feat: add two more capability tables for Athena

Add two more capability tables to Glue so Athena can query them.

I'd like to start doing this in an automated way at some point, but that doesn't feel high priority enough for the moment so I've filed an issue here:

#243

stacks/firehose-stack.js

@@ -9,6 +9,7 @@ import {
   aws_athena as athena,
   aws_sam as sam
 } from 'aws-cdk-lib'
+import { Access, Provider, Space, Store, Upload, Consumer, Customer, RateLimit, Subscription, Filecoin, Admin, UCAN } from '@web3-storage/capabilities'
 
 import { UcanInvocationStack } from './ucan-invocation-stack.js'
 
@@ -326,6 +327,104 @@ export function UcanFirehoseStack ({ stack, app }) {
   })
   uploadAddTable.addDependsOn(glueDatabase)
 
+    // creates a table that can be seen in the AWS Glue table browser at 
+  // https://console.aws.amazon.com/glue/home#/v2/data-catalog/tables
+  // and in the data browser in the Athena Query editor at
+  // https://console.aws.amazon.com/athena/home#/query-editor
+  const storeRemoveTableName = getCdkNames('store-remove-table', app.stage)
+  const storeRemoveTable = new glue.CfnTable(stack, storeRemoveTableName, {
+    catalogId: Aws.ACCOUNT_ID,
+    databaseName,
+    tableInput: {
+      name: storeRemoveTableName,
+      partitionKeys: [
+        { name: 'day', type: 'date' }
+      ],
+      parameters: {
+        classification: "json",
+        typeOfData: "file",
+        // @see https://docs.aws.amazon.com/athena/latest/ug/partition-projection-kinesis-firehose-example.html for more information on projection
+        // configuration - this should match the "day" parameter and S3 prefix configured in the delivery stream
+        "projection.enabled": "true",
+        "projection.day.type": "date",
+        "projection.day.format": "yyyy-MM-dd",
+        "projection.day.range": "2023-01-01,NOW",
+        "projection.day.interval": "1",
+        "projection.day.interval.unit": "DAYS",
+        "storage.location.template": `s3://${streamLogBucket.bucketName}/logs/receipt/store_remove/\${day}/`
+      },
+      storageDescriptor: {
+        location: `s3://${streamLogBucket.bucketName}/logs/receipt/store_remove/`,
+        columns: [
+          { name: 'carcid', type: 'string' },
+          // STRUCT here refers to the Apache Hive STRUCT datatype - see https://aws.amazon.com/blogs/big-data/create-tables-in-amazon-athena-from-nested-json-and-mappings-using-jsonserde/
+          { name: 'value', type: 'STRUCT<att:ARRAY<struct<can:STRING,with:STRING,nb:STRUCT<link:STRUCT<_cid_slash:STRING>>>>,iss:STRING,aud:STRING>' },
+          { name: "out", type: "STRUCT<error:STRUCT<name:STRING>,ok:STRUCT<size:BIGINT>>" },
+          { name: "ts", type: "timestamp" }
+        ],
+        inputFormat: 'org.apache.hadoop.mapred.TextInputFormat',
+        outputFormat: 'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat',
+        serdeInfo: {
+          serializationLibrary: 'org.openx.data.jsonserde.JsonSerDe',
+          parameters: {
+            // see https://aws.amazon.com/blogs/big-data/create-tables-in-amazon-athena-from-nested-json-and-mappings-using-jsonserde/
+            'mapping._cid_slash': '/'
+          }
+        }
+      }
+    }
+  })
+  storeRemoveTable.addDependsOn(glueDatabase)
+
+  // creates a table that can be seen in the AWS Glue table browser at 
+  // https://console.aws.amazon.com/glue/home#/v2/data-catalog/tables
+  // and in the data browser in the Athena Query editor at
+  // https://console.aws.amazon.com/athena/home#/query-editor
+  const uploadRemoveTableName = getCdkNames('upload-remove-table', app.stage)
+  const uploadRemoveTable = new glue.CfnTable(stack, uploadRemoveTableName, {
+    catalogId: Aws.ACCOUNT_ID,
+    databaseName,
+    tableInput: {
+      name: uploadRemoveTableName,
+      partitionKeys: [
+        { name: 'day', type: 'date' }
+      ],
+      parameters: {
+        classification: "json",
+        typeOfData: "file",
+        // @see https://docs.aws.amazon.com/athena/latest/ug/partition-projection-kinesis-firehose-example.html for more information on projection
+        // configuration - this should match the "day" parameter and S3 prefix configured in the delivery stream
+        "projection.enabled": "true",
+        "projection.day.type": "date",
+        "projection.day.format": "yyyy-MM-dd",
+        "projection.day.range": "2023-01-01,NOW",
+        "projection.day.interval": "1",
+        "projection.day.interval.unit": "DAYS",
+        "storage.location.template": `s3://${streamLogBucket.bucketName}/logs/receipt/upload_remove/\${day}/`
+      },
+      storageDescriptor: {
+        location: `s3://${streamLogBucket.bucketName}/logs/receipt/upload_remove/`,
+        columns: [
+          { name: 'carcid', type: 'string' },
+          // STRUCT here refers to the Apache Hive STRUCT datatype - see https://aws.amazon.com/blogs/big-data/create-tables-in-amazon-athena-from-nested-json-and-mappings-using-jsonserde/
+          { name: 'value', type: 'STRUCT<att:ARRAY<STRUCT<can:STRING,with:STRING,nb:STRUCT<root:STRUCT<_cid_slash:STRING>,shards:ARRAY<STRUCT<_cid_slash:STRING>>>>>,iss:STRING,aud:STRING>' },
+          { name: "out", type: "STRUCT<error:STRUCT<name:STRING>,ok:STRUCT<root:STRUCT<_cid_slash:STRING>,shards:ARRAY<STRUCT<_cid_slash:STRING>>>>" },
+          { name: "ts", type: "timestamp" }
+        ],
+        inputFormat: 'org.apache.hadoop.mapred.TextInputFormat',
+        outputFormat: 'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat',
+        serdeInfo: {
+          serializationLibrary: 'org.openx.data.jsonserde.JsonSerDe',
+          parameters: {
+            // see https://aws.amazon.com/blogs/big-data/create-tables-in-amazon-athena-from-nested-json-and-mappings-using-jsonserde/
+            'mapping._cid_slash': '/'
+          }
+        }
+      }
+    }
+  })
+  uploadRemoveTable.addDependsOn(glueDatabase)
+
   // creates a table that can be seen in the AWS Glue table browser at 
   // https://console.aws.amazon.com/glue/home#/v2/data-catalog/tables
   // and in the data browser in the Athena Query editor at