feat: add czv, czv-wasm, and czv-python (init release)

This commit is contained in:
rzmk 2024-06-19 22:37:33 -04:00
commit 9799ab694b
No known key found for this signature in database
40 changed files with 70383 additions and 0 deletions

17
czv-wasm/Cargo.toml Normal file
View file

@ -0,0 +1,17 @@
[package]
name = "czv-wasm"
version = "0.0.0"
authors = ["Mueez Khan"]
description = "WASM library for performing CSV-related functions for data engineering and analysis."
repository = "https://github.com/rzmk/czv"
edition = "2021"
[lib]
crate-type = ["cdylib", "rlib"]
[dependencies]
anyhow = "1.0.86"
csv = "1.3.0"
thiserror = "1.0.61"
wasm-bindgen = { version = "0.2" }
wasm-bindgen-test = { version = "0.3.42" }

47
czv-wasm/README.md Normal file
View file

@ -0,0 +1,47 @@
# czv-wasm
WebAssembly (JavaScript and TypeScript) library for [czv](https://github.com/rzmk/czv). czv is a library of utility functions for CSV-related data engineering and analysis tasks.
## Installation and example
```bash
bun install czv
```
Or use `npm`, `pnpm`, or `yarn` instead of `bun`.
```js
import init, * as czv from "czv";
// Must run `await init()` or `initSync()` first for web use
await init();
const data = `fruits,price
apple,2.50
banana,3.00
strawberry,1.50`;
const output = czv.rowCount(data);
console.log(output);
```
## Development
You must have [wasm-pack](https://rustwasm.github.io/wasm-pack/installer/) installed. If you have Cargo installed you may run:
```bash
cargo install wasm-pack
```
### Build WASM for web
```bash
wasm-pack build --release --target web
```
### Test WASM for browser
```bash
wasm-pack test --firefox --release
```
You may replace `--firefox` with another browser such as `--chrome` and `--safari`.

View file

@ -0,0 +1,69 @@
<!DOCTYPE html>
<html id="html" lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<link rel="stylesheet" href="pico.min.css" />
<title>czv demo</title>
</head>
<body style="padding:1rem">
<div style="display: flex; gap: 2rem; justify-content: space-between;">
<h1>czv playground</h1>
<button class="outline secondary" style="height: fit-content; padding: 0.25rem;" onclick="const html = document.getElementById('html');
if (html.getAttribute('data-theme') === 'light')
html.setAttribute('data-theme', 'dark')
else
html.setAttribute('data-theme', 'light')">Switch
page theme</button>
</div>
<p>Import a CSV file and get statistical data from running <a href="https://github.com/rzmk/czv">czv</a> in your
browser using WASM.</p>
<input type="file" id="upload" accept=".csv" class="hidden" />
<label for="upload" style="display: none;" id="progress">Loading...</label>
<table style="width: 100%;" class="striped">
<thead>
<tr>
<th style="width: 10rem">Output type</th>
<th>Output</th>
</tr>
</thead>
<tbody>
<tr>
<td>Row count</td>
<td id="row-count"></td>
</tr>
<tr>
<td>Column count</td>
<td id="column-count"></td>
</tr>
</tbody>
</table>
<script type="module">
const input = document.getElementById("upload")
const progress = document.getElementById("progress")
import init, * as czv from "../../pkg/czv.js";
// Must run `await init()` or `initSync()` first for web use
await init();
const fileReader = new FileReader()
fileReader.onloadstart = () => {
progress.style.display = "block";
}
fileReader.onloadend = () => {
document.getElementById("column-count").innerText = czv.columnCount(fileReader.result)
document.getElementById("row-count").innerText = czv.rowCount(fileReader.result)
progress.style.display = "none";
}
input.addEventListener("change", () => {
fileReader.readAsText(input.files[0])
})
</script>
</body>
</html>

File diff suppressed because one or more lines are too long

32
czv-wasm/src/count.rs Normal file
View file

@ -0,0 +1,32 @@
use crate::Result;
use csv::ReaderBuilder;
use wasm_bindgen::prelude::*;
/// Returns a count of the total number of rows.
///
/// @param {string} `file_data` CSV file data.
/// @param {boolean | undefined} `include_header_row` Specify whether to include the header row (first row) in the row count. Default is false.
/// @returns {number}
#[wasm_bindgen(skip_jsdoc, js_name = rowCount)]
pub fn row_count(file_data: String, include_header_row: Option<bool>) -> Result<usize> {
let mut rdr = ReaderBuilder::new();
rdr.has_headers(!include_header_row.unwrap_or(false));
return Ok(rdr.from_reader(file_data.as_bytes()).records().count());
}
/// Returns a count of the total number of columns (fields).
///
/// ## Arguments
///
/// @param {string} `file_data` CSV file data.
#[wasm_bindgen(skip_jsdoc, js_name = columnCount)]
pub fn column_count(file_data: Option<String>) -> Result<usize> {
let rdr = ReaderBuilder::new();
if let Some(file_data) = file_data {
return Ok(rdr.from_reader(file_data.as_bytes()).headers()?.len());
} else {
bail!("Could not determine a file path or file data for column_count_builder.");
}
}

30
czv-wasm/src/lib.rs Normal file
View file

@ -0,0 +1,30 @@
use wasm_bindgen::JsValue;
// Error-handling helpers
#[derive(thiserror::Error, Debug)]
#[error("{0}")]
pub struct CzvError(anyhow::Error);
impl From<csv::Error> for CzvError {
fn from(value: csv::Error) -> Self {
value.into()
}
}
impl Into<JsValue> for CzvError {
fn into(self) -> JsValue {
JsValue::from_str(self.to_string().as_str())
}
}
pub type Result<T> = anyhow::Result<T, CzvError>;
#[allow(unused_macros)]
macro_rules! bail {
($err:expr $(,)?) => {
return Err(crate::CzvError(anyhow::anyhow!($err)))
};
}
// Command imports
pub mod count;

19
czv-wasm/tests/count.rs Normal file
View file

@ -0,0 +1,19 @@
use czv_wasm;
use czv_wasm::Result;
use wasm_bindgen_test::*;
wasm_bindgen_test::wasm_bindgen_test_configure!(run_in_browser);
#[test]
#[wasm_bindgen_test]
fn basic() -> Result<()> {
let result = czv_wasm::count::row_count(
"fruit,price
apple,2.00
banana,1.50
strawberry,3.00"
.to_string(),
Some(false),
)?;
assert_eq!(result, 3);
Ok(())
}

1
czv-wasm/tests/tests.rs Normal file
View file

@ -0,0 +1 @@
mod count;