nushell/crates/nu-cmd-dataframe/src/dataframe/eager/query_df.rs
JT 6cdfee3573
Move Value to helpers, separate span call (#10121)
# Description

As part of the refactor to split spans off of Value, this moves to using
helper functions to create values, and using `.span()` instead of
matching span out of Value directly.

Hoping to get a few more helping hands to finish this, as there are a
lot of commands to update :)

# User-Facing Changes
<!-- List of all changes that impact the user experience here. This
helps us keep track of breaking changes. -->

# Tests + Formatting
<!--
Don't forget to add tests that cover your changes.

Make sure you've run and fixed any issues with these commands:

- `cargo fmt --all -- --check` to check standard code formatting (`cargo
fmt --all` applies these changes)
- `cargo clippy --workspace -- -D warnings -D clippy::unwrap_used` to
check that you're using the standard code style
- `cargo test --workspace` to check that all tests pass (on Windows make
sure to [enable developer
mode](https://learn.microsoft.com/en-us/windows/apps/get-started/developer-mode-features-and-debugging))
- `cargo run -- -c "use std testing; testing run-tests --path
crates/nu-std"` to run the tests for the standard library

> **Note**
> from `nushell` you can also use the `toolkit` as follows
> ```bash
> use toolkit.nu # or use an `env_change` hook to activate it
automatically
> toolkit check pr
> ```
-->

# After Submitting
<!-- If your PR had any user-facing changes, update [the
documentation](https://github.com/nushell/nushell.github.io) after the
PR is merged, if necessary. This will help us keep the docs up to date.
-->

---------

Co-authored-by: Darren Schroeder <343840+fdncred@users.noreply.github.com>
Co-authored-by: WindSoilder <windsoilder@outlook.com>
2023-09-03 07:27:29 -07:00

106 lines
3.0 KiB
Rust

use super::super::values::NuDataFrame;
use crate::dataframe::values::Column;
use crate::dataframe::{eager::SQLContext, values::NuLazyFrame};
use nu_engine::CallExt;
use nu_protocol::{
ast::Call,
engine::{Command, EngineState, Stack},
Category, Example, PipelineData, ShellError, Signature, Span, SyntaxShape, Type, Value,
};
// attribution:
// sql_context.rs, and sql_expr.rs were copied from polars-sql. thank you.
// maybe we should just use the crate at some point but it's not published yet.
// https://github.com/pola-rs/polars/tree/master/polars-sql
#[derive(Clone)]
pub struct QueryDf;
impl Command for QueryDf {
fn name(&self) -> &str {
"dfr query"
}
fn usage(&self) -> &str {
"Query dataframe using SQL. Note: The dataframe is always named 'df' in your query's from clause."
}
fn signature(&self) -> Signature {
Signature::build(self.name())
.required("sql", SyntaxShape::String, "sql query")
.input_output_type(
Type::Custom("dataframe".into()),
Type::Custom("dataframe".into()),
)
.category(Category::Custom("dataframe".into()))
}
fn search_terms(&self) -> Vec<&str> {
vec!["dataframe", "sql", "search"]
}
fn examples(&self) -> Vec<Example> {
vec![Example {
description: "Query dataframe using SQL",
example: "[[a b]; [1 2] [3 4]] | dfr into-df | dfr query 'select a from df'",
result: Some(
NuDataFrame::try_from_columns(vec![Column::new(
"a".to_string(),
vec![Value::test_int(1), Value::test_int(3)],
)])
.expect("simple df for test should not fail")
.into_value(Span::test_data()),
),
}]
}
fn run(
&self,
engine_state: &EngineState,
stack: &mut Stack,
call: &Call,
input: PipelineData,
) -> Result<PipelineData, ShellError> {
command(engine_state, stack, call, input)
}
}
fn command(
engine_state: &EngineState,
stack: &mut Stack,
call: &Call,
input: PipelineData,
) -> Result<PipelineData, ShellError> {
let sql_query: String = call.req(engine_state, stack, 0)?;
let df = NuDataFrame::try_from_pipeline(input, call.head)?;
let mut ctx = SQLContext::new();
ctx.register("df", &df.df);
let df_sql = ctx.execute(&sql_query).map_err(|e| {
ShellError::GenericError(
"Dataframe Error".into(),
e.to_string(),
Some(call.head),
None,
Vec::new(),
)
})?;
let lazy = NuLazyFrame::new(false, df_sql);
let eager = lazy.collect(call.head)?;
let value = Value::custom_value(Box::new(eager), call.head);
Ok(PipelineData::Value(value, None))
}
#[cfg(test)]
mod test {
use super::super::super::test_dataframe::test_dataframe;
use super::*;
#[test]
fn test_examples() {
test_dataframe(vec![Box::new(QueryDf {})])
}
}