Additional flags for commands from csv and from tsv (#8398)

# Description

Resolves issue #8370

Adds the following flags to commands `from csv` and `from tsv`:
- `--flexible`: allow the number of fields in records to be variable
- `-c --comment`: a comment character to ignore lines starting with it
- `-q --quote`: a quote character to ignore separators in strings,
defaults to '\"'
- `-e --escape`: an escape character for strings containing the quote
character

Internally, the `Value` struct has an additional helper function
`as_char` which converts it to a single `char`

# User-Facing Changes

The single quoted string `'\t'` can no longer be used as a parameter for
the flag `--separator '\t'` as it is interpreted as a two-character
string. One needs to use from now on the flag with a double quoted
string like so: `-s "\t"` which correctly interprets the string as a
single `char`.
This commit is contained in:
Matthew Deville
2023-03-16 23:49:46 +01:00
committed by GitHub
parent bdaa01165e
commit 8543b0789d
6 changed files with 494 additions and 54 deletions

View File

@ -183,8 +183,92 @@ fn from_csv_text_with_tab_separator_to_table() {
}
#[test]
fn from_csv_text_skipping_headers_to_table() {
fn from_csv_text_with_comments_to_table() {
Playground::setup("filter_from_csv_test_5", |dirs, sandbox| {
sandbox.with_files(vec![FileWithContentToBeTrimmed(
"los_tres_caballeros.txt",
r#"
# This is a comment
first_name,last_name,rusty_luck
# This one too
Andrés,Robalino,1
Jonathan,Turner,1
Yehuda,Katz,1
# This one also
"#,
)]);
let actual = nu!(
cwd: dirs.test(), pipeline(
r##"
open los_tres_caballeros.txt
| from csv --comment "#"
| get rusty_luck
| length
"##
));
assert_eq!(actual.out, "3");
})
}
#[test]
fn from_csv_text_with_custom_quotes_to_table() {
Playground::setup("filter_from_csv_test_6", |dirs, sandbox| {
sandbox.with_files(vec![FileWithContentToBeTrimmed(
"los_tres_caballeros.txt",
r#"
first_name,last_name,rusty_luck
'And''rés',Robalino,1
Jonathan,Turner,1
Yehuda,Katz,1
"#,
)]);
let actual = nu!(
cwd: dirs.test(), pipeline(
r#"
open los_tres_caballeros.txt
| from csv --quote "'"
| first
| get first_name
"#
));
assert_eq!(actual.out, "And'rés");
})
}
#[test]
fn from_csv_text_with_custom_escapes_to_table() {
Playground::setup("filter_from_csv_test_7", |dirs, sandbox| {
sandbox.with_files(vec![FileWithContentToBeTrimmed(
"los_tres_caballeros.txt",
r#"
first_name,last_name,rusty_luck
"And\"rés",Robalino,1
Jonathan,Turner,1
Yehuda,Katz,1
"#,
)]);
let actual = nu!(
cwd: dirs.test(), pipeline(
r#"
open los_tres_caballeros.txt
| from csv --escape '\'
| first
| get first_name
"#
));
assert_eq!(actual.out, "And\"rés");
})
}
#[test]
fn from_csv_text_skipping_headers_to_table() {
Playground::setup("filter_from_csv_test_8", |dirs, sandbox| {
sandbox.with_files(vec![FileWithContentToBeTrimmed(
"los_tres_amigos.txt",
r#"
@ -208,6 +292,84 @@ fn from_csv_text_skipping_headers_to_table() {
})
}
#[test]
fn from_csv_text_with_missing_columns_to_table() {
Playground::setup("filter_from_csv_test_9", |dirs, sandbox| {
sandbox.with_files(vec![FileWithContentToBeTrimmed(
"los_tres_caballeros.txt",
r#"
first_name,last_name,rusty_luck
Andrés,Robalino
Jonathan,Turner,1
Yehuda,Katz,1
"#,
)]);
let actual = nu!(
cwd: dirs.test(), pipeline(
r#"
open los_tres_caballeros.txt
| from csv --flexible
| get -i rusty_luck
| compact
| length
"#
));
assert_eq!(actual.out, "2");
})
}
#[test]
fn from_csv_text_with_multiple_char_separator() {
Playground::setup("filter_from_csv_test_10", |dirs, sandbox| {
sandbox.with_files(vec![FileWithContentToBeTrimmed(
"los_tres_caballeros.txt",
r#"
first_name,last_name,rusty_luck
Andrés,Robalino,1
Jonathan,Turner,1
Yehuda,Katz,1
"#,
)]);
let actual = nu!(
cwd: dirs.test(), pipeline(
r#"
open los_tres_caballeros.txt
| from csv --separator "li"
"#
));
assert!(actual.err.contains("single character separator"));
})
}
#[test]
fn from_csv_text_with_wrong_type_separator() {
Playground::setup("filter_from_csv_test_11", |dirs, sandbox| {
sandbox.with_files(vec![FileWithContentToBeTrimmed(
"los_tres_caballeros.txt",
r#"
first_name,last_name,rusty_luck
Andrés,Robalino,1
Jonathan,Turner,1
Yehuda,Katz,1
"#,
)]);
let actual = nu!(
cwd: dirs.test(), pipeline(
r#"
open los_tres_caballeros.txt
| from csv --separator ('123' | into int)
"#
));
assert!(actual.err.contains("can't convert int to char"));
})
}
#[test]
fn table_with_record_error() {
let actual = nu!(

View File

@ -16,7 +16,7 @@ fn table_to_tsv_text_and_from_tsv_text_back_into_table() {
fn table_to_tsv_text_and_from_tsv_text_back_into_table_using_csv_separator() {
let actual = nu!(
cwd: "tests/fixtures/formats",
r"open caco3_plastics.tsv | to tsv | from csv --separator '\t' | first | get origin"
r#"open caco3_plastics.tsv | to tsv | from csv --separator "\t" | first | get origin"#
);
assert_eq!(actual.out, "SPAIN");
@ -106,8 +106,92 @@ fn from_tsv_text_to_table() {
}
#[test]
fn from_tsv_text_skipping_headers_to_table() {
fn from_tsv_text_with_comments_to_table() {
Playground::setup("filter_from_tsv_test_2", |dirs, sandbox| {
sandbox.with_files(vec![FileWithContentToBeTrimmed(
"los_tres_caballeros.txt",
r#"
# This is a comment
first_name last_name rusty_luck
# This one too
Andrés Robalino 1
Jonathan Turner 1
Yehuda Katz 1
# This one also
"#,
)]);
let actual = nu!(
cwd: dirs.test(), pipeline(
r##"
open los_tres_caballeros.txt
| from tsv --comment "#"
| get rusty_luck
| length
"##
));
assert_eq!(actual.out, "3");
})
}
#[test]
fn from_tsv_text_with_custom_quotes_to_table() {
Playground::setup("filter_from_tsv_test_3", |dirs, sandbox| {
sandbox.with_files(vec![FileWithContentToBeTrimmed(
"los_tres_caballeros.txt",
r#"
first_name last_name rusty_luck
'And''rés' Robalino 1
Jonathan Turner 1
Yehuda Katz 1
"#,
)]);
let actual = nu!(
cwd: dirs.test(), pipeline(
r#"
open los_tres_caballeros.txt
| from tsv --quote "'"
| first
| get first_name
"#
));
assert_eq!(actual.out, "And'rés");
})
}
#[test]
fn from_tsv_text_with_custom_escapes_to_table() {
Playground::setup("filter_from_tsv_test_4", |dirs, sandbox| {
sandbox.with_files(vec![FileWithContentToBeTrimmed(
"los_tres_caballeros.txt",
r#"
first_name last_name rusty_luck
"And\"rés" Robalino 1
Jonathan Turner 1
Yehuda Katz 1
"#,
)]);
let actual = nu!(
cwd: dirs.test(), pipeline(
r#"
open los_tres_caballeros.txt
| from tsv --escape '\'
| first
| get first_name
"#
));
assert_eq!(actual.out, "And\"rés");
})
}
#[test]
fn from_tsv_text_skipping_headers_to_table() {
Playground::setup("filter_from_tsv_test_5", |dirs, sandbox| {
sandbox.with_files(vec![FileWithContentToBeTrimmed(
"los_tres_amigos.txt",
r#"
@ -130,3 +214,81 @@ fn from_tsv_text_skipping_headers_to_table() {
assert_eq!(actual.out, "3");
})
}
#[test]
fn from_tsv_text_with_missing_columns_to_table() {
Playground::setup("filter_from_tsv_test_6", |dirs, sandbox| {
sandbox.with_files(vec![FileWithContentToBeTrimmed(
"los_tres_caballeros.txt",
r#"
first_name last_name rusty_luck
Andrés Robalino
Jonathan Turner 1
Yehuda Katz 1
"#,
)]);
let actual = nu!(
cwd: dirs.test(), pipeline(
r#"
open los_tres_caballeros.txt
| from tsv --flexible
| get -i rusty_luck
| compact
| length
"#
));
assert_eq!(actual.out, "2");
})
}
#[test]
fn from_tsv_text_with_multiple_char_comment() {
Playground::setup("filter_from_tsv_test_7", |dirs, sandbox| {
sandbox.with_files(vec![FileWithContentToBeTrimmed(
"los_tres_caballeros.txt",
r#"
first_name last_name rusty_luck
Andrés Robalino 1
Jonathan Turner 1
Yehuda Katz 1
"#,
)]);
let actual = nu!(
cwd: dirs.test(), pipeline(
r#"
open los_tres_caballeros.txt
| from csv --comment "li"
"#
));
assert!(actual.err.contains("single character separator"));
})
}
#[test]
fn from_tsv_text_with_wrong_type_comment() {
Playground::setup("filter_from_csv_test_8", |dirs, sandbox| {
sandbox.with_files(vec![FileWithContentToBeTrimmed(
"los_tres_caballeros.txt",
r#"
first_name last_name rusty_luck
Andrés Robalino 1
Jonathan Turner 1
Yehuda Katz 1
"#,
)]);
let actual = nu!(
cwd: dirs.test(), pipeline(
r#"
open los_tres_caballeros.txt
| from csv --comment ('123' | into int)
"#
));
assert!(actual.err.contains("can't convert int to char"));
})
}