mirror of
https://github.com/nushell/nushell
synced 2024-12-27 05:23:11 +00:00
7efb31a4e4
Restructure and streamline token expansion The purpose of this commit is to streamline the token expansion code, by removing aspects of the code that are no longer relevant, removing pointless duplication, and eliminating the need to pass the same arguments to `expand_syntax`. The first big-picture change in this commit is that instead of a handful of `expand_` functions, which take a TokensIterator and ExpandContext, a smaller number of methods on the `TokensIterator` do the same job. The second big-picture change in this commit is fully eliminating the coloring traits, making coloring a responsibility of the base expansion implementations. This also means that the coloring tracer is merged into the expansion tracer, so you can follow a single expansion and see how the expansion process produced colored tokens. One side effect of this change is that the expander itself is marginally more error-correcting. The error correction works by switching from structured expansion to `BackoffColoringMode` when an unexpected token is found, which guarantees that all spans of the source are colored, but may not be the most optimal error recovery strategy. That said, because `BackoffColoringMode` only extends as far as a closing delimiter (`)`, `]`, `}`) or pipe (`|`), it does result in fairly granular correction strategy. The current code still produces an `Err` (plus a complete list of colored shapes) from the parsing process if any errors are encountered, but this could easily be addressed now that the underlying expansion is error-correcting. This commit also colors any spans that are syntax errors in red, and causes the parser to include some additional information about what tokens were expected at any given point where an error was encountered, so that completions and hinting could be more robust in the future. Co-authored-by: Jonathan Turner <jonathandturner@users.noreply.github.com> Co-authored-by: Andrés N. Robalino <andres@androbtech.com>
230 lines
7.9 KiB
Rust
230 lines
7.9 KiB
Rust
use nu_test_support::fs::Stub::FileWithContentToBeTrimmed;
|
|
use nu_test_support::playground::Playground;
|
|
use nu_test_support::{nu, nu_error, pipeline};
|
|
|
|
#[test]
|
|
fn parses_csv() {
|
|
Playground::setup("open_test_1", |dirs, sandbox| {
|
|
sandbox.with_files(vec![FileWithContentToBeTrimmed(
|
|
"nu.zion.csv",
|
|
r#"
|
|
author,lang,source
|
|
Jonathan Turner,Rust,New Zealand
|
|
Andres N. Robalino,Rust,Ecuador
|
|
Yehuda Katz,Rust,Estados Unidos
|
|
"#,
|
|
)]);
|
|
|
|
let actual = nu!(
|
|
cwd: dirs.test(), pipeline(
|
|
r#"
|
|
open nu.zion.csv
|
|
| where author == "Andres N. Robalino"
|
|
| get source
|
|
| echo $it
|
|
"#
|
|
));
|
|
|
|
assert_eq!(actual, "Ecuador");
|
|
})
|
|
}
|
|
|
|
// sample.bson has the following format:
|
|
// ━━━━━━━━━━┯━━━━━━━━━━━
|
|
// _id │ root
|
|
// ──────────┼───────────
|
|
// [object] │ [9 items]
|
|
// ━━━━━━━━━━┷━━━━━━━━━━━
|
|
//
|
|
// the root value is:
|
|
// ━━━┯━━━━━━━━━━━━━━━━━━━┯━━━━━━━━━━━━━━━━━━━━━━━━━┯━━━━━━━━━━┯━━━━━━━━━━
|
|
// # │ _id │ a │ b │ c
|
|
// ───┼───────────────────┼─────────────────────────┼──────────┼──────────
|
|
// 0 │ [object] │ 1.000000000000000 │ hello │ [2 items]
|
|
// 1 │ [object] │ 42.00000000000000 │ whel │ hello
|
|
// 2 │ [object] │ [object] │ │
|
|
// 3 │ [object] │ │ [object] │
|
|
// 4 │ [object] │ │ │ [object]
|
|
// 5 │ [object] │ │ │ [object]
|
|
// 6 │ [object] │ [object] │ [object] │
|
|
// 7 │ [object] │ <date value> │ [object] │
|
|
// 8 │ 1.000000 │ <decimal value> │ [object] │
|
|
//
|
|
// The decimal value is supposed to be π, but is currently wrong due to
|
|
// what appears to be an issue in the bson library that is under investigation.
|
|
//
|
|
|
|
#[test]
|
|
fn parses_bson() {
|
|
let actual = nu!(
|
|
cwd: "tests/fixtures/formats",
|
|
"open sample.bson | get root | nth 0 | get b | echo $it"
|
|
);
|
|
|
|
assert_eq!(actual, "hello");
|
|
}
|
|
|
|
#[test]
|
|
fn parses_more_bson_complexity() {
|
|
let actual = nu!(
|
|
cwd: "tests/fixtures/formats", pipeline(
|
|
r#"
|
|
open sample.bson
|
|
| get root
|
|
| nth 6
|
|
| get b
|
|
| get '$binary_subtype'
|
|
| echo $it
|
|
"#
|
|
));
|
|
|
|
assert_eq!(actual, "function");
|
|
}
|
|
|
|
// sample.db has the following format:
|
|
//
|
|
// ━━━┯━━━━━━━━━━━━┯━━━━━━━━━━━━━━
|
|
// # │ table_name │ table_values
|
|
// ───┼────────────┼──────────────
|
|
// 0 │ strings │ [6 items]
|
|
// 1 │ ints │ [5 items]
|
|
// 2 │ floats │ [4 items]
|
|
// ━━━┷━━━━━━━━━━━━┷━━━━━━━━━━━━━━
|
|
//
|
|
// In this case, this represents a sqlite database
|
|
// with three tables named `strings`, `ints`, and `floats`.
|
|
// The table_values represent the values for the tables:
|
|
//
|
|
// ━━━━┯━━━━━━━┯━━━━━━━━━━┯━━━━━━┯━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
|
// # │ x │ y │ z │ f
|
|
// ────┼───────┼──────────┼──────┼──────────────────────────────────────────────────────────────────────
|
|
// 0 │ hello │ <binary> │ │
|
|
// 1 │ hello │ <binary> │ │
|
|
// 2 │ hello │ <binary> │ │
|
|
// 3 │ hello │ <binary> │ │
|
|
// 4 │ world │ <binary> │ │
|
|
// 5 │ world │ <binary> │ │
|
|
// 6 │ │ │ 1 │
|
|
// 7 │ │ │ 42 │
|
|
// 8 │ │ │ 425 │
|
|
// 9 │ │ │ 4253 │
|
|
// 10 │ │ │ │
|
|
// 11 │ │ │ │ 3.400000000000000
|
|
// 12 │ │ │ │ 3.141592650000000
|
|
// 13 │ │ │ │ 23.00000000000000
|
|
// 14 │ │ │ │ this string that doesn't really belong here but sqlite is what it is
|
|
// ━━━━┷━━━━━━━┷━━━━━━━━━━┷━━━━━━┷━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
|
//
|
|
// We can see here that each table has different columns. `strings` has `x` and `y`, while
|
|
// `ints` has just `z`, and `floats` has only the column `f`. This means, in general, when working
|
|
// with sqlite, one will want to select a single table, e.g.:
|
|
//
|
|
// open sample.db | nth 1 | get table_values
|
|
// ━━━┯━━━━━━
|
|
// # │ z
|
|
// ───┼──────
|
|
// 0 │ 1
|
|
// 1 │ 42
|
|
// 2 │ 425
|
|
// 3 │ 4253
|
|
// 4 │
|
|
// ━━━┷━━━━━━
|
|
|
|
#[test]
|
|
fn parses_sqlite() {
|
|
let actual = nu!(
|
|
cwd: "tests/fixtures/formats", pipeline(
|
|
r#"
|
|
open sample.db
|
|
| get table_values
|
|
| nth 2
|
|
| get x
|
|
| echo $it
|
|
"#
|
|
));
|
|
|
|
assert_eq!(actual, "hello");
|
|
}
|
|
|
|
#[test]
|
|
fn parses_toml() {
|
|
let actual = nu!(
|
|
cwd: "tests/fixtures/formats",
|
|
"open cargo_sample.toml | get package.edition | echo $it"
|
|
);
|
|
|
|
assert_eq!(actual, "2018");
|
|
}
|
|
|
|
#[test]
|
|
fn parses_tsv() {
|
|
let actual = nu!(
|
|
cwd: "tests/fixtures/formats", pipeline(
|
|
r#"
|
|
open caco3_plastics.tsv
|
|
| first 1
|
|
| get origin
|
|
| echo $it
|
|
"#
|
|
));
|
|
|
|
assert_eq!(actual, "SPAIN")
|
|
}
|
|
|
|
#[test]
|
|
fn parses_json() {
|
|
let actual = nu!(
|
|
cwd: "tests/fixtures/formats", pipeline(
|
|
r#"
|
|
open sgml_description.json
|
|
| get glossary.GlossDiv.GlossList.GlossEntry.GlossSee
|
|
| echo $it
|
|
"#
|
|
));
|
|
|
|
assert_eq!(actual, "markup")
|
|
}
|
|
|
|
#[test]
|
|
fn parses_xml() {
|
|
let actual = nu!(
|
|
cwd: "tests/fixtures/formats",
|
|
"open jonathan.xml | get rss.channel | get item | get link | echo $it"
|
|
);
|
|
|
|
assert_eq!(
|
|
actual,
|
|
"http://www.jonathanturner.org/2015/10/off-to-new-adventures.html"
|
|
)
|
|
}
|
|
|
|
#[test]
|
|
fn parses_ini() {
|
|
let actual = nu!(
|
|
cwd: "tests/fixtures/formats",
|
|
"open sample.ini | get SectionOne.integer | echo $it"
|
|
);
|
|
|
|
assert_eq!(actual, "1234")
|
|
}
|
|
|
|
#[test]
|
|
fn parses_utf16_ini() {
|
|
let actual = nu!(
|
|
cwd: "tests/fixtures/formats",
|
|
"open utf16.ini | get '.ShellClassInfo' | get IconIndex | echo $it"
|
|
);
|
|
|
|
assert_eq!(actual, "-236")
|
|
}
|
|
|
|
#[test]
|
|
fn errors_if_file_not_found() {
|
|
let actual = nu_error!(
|
|
cwd: "tests/fixtures/formats",
|
|
"open i_dont_exist.txt"
|
|
);
|
|
|
|
assert!(actual.contains("File could not be opened"));
|
|
assert!(actual.contains("file not found"));
|
|
}
|