asadbek064/hyparquet
1
Fork 0
mirror of https://github.com/asadbek064/hyparquet.git synced 2026-02-22 12:21:33 +00:00
Code Issues Actions Projects Releases Wiki Activity

factor tests with it.for() (#55)

Browse Source
This commit is contained in:
Sylvain Lesage 2024-12-20 09:53:56 +01:00 committed by GitHub
parent 90f8a3b775
commit cb639a0b45
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 9 additions and 60 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

69
test/column.test.js
View File

@ -1,12 +1,19 @@
import { compressors } from 'hyparquet-compressors'
import { describe, expect, it } from 'vitest'
import { getColumnRange, readColumn } from '../src/column.js'
import { parquetMetadata } from '../src/hyparquet.js'
import { getSchemaPath } from '../src/schema.js'
import { getColumnRange, readColumn } from '../src/column.js'
import { asyncBufferFromFile } from '../src/utils.js'
const values = [null, 1, -2, NaN, 0, -1, -0, 2]
describe('readColumn', () => {
it('read columns when rowLimit is undefined', async () => {
it.for([
{ rowLimit: undefined, expected: values },
{ rowLimit: Infinity, expected: values },
{ rowLimit: 2, expected: values.slice(0, 2) },
{ rowLimit: 0, expected: [] },
])('readColumn with rowLimit %p', async ({ rowLimit, expected }) => {
const testFile = 'test/files/float16_nonzeros_and_nans.parquet'
const asyncBuffer = await asyncBufferFromFile(testFile)
const arrayBuffer = await asyncBuffer.slice(0)
@ -19,65 +26,7 @@ describe('readColumn', () => {
const schemaPath = getSchemaPath(metadata.schema, column.meta_data?.path_in_schema ?? [])
const reader = { view: new DataView(columnArrayBuffer), offset: 0 }
const rowLimit = undefined
const result = readColumn(reader, rowLimit, column.meta_data, schemaPath, { file: asyncBuffer, compressors })
const expected = [null, 1, -2, NaN, 0, -1, -0, 2]
expect(result).toEqual(expected)
})
it('read columns when rowLimit is Infinity', async () => {
const testFile = 'test/files/float16_nonzeros_and_nans.parquet'
const asyncBuffer = await asyncBufferFromFile(testFile)
const arrayBuffer = await asyncBuffer.slice(0)
const metadata = parquetMetadata(arrayBuffer)
const column = metadata.row_groups[0].columns[0]
if (!column.meta_data) throw new Error(`No column metadata for ${testFile}`)
const [columnStartByte, columnEndByte] = getColumnRange(column.meta_data).map(Number)
const columnArrayBuffer = arrayBuffer.slice(columnStartByte, columnEndByte)
const schemaPath = getSchemaPath(metadata.schema, column.meta_data?.path_in_schema ?? [])
const reader = { view: new DataView(columnArrayBuffer), offset: 0 }
const rowLimit = Infinity
const result = readColumn(reader, rowLimit, column.meta_data, schemaPath, { file: asyncBuffer, compressors })
const expected = [null, 1, -2, NaN, 0, -1, -0, 2]
expect(result).toEqual(expected)
})
it('read columns when rowLimit is defined', async () => {
const testFile = 'test/files/float16_nonzeros_and_nans.parquet'
const asyncBuffer = await asyncBufferFromFile(testFile)
const arrayBuffer = await asyncBuffer.slice(0)
const metadata = parquetMetadata(arrayBuffer)
const column = metadata.row_groups[0].columns[0]
if (!column.meta_data) throw new Error(`No column metadata for ${testFile}`)
const [columnStartByte, columnEndByte] = getColumnRange(column.meta_data).map(Number)
const columnArrayBuffer = arrayBuffer.slice(columnStartByte, columnEndByte)
const schemaPath = getSchemaPath(metadata.schema, column.meta_data?.path_in_schema ?? [])
const reader = { view: new DataView(columnArrayBuffer), offset: 0 }
const rowLimit = 2
const result = readColumn(reader, rowLimit, column.meta_data, schemaPath, { file: asyncBuffer, compressors })
expect(result.length).toBe(rowLimit)
})
it('read columns when rowLimit is 0', async () => {
const testFile = 'test/files/float16_nonzeros_and_nans.parquet'
const asyncBuffer = await asyncBufferFromFile(testFile)
const arrayBuffer = await asyncBuffer.slice(0)
const metadata = parquetMetadata(arrayBuffer)
const column = metadata.row_groups[0].columns[0]
if (!column.meta_data) throw new Error(`No column metadata for ${testFile}`)
const [columnStartByte, columnEndByte] = getColumnRange(column.meta_data).map(Number)
const columnArrayBuffer = arrayBuffer.slice(columnStartByte, columnEndByte)
const schemaPath = getSchemaPath(metadata.schema, column.meta_data?.path_in_schema ?? [])
const reader = { view: new DataView(columnArrayBuffer), offset: 0 }
const rowLimit = 0
const result = readColumn(reader, rowLimit, column.meta_data, schemaPath, { file: asyncBuffer, compressors })
expect(result.length).toBe(rowLimit)
})
})