Skip to content

Use parquetReadColumn from hyparquet #251

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
platypii merged 1 commit into from
May 27, 2025
Merged

Use parquetReadColumn from hyparquet #251

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions package.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,7 +54,7 @@
},
"dependencies": {
"hightable": "0.16.0",
"hyparquet": "1.13.5",
"hyparquet": "1.14.0",
"hyparquet-compressors": "1.1.1",
"icebird": "0.3.0",
"react": "18.3.1",
Expand All @@ -79,7 +79,7 @@
"eslint-plugin-react-hooks": "5.2.0",
"eslint-plugin-react-refresh": "0.4.20",
"eslint-plugin-storybook": "0.12.0",
"globals": "16.1.0",
"globals": "16.2.0",
"jsdom": "26.1.0",
"nodemon": "3.1.10",
"npm-run-all": "4.1.5",
Expand Down
65 changes: 0 additions & 65 deletions src/lib/getParquetColumn.ts
View file
Open in desktop

This file was deleted.

9 changes: 4 additions & 5 deletions src/lib/workers/parquetWorker.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
import { ColumnData, parquetQuery } from 'hyparquet'
import { compressors } from 'hyparquet-compressors'
import { getParquetColumn } from '../getParquetColumn.js'
import { parquetReadColumn } from 'hyparquet/src/read.js'
import { asyncBufferFrom } from '../utils.js'
import type { ChunkMessage, ClientMessage, ColumnRanksMessage, ErrorMessage, ResultMessage } from './types.js'

Expand Down Expand Up @@ -28,10 +28,9 @@ self.onmessage = async ({ data }: { data: ClientMessage }) => {
// purpose of sorting.

try {
const sortColumn = await getParquetColumn({ metadata, file, column, compressors })
const sortColumn: unknown[] = Array.from(await parquetReadColumn({ file, metadata, columns: [column], compressors }))
const valuesWithIndex = sortColumn.map((value, index) => ({ value, index }))
const sortedValuesWithIndex = Array.from(valuesWithIndex).sort(({ value: a }, { value: b }) => compare<unknown>(a, b))
const numRows = sortedValuesWithIndex.length
const sortedValuesWithIndex = valuesWithIndex.sort(({ value: a }, { value: b }) => compare<unknown>(a, b))
const columnRanks = sortedValuesWithIndex.reduce((accumulator, currentValue, rank) => {
const { lastValue, lastRank, ranks } = accumulator
const { value, index } = currentValue
Expand All @@ -43,7 +42,7 @@ self.onmessage = async ({ data }: { data: ClientMessage }) => {
return { ranks, lastValue: value, lastRank: rank }
}
}, {
ranks: Array(numRows).fill(-1) as number[],
ranks: Array(sortColumn.length).fill(-1) as number[],
lastValue: undefined as unknown,
lastRank: 0,
}).ranks
Expand Down