initial Athena Clickhouse connector commit related to issue 1754

athena-clickhouse/.aws-sam/build.toml

@@ -0,0 +1,12 @@
+# This file is auto generated by SAM CLI build command
+
+[function_build_definitions.7ccd1098-a7c9-45fe-8bc9-6a25d68ee1b6]
+codeuri = "/Users/bishrt/dev/aws-athena-query-federation/athena-clickhouse/target/athena-clickhouse-2022.47.1.jar"
+runtime = "java11"
+architecture = "x86_64"
+handler = "com.amazonaws.athena.connectors.clickhouse.ClickHouseMuxCompositeHandler"
+manifest_hash = ""
+packagetype = "Zip"
+functions = ["JdbcConnectorConfig"]
+
+[layer_build_definitions]

athena-clickhouse/LICENSE.txt

@@ -0,0 +1,174 @@
+Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.

athena-clickhouse/README.md

@@ -0,0 +1,5 @@
+# Amazon Athena Lambda Clickhouse Connector
+
+This connector enables Amazon Athena to access your ClickHouse databases. 
+
+Documentation has moved [here](https://docs.aws.amazon.com/athena/latest/ug/connectors-athena.html).

athena-clickhouse/athena-clickhouse.yaml

@@ -0,0 +1,153 @@
+Transform: 'AWS::Serverless-2016-10-31'
+Metadata:
+  'AWS::ServerlessRepo::Application':
+    Name: AthenaClickHouseConnector
+    Description: 'This connector enables Amazon Athena to communicate with your ClickHouse instance(s) using JDBC driver.'
+    Author: 'default author'
+    SpdxLicenseId: Apache-2.0
+    LicenseUrl: LICENSE.txt
+    ReadmeUrl: README.md
+    Labels:
+      - athena-federation
+    HomePageUrl: 'https://github.com/awslabs/aws-athena-query-federation'
+    SemanticVersion: 2022.47.1
+    SourceCodeUrl: 'https://github.com/awslabs/aws-athena-query-federation'
+Parameters:
+  LambdaFunctionName:
+    Description: 'This is the name of the lambda function that will be created. This name must satisfy the pattern ^[a-z0-9-_]{1,64}$'
+    Type: String
+    AllowedPattern: ^[a-z0-9-_]{1,64}$
+  DefaultConnectionString:
+    Description: 'The default connection string is used when catalog is "lambda:${LambdaFunctionName}". Catalog specific Connection Strings can be added later. Format: ${DatabaseType}://${NativeJdbcConnectionString}.'
+    Type: String
+  SecretNamePrefix:
+    Description: 'Used to create resource-based authorization policy for "secretsmanager:GetSecretValue" action. E.g. All Athena Clickhouse Federation secret names can be prefixed with "AthenaClickHouseFederation" and authorization policy will allow "arn:${AWS::Partition}:secretsmanager:${AWS::Region}:${AWS::AccountId}:secret:AthenaJdbcFederation*". Parameter value in this case should be "AthenaClickhouseFederation". If you do not have a prefix, you can manually update the IAM policy to add allow any secret names.'
+    Type: String
+  SpillBucket:
+    Description: 'The name of the bucket where this function can spill data.'
+    Type: String
+  SpillPrefix:
+    Description: 'The prefix within SpillBucket where this function can spill data.'
+    Type: String
+    Default: athena-spill
+  LambdaTimeout:
+    Description: 'Maximum Lambda invocation runtime in seconds. (min 1 - 900 max)'
+    Default: 900
+    Type: Number
+  LambdaMemory:
+    Description: 'Lambda memory in MB (min 128 - 3008 max).'
+    Default: 3008
+    Type: Number
+  LambdaRoleARN:
+    Description: "(Optional) A custom role to be used by the Connector lambda"
+    Type: String
+    Default: ""
+  DisableSpillEncryption:
+    Description: 'If set to ''false'' data spilled to S3 is encrypted with AES GCM'
+    Default: 'false'
+    Type: String
+  SecurityGroupIds:
+    Description: 'One or more SecurityGroup IDs corresponding to the SecurityGroup that should be applied to the Lambda function. (e.g. sg1,sg2,sg3)'
+    Type: 'List<AWS::EC2::SecurityGroup::Id>'
+  SubnetIds:
+    Description: 'One or more Subnet IDs corresponding to the Subnet that the Lambda function can use to access you data source. (e.g. subnet1,subnet2)'
+    Type: 'List<AWS::EC2::Subnet::Id>'
+  PermissionsBoundaryARN:
+    Description: "(Optional) An IAM policy ARN to use as the PermissionsBoundary for the created Lambda function's execution role"
+    Default: ''
+    Type: String
+Conditions:
+  HasPermissionsBoundary: !Not [ !Equals [ !Ref PermissionsBoundaryARN, "" ] ]
+  NotHasLambdaRole: !Equals [!Ref LambdaRoleARN, ""]
+Resources:
+  JdbcConnectorConfig:
+    Type: 'AWS::Serverless::Function'
+    Properties:
+      Environment:
+        Variables:
+          disable_spill_encryption: !Ref DisableSpillEncryption
+          spill_bucket: !Ref SpillBucket
+          spill_prefix: !Ref SpillPrefix
+          default: !Ref DefaultConnectionString
+      FunctionName: !Ref LambdaFunctionName
+      Handler: "com.amazonaws.athena.connectors.clickhouse.ClickHouseMuxCompositeHandler"
+      CodeUri: "./target/athena-clickhouse-2022.47.1.jar"
+      Description: "Enables Amazon Athena to communicate with ClickHouse using JDBC"
+      Runtime: java11
+      Timeout: !Ref LambdaTimeout
+      MemorySize: !Ref LambdaMemory
+      PermissionsBoundary: !If [ HasPermissionsBoundary, !Ref PermissionsBoundaryARN, !Ref "AWS::NoValue" ]
+      Role: !If [NotHasLambdaRole, !GetAtt FunctionRole.Arn, !Ref LambdaRoleARN]
+      VpcConfig:
+        SecurityGroupIds: !Ref SecurityGroupIds
+        SubnetIds: !Ref SubnetIds
+  FunctionRole:
+    Condition: NotHasLambdaRole
+    Type: AWS::IAM::Role
+    Properties:
+      ManagedPolicyArns:
+        - "arn:aws:iam::aws:policy/service-role/AWSLambdaVPCAccessExecutionRole"
+      AssumeRolePolicyDocument:
+        Version: 2012-10-17
+        Statement:
+          - Effect: Allow
+            Principal:
+              Service:
+                - lambda.amazonaws.com
+            Action:
+                - "sts:AssumeRole"
+  FunctionExecutionPolicy:
+    Condition: NotHasLambdaRole
+    Type: "AWS::IAM::Policy"
+    Properties:
+      Roles:
+        - !Ref FunctionRole
+      PolicyName: FunctionExecutionPolicy
+      PolicyDocument:
+        Version: 2012-10-17
+        Statement:
+          - Action:
+              - secretsmanager:GetSecretValue
+            Effect: Allow
+            Resource: !Sub 'arn:${AWS::Partition}:secretsmanager:${AWS::Region}:${AWS::AccountId}:secret:${SecretNamePrefix}*'
+          - Action:
+              - logs:CreateLogGroup
+            Effect: Allow
+            Resource: !Sub 'arn:${AWS::Partition}:logs:${AWS::Region}:${AWS::AccountId}:*'
+          - Action:
+            - logs:CreateLogStream
+            - logs:PutLogEvents
+            Effect: Allow
+            Resource: !Sub 'arn:${AWS::Partition}:logs:${AWS::Region}:${AWS::AccountId}:log-group:/aws/lambda/${LambdaFunctionName}:*'
+          - Action:
+            - athena:GetQueryExecution
+            - s3:ListAllMyBuckets
+            Effect: Allow
+            Resource: '*'
+          - Action:
+            - ec2:CreateNetworkInterface
+            - ec2:DeleteNetworkInterface
+            - ec2:DescribeNetworkInterfaces
+            - ec2:DetachNetworkInterface
+            Effect: Allow
+            Resource: '*'
+          - Action:
+             - s3:GetObject
+             - s3:ListBucket
+             - s3:GetBucketLocation
+             - s3:GetObjectVersion
+             - s3:PutObject
+             - s3:PutObjectAcl
+             - s3:GetLifecycleConfiguration
+             - s3:PutLifecycleConfiguration
+             - s3:DeleteObject
+            Effect: Allow
+            Resource:
+              - Fn::Sub:
+                - arn:${AWS::Partition}:s3:::${bucketName}
+                - bucketName:
+                    Ref: SpillBucket
+              - Fn::Sub:
+                - arn:${AWS::Partition}:s3:::${bucketName}/*
+                - bucketName:
+                    Ref: SpillBucket

athena-clickhouse/etc/test-config.json

@@ -0,0 +1,23 @@
+{
+  "athena_work_group" : "FederationIntegrationTests", /* The Athena Workgroup used for running integration tests (default: FederationIntegrationTests) */
+  "athena_result_location": "<bucket_path (without s3://)>", /* The s3 bucket path used to store results of Athena queries */
+  "secrets_manager_secret" : "<secret name>",         /* Secret name used to retrieve user credentials from SecretsManager. */
+  "environment_vars" : {                  /* Parameters used by the connector's internal logic */
+    "spill_bucket" : "<spill bucket>",    /* The S3 bucket used for spilling excess data */
+    "spill_prefix" : "athena-spill",      /* The prefix within the S3 spill bucket (default: athena-spill) */
+    "disable_spill_encryption" : "false",  /* If set to true encryption for spilled data is disabled (default: false) */
+    "spill_put_request_headers": ""  /* JSON encoded map of request headers and values for the s3 putObject request used for spilling. This is a String not an object. Optional.*/
+  },
+  "vpc_configuration" : {                 /* VPC configuration for DB instances within a VPC */
+    "vpc_id": "<VPC Id>",                 /* The VPC Id (e.g. vpc-xxx) */
+    "security_group_id": "<SG Id>",       /* The Security Group Id (e.g. sg-xxx) */
+    "subnet_ids": ["<Subnet 1>", "<Subnet 2>"],     /* A list consisting of at least one Subnet Id (e.g. subnet-xxxx) */
+    "availability_zones": ["<Zone 1>", "<Zone 2>"]  /* A list consisting of at least one AZ (e.g. us-east-1a) */
+  },
+  "user_settings" : {                     /* User customizable settings */
+    "mysql_db_name": "<DB Name>",         /* Name of the Db used by the MySql integration tests */
+    "mysql_db_port": "<Port (Integer)>",    /* Port number associated with the MySql instance endpoint */
+    "mysql_table_movies": "<Table Name>",       /* MySql table name */
+    "mysql_table_bday": "<Table Name>"          /* MySql table name */
+  }
+}