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

Jump to bottom

Fix error when querying ABCD datasets from NFDI #486

Merged
merged 9 commits into from
Mar 3, 2022
Merged

Fix error when querying ABCD datasets from NFDI #486

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
beccfde
parse emtpy strings as null
1lutz Feb 24, 2022
cf8759a
Merge branch 'master' into bug-abcd
1lutz Feb 24, 2022
0558ac0
test loading of csv files with empty fields
1lutz Feb 25, 2022
c96ff30
test whats inside FeatureDataRef
1lutz Feb 25, 2022
5919195
fix clippy
1lutz Feb 25, 2022
6c65a21
remove EMPTY_STRING_AS_NULL=YES
1lutz Feb 28, 2022
71b6362
differentiate empty strings from missing strings
1lutz Mar 3, 2022
7711548
remove unused file
1lutz Mar 3, 2022
22c5615
fix clippy
1lutz Mar 3, 2022
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
26 changes: 26 additions & 0 deletions datatypes/src/collections/data_collection.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -197,6 +197,32 @@ mod tests {
assert!(collection.rename_column("foo", "bar").is_err());
}

#[test]
fn distinguish_null_and_empty_strings() {
let pc = DataCollection::from_data(
vec![],
vec![TimeInterval::default(); 2],
[(
"foo".to_string(),
FeatureData::NullableText(vec![None, Some("".to_owned())]),
)]
.into_iter()
.collect(),
)
.unwrap();
let column = pc.data("foo").unwrap();

assert_eq!(column.nulls(), vec![true, false]);
assert_eq!(
column.get_unchecked(0),
FeatureDataValue::NullableText(None)
);
assert_eq!(
column.get_unchecked(1),
FeatureDataValue::NullableText(Some("".to_string()))
);
}

#[test]
fn iterator() {
let collection = DataCollection::from_data(
Expand Down
15 changes: 7 additions & 8 deletions datatypes/src/primitives/feature_data.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -575,7 +575,11 @@ impl<'r> DataRef<'r, u8> for TextDataRef<'r> {
let end = offsets[pos + 1];

if start == end {
return serde_json::Value::Null;
return if self.is_valid(pos) {
serde_json::Value::String(String::default())
} else {
serde_json::Value::Null
};
}

let text = unsafe {
Expand Down Expand Up @@ -617,12 +621,7 @@ impl<'r> DataRef<'r, u8> for TextDataRef<'r> {
/// ```
///
fn nulls(&self) -> Vec<bool> {
let mut nulls = Vec::with_capacity(self.offsets.len() - 1);
for window in self.offsets.windows(2) {
let (start, end) = (window[0], window[1]);
nulls.push(start == end);
}
nulls
null_bitmap_to_bools(self.valid_bitmap, self.offsets.len() - 1)
}

fn is_valid(&self, i: usize) -> bool {
Expand Down Expand Up @@ -760,7 +759,7 @@ impl<'r> TextDataRef<'r> {
let end = self.offsets[pos + 1];

if start == end {
return Ok(None);
return Ok(if self.is_valid(pos) { Some("") } else { None });
}

let text = unsafe {
Expand Down