Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Modify decimal regex to accept positive exponent specifier #5649

Merged
merged 3 commits into from
Apr 16, 2024
Merged

Modify decimal regex to accept positive exponent specifier #5649

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
39da0a2
Modify decimal regex to accept positive exponent specifier
jdcasale Apr 15, 2024
aed4dae
add test for positive exponent specifier
jdcasale Apr 15, 2024
ec1ede5
nit
jdcasale Apr 15, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
23 changes: 22 additions & 1 deletion arrow-csv/src/reader/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -148,7 +148,7 @@ lazy_static! {
static ref REGEX_SET: RegexSet = RegexSet::new([
r"(?i)^(true)$|^(false)$(?-i)", //BOOLEAN
r"^-?(\d+)$", //INTEGER
r"^-?((\d*\.\d+|\d+\.\d*)([eE]-?\d+)?|\d+([eE]-?\d+))$", //DECIMAL
r"^-?((\d*\.\d+|\d+\.\d*)([eE][-+]?\d+)?|\d+([eE][-+]?\d+))$", //DECIMAL
r"^\d{4}-\d\d-\d\d$", //DATE32
r"^\d{4}-\d\d-\d\d[T ]\d\d:\d\d:\d\d(?:[^\d\.].*)?$", //Timestamp(Second)
r"^\d{4}-\d\d-\d\d[T ]\d\d:\d\d:\d\d\.\d{1,3}(?:[^\d].*)?$", //Timestamp(Millisecond)
Expand Down Expand Up @@ -1658,6 +1658,27 @@ mod tests {
assert_eq!(batch.schema().as_ref(), &expected_schema);
}

#[test]
fn test_scientific_notation_with_inference() {
let mut file = File::open("test/data/scientific_notation_test.csv").unwrap();
let format = Format::default().with_header(false).with_delimiter(b',');

let (schema, _) = format.infer_schema(&mut file, None).unwrap();
file.rewind().unwrap();

let builder = ReaderBuilder::new(Arc::new(schema))
.with_format(format)
.with_batch_size(512)
.with_projection(vec![0, 1]);

let mut csv = builder.build(file).unwrap();
let batch = csv.next().unwrap().unwrap();

let schema = batch.schema();

assert_eq!(&DataType::Float64, schema.field(0).data_type());
}

#[test]
fn test_parse_invalid_csv() {
let file = File::open("test/data/various_types_invalid.csv").unwrap();
Expand Down
19 changes: 19 additions & 0 deletions arrow-csv/test/data/scientific_notation_test.csv
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,19 @@
1.439e+04, positive_exponent
1.31e+04, positive_exponent
1.2711e+0, positive_exponent
1.44e+04, positive_exponent
2.22e+04, positive_exponent
1.149e+04, positive_exponent
2.139e+04, positive_exponent
7.322e+04, positive_exponent
1.531e+04, positive_exponent
2.206e-04, negative_exponent
1.517e-04, negative_exponent
2.332e-04, negative_exponent
2.19e-04, negative_exponent
2.087e-04, negative_exponent
12683.18, no_exponent
7134.6, no_exponent
8540.17, no_exponent
21462.36, no_exponent
1120.76, no_exponent
Loading