hyparquet - npm Package Compare versions

Comparing version 1.3.0 to 1.4.0

package.json

 {
   "name": "hyparquet",
-  "version": "1.3.0",
+  "version": "1.4.0",
   "description": "parquet file parser for javascript",
@@ -25,2 +25,3 @@ "keywords": [
     "demo": "http-server -o",
+    "demo:build": "rollup -c",
     "lint": "eslint .",
@@ -30,13 +31,23 @@ "test": "vitest run"
   "devDependencies": {
-    "@types/node": "22.4.1",
-    "@typescript-eslint/eslint-plugin": "8.2.0",
-    "@vitest/coverage-v8": "2.0.5",
-    "eslint": "8.57.0",
-    "eslint-plugin-import": "2.29.1",
-    "eslint-plugin-jsdoc": "50.2.2",
+    "@rollup/plugin-commonjs": "28.0.0",
+    "@rollup/plugin-node-resolve": "15.3.0",
+    "@rollup/plugin-replace": "6.0.1",
+    "@rollup/plugin-terser": "0.4.4",
+    "@rollup/plugin-typescript": "12.1.0",
+    "@types/node": "22.7.0",
+    "@types/react": "18.3.9",
+    "@types/react-dom": "18.3.0",
+    "@vitest/coverage-v8": "2.1.1",
+    "eslint": "9.11.1",
+    "eslint-plugin-jsdoc": "50.2.4",
+    "hightable": "0.4.4",
     "http-server": "14.1.1",
     "hyparquet-compressors": "0.1.4",
-    "typescript": "5.5.4",
-    "vitest": "2.0.5"
+    "react": "18.3.1",
+    "react-dom": "18.3.1",
+    "rollup": "4.22.4",
+    "typescript": "5.6.2",
+    "typescript-eslint": "8.7.0",
+    "vitest": "2.1.1"
   }
 }

README.md

@@ -9,3 +9,3 @@ # hyparquet
 [![dependencies](https://img.shields.io/badge/Dependencies-0-blueviolet)](https://www.npmjs.com/package/hyparquet?activeTab=dependencies)
-![coverage](https://img.shields.io/badge/Coverage-95-darkred)
+![coverage](https://img.shields.io/badge/Coverage-96-darkred)
 
@@ -18,3 +18,3 @@ Dependency free since 2023!
 
-Hyparquet allows you to read and extract data from Parquet files directly in JavaScript environments, both in Node.js and in the browser. It is designed to be fast, memory-efficient, and easy to use.
+Hyparquet allows you to read and extract data from Parquet files directly in JavaScript environments, both in Node.js and in the browser, without any dependencies. Designed for performance and ease of use, hyparquet is ideal for data engineering, data science, and machine learning applications that require efficient data processing.
 
@@ -27,2 +27,4 @@ ## Demo
 
+[![hyparquet demo](demo/assets/demo.png)](https://hyparam.github.io/hyparquet/)
+
 ## Features
@@ -57,3 +59,3 @@
 
-```js
+```javascript
 const { asyncBufferFromFile, parquetRead } = await import('hyparquet')
@@ -83,3 +85,3 @@ await parquetRead({
 
-```js
+```javascript
 const { parquetMetadata } = await import('hyparquet')
@@ -97,3 +99,3 @@ const fs = await import('fs')
 
-```js
+```javascript
 import { parquetMetadata } from 'hyparquet'
@@ -115,3 +117,3 @@
 
-```js
+```javascript
 import { parquetRead } from 'hyparquet'
@@ -133,3 +135,3 @@
 
-```js
+```javascript
 import { parquetRead } from 'hyparquet'
@@ -160,3 +162,3 @@
 
-```js
+```javascript
 import { parquetRead } from 'hyparquet'
@@ -163,0 +165,0 @@

src/hyparquet.d.ts

@@ -45,2 +45,13 @@ import type { AsyncBuffer, Compressors, FileMetaData, SchemaTree } from './types.d.ts'
 /**
+ * Wraps parquetRead with orderBy support.
+ * This is a parquet-aware query engine that can read a subset of rows and columns.
+ * Accepts an optional orderBy column name to sort the results.
+ * Note that using orderBy may SIGNIFICANTLY increase the query time.
+ *
+ * @param {ParquetReadOptions & { orderBy?: string }} options
+ * @returns {Promise<Record<string, any>[]>} resolves when all requested rows and columns are parsed
+ */
+export function parquetQuery(options: ParquetReadOptions & { orderBy?: string }): Promise<Array<Record<string, any>>>
+
+/**
  * Read parquet metadata from an async buffer.
@@ -47,0 +58,0 @@ *

src/hyparquet.js

@@ -1,3 +0,2 @@
-import { parquetMetadata, parquetMetadataAsync, parquetSchema } from './metadata.js'
-export { parquetMetadata, parquetMetadataAsync, parquetSchema }
+export { parquetMetadata, parquetMetadataAsync, parquetSchema } from './metadata.js'
 
@@ -7,8 +6,8 @@ import { parquetRead } from './read.js'
 
-import { snappyUncompress } from './snappy.js'
-export { snappyUncompress }
+export { parquetQuery } from './query.js'
 
-import { asyncBufferFromFile, asyncBufferFromUrl, toJson } from './utils.js'
-export { asyncBufferFromFile, asyncBufferFromUrl, toJson }
+export { snappyUncompress } from './snappy.js'
 
+export { asyncBufferFromFile, asyncBufferFromUrl, toJson } from './utils.js'
+
 /**
@@ -15,0 +14,0 @@ * @param {import('./hyparquet.js').ParquetReadOptions} options

src/utils.js

@@ -40,11 +40,9 @@ /**
 /**
- * Construct an AsyncBuffer for a URL.
+ * Get the byte length of a URL using a HEAD request.
  *
- * @typedef {import('./types.js').AsyncBuffer} AsyncBuffer
  * @param {string} url
- * @returns {Promise<AsyncBuffer>}
+ * @returns {Promise<number>}
  */
-export async function asyncBufferFromUrl(url) {
-  // byte length from HEAD request
-  const byteLength = await fetch(url, { method: 'HEAD' })
+export async function byteLengthFromUrl(url) {
+  return await fetch(url, { method: 'HEAD' })
     .then(res => {
@@ -56,2 +54,15 @@ if (!res.ok) throw new Error(`fetch head failed ${res.status}`)
     })
+}
+
+/**
+ * Construct an AsyncBuffer for a URL.
+ *
+ * @typedef {import('./types.js').AsyncBuffer} AsyncBuffer
+ * @param {string} url
+ * @param {number} [byteLength]
+ * @returns {Promise<AsyncBuffer>}
+ */
+export async function asyncBufferFromUrl(url, byteLength) {
+  // byte length from HEAD request
+  byteLength ||= await byteLengthFromUrl(url)
   return {
@@ -58,0 +69,0 @@ byteLength,

New alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Fixed alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Improved metrics

Total package byte prevSize

114301

increased by4.18%

Number of package files

24

increased by4.35%

Lines of code

2967

increased by3.78%

Number of lines in readme file

257

increased by0.78%

Worsened metrics

Dev dependency count

20

increased by100%

No dependency changes