Athena: Remove duplicate first row (#3101)

catalog/app/containers/Bucket/Queries/Athena/Athena.tsx

@@ -182,7 +182,7 @@ function ResultsContainer({
         workgroup={workgroup}
       >
         {!!queryResults.rows.length && (
-          <CreatePackage bucket={bucket} rows={queryResults.rows} />
+          <CreatePackage bucket={bucket} queryResults={queryResults} />
         )}
       </ResultsBreadcrumbs>
       {/* eslint-disable-next-line no-nested-ternary */}

catalog/app/containers/Bucket/Queries/Athena/CreatePackage.tsx

@@ -24,25 +24,25 @@ function SeeDocsForCreatingPackage() {
 }
 
 function doQueryResultsContainManifestEntries(
-  rows: string[][],
-): rows is [ManifestKey[], ...string[][]] {
-  const [head] = rows
+  queryResults: requests.athena.QueryResultsResponse,
+): queryResults is requests.athena.QueryManifestsResponse {
+  const columnNames = queryResults.columns.map(({ name }) => name)
   return (
-    head.includes('size') &&
-    head.includes('physical_keys') &&
-    head.includes('logical_key')
+    columnNames.includes('size') &&
+    columnNames.includes('physical_keys') &&
+    columnNames.includes('logical_key')
   )
 }
 
 function rowToManifestEntryStringified(
   row: string[],
-  head: ManifestKey[],
+  columns: requests.athena.QueryResultsColumns,
 ): ManifestEntryStringified {
   return row.reduce((acc, value, index) => {
-    if (!head[index]) return acc
+    if (!columns[index].name) return acc
     return {
       ...acc,
-      [head[index]]: value,
+      [columns[index].name]: value,
     }
   }, {} as ManifestEntryStringified)
 }
@@ -72,11 +72,10 @@ function parseManifestEntryStringified(entry: ManifestEntryStringified): {
 }
 
 function parseQueryResults(
-  rows: [ManifestKey[], ...string[][]],
+  queryResults: requests.athena.QueryManifestsResponse,
 ): Record<string, Model.S3File> {
-  const [head, ...tail] = rows
-  const manifestEntries: ManifestEntryStringified[] = tail.reduce(
-    (memo, row) => memo.concat(rowToManifestEntryStringified(row, head)),
+  const manifestEntries: ManifestEntryStringified[] = queryResults.rows.reduce(
+    (memo, row) => memo.concat(rowToManifestEntryStringified(row, queryResults.columns)),
     [] as ManifestEntryStringified[],
   )
   return manifestEntries.reduce(
@@ -90,26 +89,28 @@ function parseQueryResults(
 
 interface CreatePackageProps {
   bucket: string
-  rows: requests.athena.QueryResultsRows
+  queryResults: requests.athena.QueryResultsResponse
 }
 
-export default function CreatePackage({ bucket, rows }: CreatePackageProps) {
+export default function CreatePackage({ bucket, queryResults }: CreatePackageProps) {
   const addToPackage = AddToPackage.use()
   const createDialog = usePackageCreationDialog({
     bucket,
     delayHashing: true,
     disableStateDisplay: true,
   })
   const onPackage = React.useCallback(() => {
-    if (!doQueryResultsContainManifestEntries(rows)) return
+    if (!doQueryResultsContainManifestEntries(queryResults)) return
 
     // TODO: make it lazy, and disable button
-    const entries = parseQueryResults(rows)
+    const entries = parseQueryResults(queryResults)
     addToPackage?.merge(entries)
     createDialog.open()
-  }, [addToPackage, createDialog, rows])
+  }, [addToPackage, createDialog, queryResults])
 
-  if (!doQueryResultsContainManifestEntries(rows)) return <SeeDocsForCreatingPackage />
+  if (!doQueryResultsContainManifestEntries(queryResults)) {
+    return <SeeDocsForCreatingPackage />
+  }
 
   return (
     <>

catalog/app/containers/Bucket/Queries/requests/athena.ts

@@ -325,6 +325,12 @@ export interface QueryResultsResponse {
   rows: QueryResultsRows
 }
 
+type ManifestKey = 'hash' | 'logical_key' | 'meta' | 'physical_keys' | 'size'
+
+export interface QueryManifestsResponse extends QueryResultsResponse {
+  rows: [ManifestKey[], ...string[][]]
+}
+
 interface QueryResultsArgs {
   athena: Athena
   queryExecutionId: string
@@ -361,15 +367,17 @@ async function fetchQueryResults({
         (row) => row?.Data?.map((item) => item?.VarCharValue || '') || emptyRow,
       ) || emptyList
     const rows = [...(prev?.rows || emptyList), ...parsed]
+    const columns =
+      queryResultsOutput.ResultSet?.ResultSetMetadata?.ColumnInfo?.map(
+        ({ Name, Type }) => ({
+          name: Name,
+          type: Type,
+        }),
+      ) || emptyColumns
+    const isHeadColumns = columns.every(({ name }, index) => name === rows[0][index])
     return {
-      rows,
-      columns:
-        queryResultsOutput.ResultSet?.ResultSetMetadata?.ColumnInfo?.map(
-          ({ Name, Type }) => ({
-            name: Name,
-            type: Type,
-          }),
-        ) || emptyColumns,
+      rows: isHeadColumns ? rows.slice(1) : rows,
+      columns,
       next: queryResultsOutput.NextToken,
       queryExecution,
     }

docs/CHANGELOG.md

@@ -32,6 +32,7 @@
 * [Added] `status_reports` lambda ([#2989](https://github.com/quiltdata/quilt/pull/2989), [#3088](https://github.com/quiltdata/quilt/pull/3088))
 * [Added] Stack Status Admin UI: reports ([#3068](https://github.com/quiltdata/quilt/pull/3068))
 * [Added] Edit button for text files in packages ([#3070](https://github.com/quiltdata/quilt/pull/3070))
+* [Added] Add execution context for Athena query execution ([#3062](https://github.com/quiltdata/quilt/pull/3062))
 * [Fixed] Fix package creation in S3 buckets with SSE-KMS enabled ([#2754](https://github.com/quiltdata/quilt/pull/2754))
 * [Fixed] Fix creation of packages with large (4+ GiB) files ([#2933](https://github.com/quiltdata/quilt/pull/2933))
 * [Fixed] Fix pre-popullation of default dates when using "dateformat" + {"format": "date"} ([3082](https://github.com/quiltdata/quilt/pull/3082))
@@ -42,6 +43,7 @@
 * [Changed] Rework package indexing: now package indexes have documents only for current versions of package pointer objects, documents for 'latest' pointers have `package_hash`, `package_stats`, `comment`, `metadata` fields properly populated ([#2897](https://github.com/quiltdata/quilt/pull/2897))
 * [Changed] Remove ClientRequestToken (idempotency token) for making Athena queries ([#2992](https://github.com/quiltdata/quilt/pull/2992))
 * [Changed] Fixed config and docs mistyping: `ui.athena.defaultWorkflow` should be `ui.athena.defaultWorkgroup` ([#3067](https://github.com/quiltdata/quilt/pull/3067))
+* [Changed] Use dedicated columns field instead of first row, fix duplicated first row in table results ([#3101](https://github.com/quiltdata/quilt/pull/3101))
 
 ## Docs
 * [Added] Fix four-deep headers so auto-link generation works ([#3100](https://github.com/quiltdata/quilt/pull/3100))