graphql-engine/server/src-lib/Hasura/Backends/Postgres/Instances/Metadata.hs
Vamshi Surabhi e8e4f30dd6 server: support remote relationships on SQL Server and BigQuery (#1497)
Remote relationships are now supported on SQL Server and BigQuery. The major change though is the re-architecture of remote join execution logic. Prior to this PR, each backend is responsible for processing the remote relationships that are part of their AST.

This is not ideal as there is nothing specific about a remote join's execution that ties it to a backend. The only backend specific part is whether or not the specification of the remote relationship is valid (i.e, we'll need to validate whether the scalars are compatible).

The approach now changes to this:

1. Before delegating the AST to the backend, we traverse the AST, collect all the remote joins while modifying the AST to add necessary join fields where needed.

1. Once the remote joins are collected from the AST, the database call is made to fetch the response. The necessary data for the remote join(s) is collected from the database's response and one or more remote schema calls are constructed as necessary.

1. The remote schema calls are then executed and the data from the database and from the remote schemas is joined to produce the final response.

### Known issues

1. Ideally the traversal of the IR to collect remote joins should return an AST which does not include remote join fields. This operation can be type safe but isn't taken up as part of the PR.

1. There is a lot of code duplication between `Transport/HTTP.hs` and `Transport/Websocket.hs` which needs to be fixed ASAP. This too hasn't been taken up by this PR.

1. The type which represents the execution plan is only modified to handle our current remote joins and as such it will have to be changed to accommodate general remote joins.

1. Use of lenses would have reduced the boilerplate code to collect remote joins from the base AST.

1. The current remote join logic assumes that the join columns of a remote relationship appear with their names in the database response. This however is incorrect as they could be aliased. This can be taken up by anyone, I've left a comment in the code.

### Notes to the reviewers

I think it is best reviewed commit by commit.

1. The first one is very straight forward.

1. The second one refactors the remote join execution logic but other than moving things around, it doesn't change the user facing functionality.  This moves Postgres specific parts to `Backends/Postgres` module from `Execute`. Some IR related code to `Hasura.RQL.IR` module.  Simplifies various type class function signatures as a backend doesn't have to handle remote joins anymore

1. The third one fixes partial case matches that for some weird reason weren't shown as warnings before this refactor

1. The fourth one generalizes the validation logic of remote relationships and implements `scalarTypeGraphQLName` function on SQL Server and BigQuery which is used by the validation logic. This enables remote relationships on BigQuery and SQL Server.

https://github.com/hasura/graphql-engine-mono/pull/1497

GitOrigin-RevId: 77dd8eed326602b16e9a8496f52f46d22b795598
2021-06-11 03:27:39 +00:00

128 lines
5.3 KiB
Haskell

{-# OPTIONS_GHC -fno-warn-orphans #-}
{-# LANGUAGE UndecidableInstances #-}
module Hasura.Backends.Postgres.Instances.Metadata () where
import Hasura.Prelude
import qualified Data.HashMap.Strict as Map
import Data.Text.Extended
import qualified Hasura.Backends.Postgres.DDL as PG
import Hasura.Backends.Postgres.SQL.Types (QualifiedTable)
import Hasura.Backends.Postgres.Types.CitusExtraTableMetadata
import Hasura.Base.Error
import Hasura.RQL.Types.Backend (Backend)
import Hasura.RQL.Types.Metadata.Backend
import Hasura.RQL.Types.Relationship
import Hasura.RQL.Types.Table
import Hasura.SQL.Backend
--------------------------------------------------------------------------------
-- PostgresMetadata
-- | We differentiate the handling of metadata between Citus and Vanilla
-- Postgres because Citus imposes limitations on the types of joins that it
-- permits, which then limits the types of relations that we can track.
class PostgresMetadata (pgKind :: PostgresKind) where
-- TODO: find a better name
validateRel
:: MonadError QErr m
=> TableCache ('Postgres pgKind)
-> QualifiedTable
-> Either (ObjRelDef ('Postgres pgKind)) (ArrRelDef ('Postgres pgKind))
-> m ()
instance PostgresMetadata 'Vanilla where
validateRel _ _ _ = pure ()
instance PostgresMetadata 'Citus where
validateRel
:: forall m
. MonadError QErr m
=> TableCache ('Postgres 'Citus)
-> QualifiedTable
-> Either (ObjRelDef ('Postgres 'Citus)) (ArrRelDef ('Postgres 'Citus))
-> m ()
validateRel tableCache sourceTable relInfo = do
sourceTableInfo <- lookupTableInfo sourceTable
case relInfo of
Left (RelDef _ obj _) ->
case obj of
RUFKeyOn (SameTable _) -> pure ()
RUFKeyOn (RemoteTable targetTable _) -> checkObjectRelationship sourceTableInfo targetTable
RUManual RelManualConfig { } -> pure ()
Right (RelDef _ obj _) ->
case obj of
RUFKeyOn (ArrRelUsingFKeyOn targetTable _col) -> checkArrayRelationship sourceTableInfo targetTable
RUManual RelManualConfig { } -> pure ()
where
lookupTableInfo tableName = Map.lookup tableName tableCache
`onNothing` throw400 NotFound ("no such table " <>> tableName)
checkObjectRelationship sourceTableInfo targetTable = do
targetTableInfo <- lookupTableInfo targetTable
let notSupported = throwNotSupportedError sourceTableInfo targetTableInfo "object"
case ( _tciExtraTableMetadata $ _tiCoreInfo sourceTableInfo
, _tciExtraTableMetadata $ _tiCoreInfo targetTableInfo
) of
(Distributed{}, Local) -> notSupported
(Distributed{}, Reference) -> pure ()
(Distributed{}, Distributed{}) -> pure ()
(_, Distributed{}) -> notSupported
(_, _) -> pure ()
checkArrayRelationship sourceTableInfo targetTable = do
targetTableInfo <- lookupTableInfo targetTable
let notSupported = throwNotSupportedError sourceTableInfo targetTableInfo "array"
case ( _tciExtraTableMetadata $ _tiCoreInfo sourceTableInfo
, _tciExtraTableMetadata $ _tiCoreInfo targetTableInfo
) of
(Distributed{}, Distributed{}) -> pure ()
(Distributed{}, _) -> notSupported
(_, Distributed{}) -> notSupported
(_, _) -> pure ()
showDistributionType :: ExtraTableMetadata -> Text
showDistributionType = \case
Local -> "local"
Distributed _ -> "distributed"
Reference -> "reference"
throwNotSupportedError :: TableInfo ('Postgres 'Citus) -> TableInfo ('Postgres 'Citus) -> Text -> m ()
throwNotSupportedError sourceTableInfo targetTableInfo t =
let tciSrc = _tiCoreInfo sourceTableInfo
tciTgt = _tiCoreInfo targetTableInfo
in
throw400 NotSupported (
showDistributionType (_tciExtraTableMetadata tciSrc) <>
" tables (" <> toTxt (_tciName tciSrc) <> ") cannot have an " <> t <> " relationship against a " <>
showDistributionType (_tciExtraTableMetadata $ _tiCoreInfo targetTableInfo) <>
" table (" <> toTxt (_tciName tciTgt) <> ")")
----------------------------------------------------------------
-- BackendMetadata instance
instance
( Backend ('Postgres pgKind)
, PostgresMetadata pgKind
, PG.ToMetadataFetchQuery pgKind
) => BackendMetadata ('Postgres pgKind) where
buildComputedFieldInfo = PG.buildComputedFieldInfo
fetchAndValidateEnumValues = PG.fetchAndValidateEnumValues
resolveSourceConfig = PG.resolveSourceConfig
resolveDatabaseMetadata = PG.resolveDatabaseMetadata
createTableEventTrigger = PG.createTableEventTrigger
buildEventTriggerInfo = PG.buildEventTriggerInfo @pgKind
parseBoolExpOperations = PG.parseBoolExpOperations
buildFunctionInfo = PG.buildFunctionInfo
updateColumnInEventTrigger = PG.updateColumnInEventTrigger
parseCollectableType = PG.parseCollectableType
postDropSourceHook = PG.postDropSourceHook
validateRelationship = validateRel @pgKind