nushell/crates/nu-cli/src/commands/get.rs

264 lines
9.6 KiB
Rust
Raw Normal View History

2019-08-15 07:02:02 +02:00
use crate::commands::WholeStreamCommand;
2019-05-29 06:02:36 +02:00
use crate::prelude::*;
use indexmap::set::IndexSet;
Overhaul the expansion system The main thrust of this (very large) commit is an overhaul of the expansion system. The parsing pipeline is: - Lightly parse the source file for atoms, basic delimiters and pipeline structure into a token tree - Expand the token tree into a HIR (high-level intermediate representation) based upon the baseline syntax rules for expressions and the syntactic shape of commands. Somewhat non-traditionally, nu doesn't have an AST at all. It goes directly from the token tree, which doesn't represent many important distinctions (like the difference between `hello` and `5KB`) directly into a high-level representation that doesn't have a direct correspondence to the source code. At a high level, nu commands work like macros, in the sense that the syntactic shape of the invocation of a command depends on the definition of a command. However, commands do not have the ability to perform unrestricted expansions of the token tree. Instead, they describe their arguments in terms of syntactic shapes, and the expander expands the token tree into HIR based upon that definition. For example, the `where` command says that it takes a block as its first required argument, and the description of the block syntactic shape expands the syntax `cpu > 10` into HIR that represents `{ $it.cpu > 10 }`. This commit overhauls that system so that the syntactic shapes are described in terms of a few new traits (`ExpandSyntax` and `ExpandExpression` are the primary ones) that are more composable than the previous system. The first big win of this new system is the addition of the `ColumnPath` shape, which looks like `cpu."max ghz"` or `package.version`. Previously, while a variable path could look like `$it.cpu."max ghz"`, the tail of a variable path could not be easily reused in other contexts. Now, that tail is its own syntactic shape, and it can be used as part of a command's signature. This cleans up commands like `inc`, `add` and `edit` as well as shorthand blocks, which can now look like `| where cpu."max ghz" > 10`
2019-09-18 00:26:27 +02:00
use log::trace;
use nu_errors::ShellError;
use nu_protocol::{
did_you_mean, ColumnPath, PathMember, Primitive, ReturnSuccess, Signature, SyntaxShape,
UnspannedPathMember, UntaggedValue, Value,
};
use nu_source::HasFallibleSpan;
2019-12-09 19:52:01 +01:00
use nu_value_ext::get_data_by_column_path;
2019-05-29 06:02:36 +02:00
2019-08-02 21:15:07 +02:00
pub struct Get;
#[derive(Deserialize)]
pub struct GetArgs {
Overhaul the expansion system The main thrust of this (very large) commit is an overhaul of the expansion system. The parsing pipeline is: - Lightly parse the source file for atoms, basic delimiters and pipeline structure into a token tree - Expand the token tree into a HIR (high-level intermediate representation) based upon the baseline syntax rules for expressions and the syntactic shape of commands. Somewhat non-traditionally, nu doesn't have an AST at all. It goes directly from the token tree, which doesn't represent many important distinctions (like the difference between `hello` and `5KB`) directly into a high-level representation that doesn't have a direct correspondence to the source code. At a high level, nu commands work like macros, in the sense that the syntactic shape of the invocation of a command depends on the definition of a command. However, commands do not have the ability to perform unrestricted expansions of the token tree. Instead, they describe their arguments in terms of syntactic shapes, and the expander expands the token tree into HIR based upon that definition. For example, the `where` command says that it takes a block as its first required argument, and the description of the block syntactic shape expands the syntax `cpu > 10` into HIR that represents `{ $it.cpu > 10 }`. This commit overhauls that system so that the syntactic shapes are described in terms of a few new traits (`ExpandSyntax` and `ExpandExpression` are the primary ones) that are more composable than the previous system. The first big win of this new system is the addition of the `ColumnPath` shape, which looks like `cpu."max ghz"` or `package.version`. Previously, while a variable path could look like `$it.cpu."max ghz"`, the tail of a variable path could not be easily reused in other contexts. Now, that tail is its own syntactic shape, and it can be used as part of a command's signature. This cleans up commands like `inc`, `add` and `edit` as well as shorthand blocks, which can now look like `| where cpu."max ghz" > 10`
2019-09-18 00:26:27 +02:00
rest: Vec<ColumnPath>,
2019-08-02 21:15:07 +02:00
}
2020-05-29 10:22:52 +02:00
#[async_trait]
2019-08-15 07:02:02 +02:00
impl WholeStreamCommand for Get {
2019-08-02 21:15:07 +02:00
fn name(&self) -> &str {
"get"
}
fn signature(&self) -> Signature {
2019-11-04 16:47:03 +01:00
Signature::build("get").rest(
SyntaxShape::ColumnPath,
"optionally return additional data by path",
)
}
fn usage(&self) -> &str {
"Open given cells as text."
}
2020-05-29 10:22:52 +02:00
async fn run(
2019-08-02 21:15:07 +02:00
&self,
args: CommandArgs,
registry: &CommandRegistry,
) -> Result<OutputStream, ShellError> {
get(args, registry).await
2019-08-02 21:15:07 +02:00
}
fn examples(&self) -> Vec<Example> {
vec![
Example {
description: "Extract the name of files as a list",
example: "ls | get name",
result: None,
},
Example {
description: "Extract the cpu list from the sys information",
example: "sys | get cpu",
result: None,
},
]
}
2019-08-02 21:15:07 +02:00
}
pub fn get_column_path(path: &ColumnPath, obj: &Value) -> Result<Value, ShellError> {
let fields = path.clone();
get_data_by_column_path(
obj,
path,
2019-11-04 16:47:03 +01:00
Box::new(move |(obj_source, column_path_tried, error)| {
let path_members_span = fields.maybe_span().unwrap_or_else(Span::unknown);
match &obj_source.value {
UntaggedValue::Table(rows) => match column_path_tried {
PathMember {
unspanned: UnspannedPathMember::String(column),
..
} => {
let primary_label = format!("There isn't a column named '{}'", &column);
let suggestions: IndexSet<_> = rows
.iter()
.filter_map(|r| did_you_mean(&r, &column_path_tried))
.map(|s| s[0].1.to_owned())
.collect();
let mut existing_columns: IndexSet<_> = IndexSet::default();
let mut names: Vec<String> = vec![];
for row in rows {
for field in row.data_descriptors() {
if !existing_columns.contains(&field[..]) {
existing_columns.insert(field.clone());
names.push(field);
}
}
}
if names.is_empty() {
return ShellError::labeled_error_with_secondary(
"Unknown column",
primary_label,
column_path_tried.span,
"Appears to contain rows. Try indexing instead.",
column_path_tried.span.since(path_members_span),
);
} else {
return ShellError::labeled_error_with_secondary(
"Unknown column",
primary_label,
column_path_tried.span,
format!(
"Perhaps you meant '{}'? Columns available: {}",
suggestions
.iter()
.map(|x| x.to_owned())
.collect::<Vec<String>>()
.join(","),
names.join(",")
),
column_path_tried.span.since(path_members_span),
);
};
}
PathMember {
unspanned: UnspannedPathMember::Int(idx),
..
} => {
let total = rows.len();
let secondary_label = if total == 1 {
"The table only has 1 row".to_owned()
} else {
format!("The table only has {} rows (0 to {})", total, total - 1)
};
return ShellError::labeled_error_with_secondary(
"Row not found",
format!("There isn't a row indexed at {}", idx),
column_path_tried.span,
secondary_label,
column_path_tried.span.since(path_members_span),
);
}
},
UntaggedValue::Row(columns) => match column_path_tried {
PathMember {
unspanned: UnspannedPathMember::String(column),
..
} => {
let primary_label = format!("There isn't a column named '{}'", &column);
if let Some(suggestions) = did_you_mean(&obj_source, column_path_tried) {
return ShellError::labeled_error_with_secondary(
"Unknown column",
primary_label,
column_path_tried.span,
format!(
"Perhaps you meant '{}'? Columns available: {}",
suggestions[0].1,
&obj_source.data_descriptors().join(",")
),
column_path_tried.span.since(path_members_span),
);
}
}
PathMember {
unspanned: UnspannedPathMember::Int(idx),
..
} => {
return ShellError::labeled_error_with_secondary(
"No rows available",
format!("A row at '{}' can't be indexed.", &idx),
column_path_tried.span,
format!(
"Appears to contain columns. Columns available: {}",
columns.keys().join(",")
),
column_path_tried.span.since(path_members_span),
)
}
},
_ => {}
2019-10-31 10:36:08 +01:00
}
if let Some(suggestions) = did_you_mean(&obj_source, column_path_tried) {
return ShellError::labeled_error(
"Unknown column",
format!("did you mean '{}'?", suggestions[0].1),
column_path_tried.span.since(path_members_span),
);
}
2019-11-04 16:47:03 +01:00
error
}),
)
}
pub async fn get(
args: CommandArgs,
registry: &CommandRegistry,
) -> Result<OutputStream, ShellError> {
let registry = registry.clone();
let (GetArgs { rest: mut fields }, mut input) = args.process(&registry).await?;
if fields.is_empty() {
let vec = input.drain_vec().await;
2019-11-04 16:47:03 +01:00
let descs = nu_protocol::merge_descriptors(&vec);
Ok(futures::stream::iter(descs.into_iter().map(ReturnSuccess::value)).to_output_stream())
} else {
let member = fields.remove(0);
trace!("get {:?} {:?}", member, fields);
Ok(input
.map(move |item| {
2019-11-04 16:47:03 +01:00
let member = vec![member.clone()];
let column_paths = vec![&member, &fields]
.into_iter()
.flatten()
.collect::<Vec<&ColumnPath>>();
let mut output = vec![];
2019-11-04 16:47:03 +01:00
for path in column_paths {
let res = get_column_path(&path, &item);
match res {
Ok(got) => match got {
Value {
value: UntaggedValue::Table(rows),
2019-11-04 16:47:03 +01:00
..
} => {
for item in rows {
output.push(ReturnSuccess::value(item.clone()));
2019-11-04 16:47:03 +01:00
}
}
Value {
value: UntaggedValue::Primitive(Primitive::Nothing),
..
} => {}
other => output.push(ReturnSuccess::value(other.clone())),
2019-11-04 16:47:03 +01:00
},
Err(reason) => output.push(ReturnSuccess::value(
UntaggedValue::Error(reason).into_untagged_value(),
)),
2019-11-04 16:47:03 +01:00
}
2019-05-29 06:02:36 +02:00
}
futures::stream::iter(output)
})
.flatten()
.to_output_stream())
}
2019-05-29 06:02:36 +02:00
}
#[cfg(test)]
mod tests {
use super::Get;
#[test]
fn examples_work_as_expected() {
use crate::examples::test as test_examples;
test_examples(Get {})
}
}