f879c00f9d
# Description
There are times where explicitly specifying a schema for a dataframe is
needed such as:
- Opening CSV and JSON lines files and needing provide more information
to polars to keep it from failing or in a desire to override default
type conversion
- When converting a nushell value to a dataframe and wanting to override
the default conversion behaviors.
This pull requests provides:
- A flag to allow specifying a schema when using dfr into-df
- A flag to allow specifying a schema when using dfr open that works for
CSV and JSON types
- A new command `dfr schema` which displays schema information and will
allow display support schema dtypes
Schema is specified creating a record that has the key value and the
dtype. Examples usages:
```
{a:1, b:{a:2}} | dfr into-df -s {a: u8, b: {a: i32}} | dfr schema
{a: 1, b: {a: [1 2 3]}, c: [a b c]} | dfr into-df -s {a: u8, b: {a: list<u64>}, c: list<str>} | dfr schema
dfr open -s {pid: i32, ppid: i32, name: str, status: str, cpu: f64, mem: i64, virtual: i64} /tmp/ps.jsonl | dfr schema
```
Supported dtypes:
null
bool
u8
u16
u32
u64
i8
i16
i32
i64
f32
f64
str
binary
date
datetime[time_unit: (ms, us, ns) timezone (optional)]
duration[time_unit: (ms, us, ns)]
time
object
unknown
list[dtype]
structs are also supported but are specified via another record:
{a: u8, b: {d: str}}
Another feature with the dfr schema command is that it returns the data
back in a format that can be passed to provide a valid schema that can
be passed in as schema argument:
<img width="638" alt="Screenshot 2024-01-29 at 10 23 58"
src="https://github.com/nushell/nushell/assets/56345/b49c3bff-5cda-4c86-975a-dfd91d991373">
---------
Co-authored-by: Jack Wright <jack.wright@disqo.com>
109 lines
3.1 KiB
Rust
109 lines
3.1 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)],
|
|
)],
|
|
None,
|
|
)
|
|
.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 {
|
|
error: "Dataframe Error".into(),
|
|
msg: e.to_string(),
|
|
span: Some(call.head),
|
|
help: None,
|
|
inner: vec![],
|
|
})?;
|
|
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 {})])
|
|
}
|
|
}
|