
        for k, v in super()._render_iterator():
            yield k, v
        yield None, self.information_schema_view


class SchemaSearchMap(Dict[InformationSchema, Set[Optional[str]]]):
    """A utility class to keep track of what information_schema tables to
    search for what schemas. The schema values are all lowercased to avoid
    duplication.
    """

    def add(self, relation: BaseRelation):
        key = relation.information_schema_only()
        if key not in self:
            self[key] = set()
        schema: Optional[str] = None
        if relation.schema is not None:
            schema = relation.schema.lower()
        self[key].add(schema)

    def search(self) -> Iterator[Tuple[InformationSchema, Optional[str]]]:
        for information_schema, schemas in self.items():
            for schema in schemas:
                yield information_schema, schema

    def flatten(self, allow_multiple_databases: bool = False) -> "SchemaSearchMap":
        new = self.__class__()

        # make sure we don't have multiple databases if allow_multiple_databases is set to False
        if not allow_multiple_databases:
            seen = {r.database.lower() for r in self if r.database}
            if len(seen) > 1:
                raise MultipleDatabasesNotAllowedError(seen)

        for information_schema_name, schema in self.search():
            path = {"database": information_schema_name.database, "schema": schema}
            new.add(
                information_schema_name.incorporate(
                    path=path,
                    quote_policy={"database": False},
                    include_policy={"database": False},
                )
            )

        return new


@dataclass(frozen=True, eq=False, repr=False)
class AdapterTrackingRelationInfo(FakeAPIObject, Hashable):
    adapter_name: str
    base_adapter_version: str
    adapter_version: str
    model_adapter_details: Any