nushell/crates/nu-command/src/bytes/remove.rs

215 lines
7.1 KiB
Rust
Raw Normal View History

use crate::input_handler::{operate, CmdArgument};
use nu_engine::CallExt;
use nu_protocol::{
ast::{Call, CellPath},
engine::{Command, EngineState, Stack},
Category, Example, PipelineData, ShellError, Signature, Span, Spanned, SyntaxShape, Type,
Value,
};
struct Arguments {
pattern: Vec<u8>,
end: bool,
cell_paths: Option<Vec<CellPath>>,
all: bool,
}
impl CmdArgument for Arguments {
fn take_cell_paths(&mut self) -> Option<Vec<CellPath>> {
self.cell_paths.take()
}
}
#[derive(Clone)]
pub struct BytesRemove;
impl Command for BytesRemove {
fn name(&self) -> &str {
"bytes remove"
}
fn signature(&self) -> Signature {
Signature::build("bytes remove")
.input_output_types(vec![(Type::Binary, Type::Binary)])
.required("pattern", SyntaxShape::Binary, "the pattern to find")
.rest(
"rest",
SyntaxShape::CellPath,
"for a data structure input, remove bytes from data at the given cell paths",
)
.switch("end", "remove from end of binary", Some('e'))
.switch("all", "remove occurrences of finding binary", Some('a'))
.category(Category::Bytes)
}
fn usage(&self) -> &str {
"Remove bytes."
}
fn search_terms(&self) -> Vec<&str> {
vec!["search", "shift", "switch"]
}
fn run(
&self,
engine_state: &EngineState,
stack: &mut Stack,
call: &Call,
input: PipelineData,
) -> Result<PipelineData, ShellError> {
let cell_paths: Vec<CellPath> = call.rest(engine_state, stack, 1)?;
let cell_paths = (!cell_paths.is_empty()).then_some(cell_paths);
let pattern_to_remove = call.req::<Spanned<Vec<u8>>>(engine_state, stack, 0)?;
if pattern_to_remove.item.is_empty() {
Standardise the use of ShellError::UnsupportedInput and ShellError::TypeMismatch and add spans to every instance of the former (#7217) # Description * I was dismayed to discover recently that UnsupportedInput and TypeMismatch are used *extremely* inconsistently across the codebase. UnsupportedInput is sometimes used for input type-checks (as per the name!!), but *also* used for argument type-checks. TypeMismatch is also used for both. I thus devised the following standard: input type-checking *only* uses UnsupportedInput, and argument type-checking *only* uses TypeMismatch. Moreover, to differentiate them, UnsupportedInput now has *two* error arrows (spans), one pointing at the command and the other at the input origin, while TypeMismatch only has the one (because the command should always be nearby) * In order to apply that standard, a very large number of UnsupportedInput uses were changed so that the input's span could be retrieved and delivered to it. * Additionally, I noticed many places where **errors are not propagated correctly**: there are lots of `match` sites which take a Value::Error, then throw it away and replace it with a new Value::Error with less/misleading information (such as reporting the error as an "incorrect type"). I believe that the earliest errors are the most important, and should always be propagated where possible. * Also, to standardise one broad subset of UnsupportedInput error messages, who all used slightly different wordings of "expected `<type>`, got `<type>`", I created OnlySupportsThisInputType as a variant of it. * Finally, a bunch of error sites that had "repeated spans" - i.e. where an error expected two spans, but `call.head` was given for both - were fixed to use different spans. # Example BEFORE ``` 〉20b | str starts-with 'a' Error: nu::shell::unsupported_input (link) × Unsupported input ╭─[entry #31:1:1] 1 │ 20b | str starts-with 'a' · ┬ · ╰── Input's type is filesize. This command only works with strings. ╰──── 〉'a' | math cos Error: nu::shell::unsupported_input (link) × Unsupported input ╭─[entry #33:1:1] 1 │ 'a' | math cos · ─┬─ · ╰── Only numerical values are supported, input type: String ╰──── 〉0x[12] | encode utf8 Error: nu::shell::unsupported_input (link) × Unsupported input ╭─[entry #38:1:1] 1 │ 0x[12] | encode utf8 · ───┬── · ╰── non-string input ╰──── ``` AFTER ``` 〉20b | str starts-with 'a' Error: nu::shell::pipeline_mismatch (link) × Pipeline mismatch. ╭─[entry #1:1:1] 1 │ 20b | str starts-with 'a' · ┬ ───────┬─────── · │ ╰── only string input data is supported · ╰── input type: filesize ╰──── 〉'a' | math cos Error: nu::shell::pipeline_mismatch (link) × Pipeline mismatch. ╭─[entry #2:1:1] 1 │ 'a' | math cos · ─┬─ ────┬─── · │ ╰── only numeric input data is supported · ╰── input type: string ╰──── 〉0x[12] | encode utf8 Error: nu::shell::pipeline_mismatch (link) × Pipeline mismatch. ╭─[entry #3:1:1] 1 │ 0x[12] | encode utf8 · ───┬── ───┬── · │ ╰── only string input data is supported · ╰── input type: binary ╰──── ``` # User-Facing Changes Various error messages suddenly make more sense (i.e. have two arrows instead of one). # 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 -A clippy::needless_collect` to check that you're using the standard code style - `cargo test --workspace` to check that all tests pass # 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.
2022-12-23 06:48:53 +00:00
return Err(ShellError::TypeMismatch(
"the pattern to remove cannot be empty".to_string(),
pattern_to_remove.span,
));
}
let pattern_to_remove: Vec<u8> = pattern_to_remove.item;
let arg = Arguments {
pattern: pattern_to_remove,
end: call.has_flag("end"),
cell_paths,
all: call.has_flag("all"),
};
operate(remove, arg, input, call.head, engine_state.ctrlc.clone())
}
fn examples(&self) -> Vec<Example> {
vec![
Example {
description: "Remove contents",
example: "0x[10 AA FF AA FF] | bytes remove 0x[10 AA]",
result: Some(Value::Binary {
val: vec![0xFF, 0xAA, 0xFF],
span: Span::test_data(),
}),
},
Example {
description: "Remove all occurrences of find binary",
example: "0x[10 AA 10 BB 10] | bytes remove -a 0x[10]",
result: Some(Value::Binary {
val: vec![0xAA, 0xBB],
span: Span::test_data(),
}),
},
Example {
description: "Remove occurrences of find binary from end",
example: "0x[10 AA 10 BB CC AA 10] | bytes remove -e 0x[10]",
result: Some(Value::Binary {
val: vec![0x10, 0xAA, 0x10, 0xBB, 0xCC, 0xAA],
span: Span::test_data(),
}),
},
Example {
description: "Remove all occurrences of find binary in table",
example: "[[ColA ColB ColC]; [0x[11 12 13] 0x[14 15 16] 0x[17 18 19]]] | bytes remove 0x[11] ColA ColC",
result: Some(Value::List {
vals: vec![Value::Record {
cols: vec!["ColA".to_string(), "ColB".to_string(), "ColC".to_string()],
vals: vec![
Value::Binary {
val: vec![0x12, 0x13],
span: Span::test_data(),
},
Value::Binary {
val: vec![0x14, 0x15, 0x16],
span: Span::test_data(),
},
Value::Binary {
val: vec![0x17, 0x18, 0x19],
span: Span::test_data(),
},
],
span: Span::test_data(),
}],
span: Span::test_data(),
}),
},
]
}
}
fn remove(val: &Value, args: &Arguments, span: Span) -> Value {
match val {
Value::Binary {
val,
span: val_span,
} => remove_impl(val, args, *val_span),
Standardise the use of ShellError::UnsupportedInput and ShellError::TypeMismatch and add spans to every instance of the former (#7217) # Description * I was dismayed to discover recently that UnsupportedInput and TypeMismatch are used *extremely* inconsistently across the codebase. UnsupportedInput is sometimes used for input type-checks (as per the name!!), but *also* used for argument type-checks. TypeMismatch is also used for both. I thus devised the following standard: input type-checking *only* uses UnsupportedInput, and argument type-checking *only* uses TypeMismatch. Moreover, to differentiate them, UnsupportedInput now has *two* error arrows (spans), one pointing at the command and the other at the input origin, while TypeMismatch only has the one (because the command should always be nearby) * In order to apply that standard, a very large number of UnsupportedInput uses were changed so that the input's span could be retrieved and delivered to it. * Additionally, I noticed many places where **errors are not propagated correctly**: there are lots of `match` sites which take a Value::Error, then throw it away and replace it with a new Value::Error with less/misleading information (such as reporting the error as an "incorrect type"). I believe that the earliest errors are the most important, and should always be propagated where possible. * Also, to standardise one broad subset of UnsupportedInput error messages, who all used slightly different wordings of "expected `<type>`, got `<type>`", I created OnlySupportsThisInputType as a variant of it. * Finally, a bunch of error sites that had "repeated spans" - i.e. where an error expected two spans, but `call.head` was given for both - were fixed to use different spans. # Example BEFORE ``` 〉20b | str starts-with 'a' Error: nu::shell::unsupported_input (link) × Unsupported input ╭─[entry #31:1:1] 1 │ 20b | str starts-with 'a' · ┬ · ╰── Input's type is filesize. This command only works with strings. ╰──── 〉'a' | math cos Error: nu::shell::unsupported_input (link) × Unsupported input ╭─[entry #33:1:1] 1 │ 'a' | math cos · ─┬─ · ╰── Only numerical values are supported, input type: String ╰──── 〉0x[12] | encode utf8 Error: nu::shell::unsupported_input (link) × Unsupported input ╭─[entry #38:1:1] 1 │ 0x[12] | encode utf8 · ───┬── · ╰── non-string input ╰──── ``` AFTER ``` 〉20b | str starts-with 'a' Error: nu::shell::pipeline_mismatch (link) × Pipeline mismatch. ╭─[entry #1:1:1] 1 │ 20b | str starts-with 'a' · ┬ ───────┬─────── · │ ╰── only string input data is supported · ╰── input type: filesize ╰──── 〉'a' | math cos Error: nu::shell::pipeline_mismatch (link) × Pipeline mismatch. ╭─[entry #2:1:1] 1 │ 'a' | math cos · ─┬─ ────┬─── · │ ╰── only numeric input data is supported · ╰── input type: string ╰──── 〉0x[12] | encode utf8 Error: nu::shell::pipeline_mismatch (link) × Pipeline mismatch. ╭─[entry #3:1:1] 1 │ 0x[12] | encode utf8 · ───┬── ───┬── · │ ╰── only string input data is supported · ╰── input type: binary ╰──── ``` # User-Facing Changes Various error messages suddenly make more sense (i.e. have two arrows instead of one). # 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 -A clippy::needless_collect` to check that you're using the standard code style - `cargo test --workspace` to check that all tests pass # 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.
2022-12-23 06:48:53 +00:00
// Propagate errors by explicitly matching them before the final case.
Value::Error { .. } => val.clone(),
other => Value::Error {
Standardise the use of ShellError::UnsupportedInput and ShellError::TypeMismatch and add spans to every instance of the former (#7217) # Description * I was dismayed to discover recently that UnsupportedInput and TypeMismatch are used *extremely* inconsistently across the codebase. UnsupportedInput is sometimes used for input type-checks (as per the name!!), but *also* used for argument type-checks. TypeMismatch is also used for both. I thus devised the following standard: input type-checking *only* uses UnsupportedInput, and argument type-checking *only* uses TypeMismatch. Moreover, to differentiate them, UnsupportedInput now has *two* error arrows (spans), one pointing at the command and the other at the input origin, while TypeMismatch only has the one (because the command should always be nearby) * In order to apply that standard, a very large number of UnsupportedInput uses were changed so that the input's span could be retrieved and delivered to it. * Additionally, I noticed many places where **errors are not propagated correctly**: there are lots of `match` sites which take a Value::Error, then throw it away and replace it with a new Value::Error with less/misleading information (such as reporting the error as an "incorrect type"). I believe that the earliest errors are the most important, and should always be propagated where possible. * Also, to standardise one broad subset of UnsupportedInput error messages, who all used slightly different wordings of "expected `<type>`, got `<type>`", I created OnlySupportsThisInputType as a variant of it. * Finally, a bunch of error sites that had "repeated spans" - i.e. where an error expected two spans, but `call.head` was given for both - were fixed to use different spans. # Example BEFORE ``` 〉20b | str starts-with 'a' Error: nu::shell::unsupported_input (link) × Unsupported input ╭─[entry #31:1:1] 1 │ 20b | str starts-with 'a' · ┬ · ╰── Input's type is filesize. This command only works with strings. ╰──── 〉'a' | math cos Error: nu::shell::unsupported_input (link) × Unsupported input ╭─[entry #33:1:1] 1 │ 'a' | math cos · ─┬─ · ╰── Only numerical values are supported, input type: String ╰──── 〉0x[12] | encode utf8 Error: nu::shell::unsupported_input (link) × Unsupported input ╭─[entry #38:1:1] 1 │ 0x[12] | encode utf8 · ───┬── · ╰── non-string input ╰──── ``` AFTER ``` 〉20b | str starts-with 'a' Error: nu::shell::pipeline_mismatch (link) × Pipeline mismatch. ╭─[entry #1:1:1] 1 │ 20b | str starts-with 'a' · ┬ ───────┬─────── · │ ╰── only string input data is supported · ╰── input type: filesize ╰──── 〉'a' | math cos Error: nu::shell::pipeline_mismatch (link) × Pipeline mismatch. ╭─[entry #2:1:1] 1 │ 'a' | math cos · ─┬─ ────┬─── · │ ╰── only numeric input data is supported · ╰── input type: string ╰──── 〉0x[12] | encode utf8 Error: nu::shell::pipeline_mismatch (link) × Pipeline mismatch. ╭─[entry #3:1:1] 1 │ 0x[12] | encode utf8 · ───┬── ───┬── · │ ╰── only string input data is supported · ╰── input type: binary ╰──── ``` # User-Facing Changes Various error messages suddenly make more sense (i.e. have two arrows instead of one). # 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 -A clippy::needless_collect` to check that you're using the standard code style - `cargo test --workspace` to check that all tests pass # 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.
2022-12-23 06:48:53 +00:00
error: ShellError::OnlySupportsThisInputType(
"binary".into(),
other.get_type().to_string(),
span,
Standardise the use of ShellError::UnsupportedInput and ShellError::TypeMismatch and add spans to every instance of the former (#7217) # Description * I was dismayed to discover recently that UnsupportedInput and TypeMismatch are used *extremely* inconsistently across the codebase. UnsupportedInput is sometimes used for input type-checks (as per the name!!), but *also* used for argument type-checks. TypeMismatch is also used for both. I thus devised the following standard: input type-checking *only* uses UnsupportedInput, and argument type-checking *only* uses TypeMismatch. Moreover, to differentiate them, UnsupportedInput now has *two* error arrows (spans), one pointing at the command and the other at the input origin, while TypeMismatch only has the one (because the command should always be nearby) * In order to apply that standard, a very large number of UnsupportedInput uses were changed so that the input's span could be retrieved and delivered to it. * Additionally, I noticed many places where **errors are not propagated correctly**: there are lots of `match` sites which take a Value::Error, then throw it away and replace it with a new Value::Error with less/misleading information (such as reporting the error as an "incorrect type"). I believe that the earliest errors are the most important, and should always be propagated where possible. * Also, to standardise one broad subset of UnsupportedInput error messages, who all used slightly different wordings of "expected `<type>`, got `<type>`", I created OnlySupportsThisInputType as a variant of it. * Finally, a bunch of error sites that had "repeated spans" - i.e. where an error expected two spans, but `call.head` was given for both - were fixed to use different spans. # Example BEFORE ``` 〉20b | str starts-with 'a' Error: nu::shell::unsupported_input (link) × Unsupported input ╭─[entry #31:1:1] 1 │ 20b | str starts-with 'a' · ┬ · ╰── Input's type is filesize. This command only works with strings. ╰──── 〉'a' | math cos Error: nu::shell::unsupported_input (link) × Unsupported input ╭─[entry #33:1:1] 1 │ 'a' | math cos · ─┬─ · ╰── Only numerical values are supported, input type: String ╰──── 〉0x[12] | encode utf8 Error: nu::shell::unsupported_input (link) × Unsupported input ╭─[entry #38:1:1] 1 │ 0x[12] | encode utf8 · ───┬── · ╰── non-string input ╰──── ``` AFTER ``` 〉20b | str starts-with 'a' Error: nu::shell::pipeline_mismatch (link) × Pipeline mismatch. ╭─[entry #1:1:1] 1 │ 20b | str starts-with 'a' · ┬ ───────┬─────── · │ ╰── only string input data is supported · ╰── input type: filesize ╰──── 〉'a' | math cos Error: nu::shell::pipeline_mismatch (link) × Pipeline mismatch. ╭─[entry #2:1:1] 1 │ 'a' | math cos · ─┬─ ────┬─── · │ ╰── only numeric input data is supported · ╰── input type: string ╰──── 〉0x[12] | encode utf8 Error: nu::shell::pipeline_mismatch (link) × Pipeline mismatch. ╭─[entry #3:1:1] 1 │ 0x[12] | encode utf8 · ───┬── ───┬── · │ ╰── only string input data is supported · ╰── input type: binary ╰──── ``` # User-Facing Changes Various error messages suddenly make more sense (i.e. have two arrows instead of one). # 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 -A clippy::needless_collect` to check that you're using the standard code style - `cargo test --workspace` to check that all tests pass # 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.
2022-12-23 06:48:53 +00:00
// This line requires the Value::Error match above.
other.expect_span(),
),
},
}
}
fn remove_impl(input: &[u8], arg: &Arguments, span: Span) -> Value {
let mut result = vec![];
let remove_all = arg.all;
let input_len = input.len();
let pattern_len = arg.pattern.len();
// Note:
// remove_all from start and end will generate the same result.
// so we'll put `remove_all` relative logic into else clause.
if arg.end && !remove_all {
let (mut left, mut right) = (
input.len() as isize - arg.pattern.len() as isize,
input.len() as isize,
);
while left >= 0 && input[left as usize..right as usize] != arg.pattern {
result.push(input[right as usize - 1]);
left -= 1;
right -= 1;
}
// append the remaining thing to result, this can be happening when
// we have something to remove and remove_all is False.
let mut remain = input[..left as usize].iter().copied().rev().collect();
result.append(&mut remain);
result = result.into_iter().rev().collect();
Value::Binary { val: result, span }
} else {
let (mut left, mut right) = (0, arg.pattern.len());
while right <= input_len {
if input[left..right] == arg.pattern {
left += pattern_len;
right += pattern_len;
if !remove_all {
break;
}
} else {
result.push(input[left]);
left += 1;
right += 1;
}
}
// append the remaining thing to result, this can happened when
// we have something to remove and remove_all is False.
let mut remain = input[left..].to_vec();
result.append(&mut remain);
Value::Binary { val: result, span }
}
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn test_examples() {
use crate::test_examples;
test_examples(BytesRemove {})
}
}