mirror of
https://github.com/nushell/nushell
synced 2024-12-29 06:23:11 +00:00
56ed1eb807
<!-- if this PR closes one or more issues, you can automatically link the PR with them by using one of the [*linking keywords*](https://docs.github.com/en/issues/tracking-your-work-with-issues/linking-a-pull-request-to-an-issue#linking-a-pull-request-to-an-issue-using-a-keyword), e.g. - this PR should close #xxxx - fixes #xxxx --> # Description This PR implements the workaround discussed in #9795, i.e. having `parse` collect an external stream before operating on it with a regex. - Should close #9795 # User-Facing Changes <!-- List of all changes that impact the user experience here. This helps us keep track of breaking changes. --> - `parse` will give the correct output for external streams - increased memory and time overhead due to collecting the entire stream (no short-circuiting) # 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 -A clippy::result_large_err` to check that you're using the standard code style - `cargo test --workspace` to check that all tests pass - `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 > ``` --> - formatting is checked - clippy is happy - no tests that weren't already broken fail - added test case # 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. -->
229 lines
6.5 KiB
Rust
229 lines
6.5 KiB
Rust
use nu_test_support::fs::Stub;
|
|
use nu_test_support::playground::Playground;
|
|
use nu_test_support::{nu, pipeline};
|
|
|
|
mod simple {
|
|
use super::*;
|
|
|
|
#[test]
|
|
fn extracts_fields_from_the_given_the_pattern() {
|
|
Playground::setup("parse_test_1", |dirs, sandbox| {
|
|
sandbox.with_files(vec![Stub::FileWithContentToBeTrimmed(
|
|
"key_value_separated_arepa_ingredients.txt",
|
|
r#"
|
|
VAR1=Cheese
|
|
VAR2=JTParsed
|
|
VAR3=NushellSecretIngredient
|
|
"#,
|
|
)]);
|
|
|
|
let actual = nu!(
|
|
cwd: dirs.test(), pipeline(
|
|
r#"
|
|
open key_value_separated_arepa_ingredients.txt
|
|
| lines
|
|
| each { |it| echo $it | parse "{Name}={Value}" }
|
|
| flatten
|
|
| get 1
|
|
| get Value
|
|
"#
|
|
));
|
|
|
|
assert_eq!(actual.out, "JTParsed");
|
|
})
|
|
}
|
|
|
|
#[test]
|
|
fn double_open_curly_evaluates_to_a_single_curly() {
|
|
Playground::setup("parse_test_regex_2", |dirs, _sandbox| {
|
|
let actual = nu!(
|
|
cwd: dirs.test(), pipeline(
|
|
r#"
|
|
echo "{abc}123"
|
|
| parse "{{abc}{name}"
|
|
| get name.0
|
|
"#
|
|
));
|
|
|
|
assert_eq!(actual.out, "123");
|
|
})
|
|
}
|
|
|
|
#[test]
|
|
fn properly_escapes_text() {
|
|
Playground::setup("parse_test_regex_3", |dirs, _sandbox| {
|
|
let actual = nu!(
|
|
cwd: dirs.test(), pipeline(
|
|
r#"
|
|
echo "(abc)123"
|
|
| parse "(abc){name}"
|
|
| get name.0
|
|
"#
|
|
));
|
|
|
|
assert_eq!(actual.out, "123");
|
|
})
|
|
}
|
|
|
|
#[test]
|
|
fn properly_captures_empty_column() {
|
|
Playground::setup("parse_test_regex_4", |dirs, _sandbox| {
|
|
let actual = nu!(
|
|
cwd: dirs.test(), pipeline(
|
|
r#"
|
|
echo ["1:INFO:component:all is well" "2:ERROR::something bad happened"]
|
|
| parse "{timestamp}:{level}:{tag}:{entry}"
|
|
| get entry
|
|
| get 1
|
|
"#
|
|
));
|
|
|
|
assert_eq!(actual.out, "something bad happened");
|
|
})
|
|
}
|
|
|
|
#[test]
|
|
fn errors_when_missing_closing_brace() {
|
|
Playground::setup("parse_test_regex_5", |dirs, _sandbox| {
|
|
let actual = nu!(
|
|
cwd: dirs.test(), pipeline(
|
|
r#"
|
|
echo "(abc)123"
|
|
| parse "(abc){name"
|
|
| get name
|
|
"#
|
|
));
|
|
|
|
assert!(actual
|
|
.err
|
|
.contains("Found opening `{` without an associated closing `}`"));
|
|
})
|
|
}
|
|
}
|
|
|
|
mod regex {
|
|
use super::*;
|
|
|
|
fn nushell_git_log_oneline<'a>() -> Vec<Stub<'a>> {
|
|
vec![Stub::FileWithContentToBeTrimmed(
|
|
"nushell_git_log_oneline.txt",
|
|
r#"
|
|
ae87582c Fix missing invocation errors (#1846)
|
|
b89976da let format access variables also (#1842)
|
|
"#,
|
|
)]
|
|
}
|
|
|
|
#[test]
|
|
fn extracts_fields_with_all_named_groups() {
|
|
Playground::setup("parse_test_regex_1", |dirs, sandbox| {
|
|
sandbox.with_files(nushell_git_log_oneline());
|
|
|
|
let actual = nu!(
|
|
cwd: dirs.test(), pipeline(
|
|
r#"
|
|
open nushell_git_log_oneline.txt
|
|
| parse --regex "(?P<Hash>\\w+) (?P<Message>.+) \\(#(?P<PR>\\d+)\\)"
|
|
| get 1
|
|
| get PR
|
|
"#
|
|
));
|
|
|
|
assert_eq!(actual.out, "1842");
|
|
})
|
|
}
|
|
|
|
#[test]
|
|
fn extracts_fields_with_all_unnamed_groups() {
|
|
Playground::setup("parse_test_regex_2", |dirs, sandbox| {
|
|
sandbox.with_files(nushell_git_log_oneline());
|
|
|
|
let actual = nu!(
|
|
cwd: dirs.test(), pipeline(
|
|
r#"
|
|
open nushell_git_log_oneline.txt
|
|
| parse --regex "(\\w+) (.+) \\(#(\\d+)\\)"
|
|
| get 1
|
|
| get capture0
|
|
"#
|
|
));
|
|
|
|
assert_eq!(actual.out, "b89976da");
|
|
})
|
|
}
|
|
|
|
#[test]
|
|
fn extracts_fields_with_named_and_unnamed_groups() {
|
|
Playground::setup("parse_test_regex_3", |dirs, sandbox| {
|
|
sandbox.with_files(nushell_git_log_oneline());
|
|
|
|
let actual = nu!(
|
|
cwd: dirs.test(), pipeline(
|
|
r#"
|
|
open nushell_git_log_oneline.txt
|
|
| parse --regex "(?P<Hash>\\w+) (.+) \\(#(?P<PR>\\d+)\\)"
|
|
| get 1
|
|
| get capture1
|
|
"#
|
|
));
|
|
|
|
assert_eq!(actual.out, "let format access variables also");
|
|
})
|
|
}
|
|
|
|
#[test]
|
|
fn errors_with_invalid_regex() {
|
|
Playground::setup("parse_test_regex_1", |dirs, sandbox| {
|
|
sandbox.with_files(nushell_git_log_oneline());
|
|
|
|
let actual = nu!(
|
|
cwd: dirs.test(), pipeline(
|
|
r#"
|
|
open nushell_git_log_oneline.txt
|
|
| parse --regex "(?P<Hash>\\w+ unfinished capture group"
|
|
"#
|
|
));
|
|
|
|
assert!(actual
|
|
.err
|
|
.contains("Opening parenthesis without closing parenthesis"));
|
|
})
|
|
}
|
|
|
|
#[test]
|
|
fn parse_works_with_streaming() {
|
|
let actual =
|
|
nu!(r#"seq char a z | each {|c| $c + " a"} | parse '{letter} {a}' | describe"#);
|
|
|
|
assert_eq!(actual.out, "table<letter: string, a: string> (stream)")
|
|
}
|
|
|
|
#[test]
|
|
fn parse_does_not_truncate_list_streams() {
|
|
let actual = nu!(pipeline(
|
|
r#"
|
|
[a b c]
|
|
| each {|x| $x}
|
|
| parse --regex "[ac]"
|
|
| length
|
|
"#
|
|
));
|
|
|
|
assert_eq!(actual.out, "2");
|
|
}
|
|
|
|
#[test]
|
|
fn parse_handles_external_stream_chunking() {
|
|
Playground::setup("parse_test_streaming_1", |dirs, _sandbox| {
|
|
let actual = nu!(
|
|
cwd: dirs.test(), pipeline(
|
|
r#"
|
|
"abcdefghijklmnopqrstuvwxyz" * 1000 | save --force data.txt;
|
|
open data.txt | parse --regex "(abcdefghijklmnopqrstuvwxyz)" | length
|
|
"#
|
|
));
|
|
|
|
assert_eq!(actual.out, "1000");
|
|
})
|
|
}
|
|
}
|