Skip to content

Migrate tests to insta #15288

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

Merged
merged 9 commits into from
Mar 20, 2025
Merged

Migrate tests to insta #15288

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
d36493a
migrated tests to insta
jsai28 Mar 18, 2025
6eafa2e
add space
jsai28 Mar 18, 2025
b583623
taplo format
jsai28 Mar 18, 2025
a1990ff
add missing inline snapshots
jsai28 Mar 19, 2025
04a71ad
change to sort_string
jsai28 Mar 19, 2025
c7dd935
Merge remote-tracking branch 'upstream/main' into Migrate-tests-to-insta
jsai28 Mar 19, 2025
767299f
Merge remote-tracking branch 'upstream/main' into Migrate-tests-to-insta
jsai28 Mar 19, 2025
cd490c4
Merge remote-tracking branch 'upstream/main' into Migrate-tests-to-insta
jsai28 Mar 19, 2025
fc928f2
review changes
jsai28 Mar 19, 2025
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
2 changes: 2 additions & 0 deletions Cargo.lock
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

42 changes: 23 additions & 19 deletions datafusion-cli/src/main.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -322,7 +322,8 @@ fn extract_memory_pool_size(size: &str) -> Result<usize, String> {
#[cfg(test)]
mod tests {
use super::*;
use datafusion::assert_batches_eq;
use datafusion::common::test_util::batches_to_string;
use insta::assert_snapshot;

fn assert_conversion(input: &str, expected: Result<usize, String>) {
let result = extract_memory_pool_size(input);
Expand Down Expand Up @@ -391,21 +392,26 @@ mod tests {
let df = ctx.sql(sql).await?;
let rbs = df.collect().await?;

let excepted = [
"+-------------------------------------------------------------+--------------+--------------------+-----------------------+-----------------+-----------+-------------+------------+----------------+-------+-----------+-----------+------------------+----------------------+-----------------+-----------------+-------------+------------------------------+-------------------+------------------------+------------------+-----------------------+-------------------------+",
"| filename | row_group_id | row_group_num_rows | row_group_num_columns | row_group_bytes | column_id | file_offset | num_values | path_in_schema | type | stats_min | stats_max | stats_null_count | stats_distinct_count | stats_min_value | stats_max_value | compression | encodings | index_page_offset | dictionary_page_offset | data_page_offset | total_compressed_size | total_uncompressed_size |",
"+-------------------------------------------------------------+--------------+--------------------+-----------------------+-----------------+-----------+-------------+------------+----------------+-------+-----------+-----------+------------------+----------------------+-----------------+-----------------+-------------+------------------------------+-------------------+------------------------+------------------+-----------------------+-------------------------+",
"| ../datafusion/core/tests/data/fixed_size_list_array.parquet | 0 | 2 | 1 | 123 | 0 | 125 | 4 | \"f0.list.item\" | INT64 | 1 | 4 | 0 | | 1 | 4 | SNAPPY | [RLE_DICTIONARY, PLAIN, RLE] | | 4 | 46 | 121 | 123 |",
"+-------------------------------------------------------------+--------------+--------------------+-----------------------+-----------------+-----------+-------------+------------+----------------+-------+-----------+-----------+------------------+----------------------+-----------------+-----------------+-------------+------------------------------+-------------------+------------------------+------------------+-----------------------+-------------------------+",
];
assert_batches_eq!(excepted, &rbs);
assert_snapshot!(batches_to_string(&rbs), @r#"
+-------------------------------------------------------------+--------------+--------------------+-----------------------+-----------------+-----------+-------------+------------+----------------+-------+-----------+-----------+------------------+----------------------+-----------------+-----------------+-------------+------------------------------+-------------------+------------------------+------------------+-----------------------+-------------------------+
| filename | row_group_id | row_group_num_rows | row_group_num_columns | row_group_bytes | column_id | file_offset | num_values | path_in_schema | type | stats_min | stats_max | stats_null_count | stats_distinct_count | stats_min_value | stats_max_value | compression | encodings | index_page_offset | dictionary_page_offset | data_page_offset | total_compressed_size | total_uncompressed_size |
+-------------------------------------------------------------+--------------+--------------------+-----------------------+-----------------+-----------+-------------+------------+----------------+-------+-----------+-----------+------------------+----------------------+-----------------+-----------------+-------------+------------------------------+-------------------+------------------------+------------------+-----------------------+-------------------------+
| ../datafusion/core/tests/data/fixed_size_list_array.parquet | 0 | 2 | 1 | 123 | 0 | 125 | 4 | "f0.list.item" | INT64 | 1 | 4 | 0 | | 1 | 4 | SNAPPY | [RLE_DICTIONARY, PLAIN, RLE] | | 4 | 46 | 121 | 123 |
+-------------------------------------------------------------+--------------+--------------------+-----------------------+-----------------+-----------+-------------+------------+----------------+-------+-----------+-----------+------------------+----------------------+-----------------+-----------------+-------------+------------------------------+-------------------+------------------------+------------------+-----------------------+-------------------------+
"#);

// input with double quote
let sql =
"SELECT * FROM parquet_metadata(\"../datafusion/core/tests/data/fixed_size_list_array.parquet\")";
let df = ctx.sql(sql).await?;
let rbs = df.collect().await?;
assert_batches_eq!(excepted, &rbs);
assert_snapshot!(batches_to_string(&rbs), @r#"
+-------------------------------------------------------------+--------------+--------------------+-----------------------+-----------------+-----------+-------------+------------+----------------+-------+-----------+-----------+------------------+----------------------+-----------------+-----------------+-------------+------------------------------+-------------------+------------------------+------------------+-----------------------+-------------------------+
| filename | row_group_id | row_group_num_rows | row_group_num_columns | row_group_bytes | column_id | file_offset | num_values | path_in_schema | type | stats_min | stats_max | stats_null_count | stats_distinct_count | stats_min_value | stats_max_value | compression | encodings | index_page_offset | dictionary_page_offset | data_page_offset | total_compressed_size | total_uncompressed_size |
+-------------------------------------------------------------+--------------+--------------------+-----------------------+-----------------+-----------+-------------+------------+----------------+-------+-----------+-----------+------------------+----------------------+-----------------+-----------------+-------------+------------------------------+-------------------+------------------------+------------------+-----------------------+-------------------------+
| ../datafusion/core/tests/data/fixed_size_list_array.parquet | 0 | 2 | 1 | 123 | 0 | 125 | 4 | "f0.list.item" | INT64 | 1 | 4 | 0 | | 1 | 4 | SNAPPY | [RLE_DICTIONARY, PLAIN, RLE] | | 4 | 46 | 121 | 123 |
+-------------------------------------------------------------+--------------+--------------------+-----------------------+-----------------+-----------+-------------+------------+----------------+-------+-----------+-----------+------------------+----------------------+-----------------+-----------------+-------------+------------------------------+-------------------+------------------------+------------------+-----------------------+-------------------------+
"#);

Ok(())
}
Expand All @@ -421,15 +427,13 @@ mod tests {
let df = ctx.sql(sql).await?;
let rbs = df.collect().await?;

let excepted = [

"+-----------------------------------------------------------------+--------------+--------------------+-----------------------+-----------------+-----------+-------------+------------+----------------+------------+-----------+-----------+------------------+----------------------+-----------------+-----------------+--------------------+--------------------------+-------------------+------------------------+------------------+-----------------------+-------------------------+",
"| filename | row_group_id | row_group_num_rows | row_group_num_columns | row_group_bytes | column_id | file_offset | num_values | path_in_schema | type | stats_min | stats_max | stats_null_count | stats_distinct_count | stats_min_value | stats_max_value | compression | encodings | index_page_offset | dictionary_page_offset | data_page_offset | total_compressed_size | total_uncompressed_size |",
"+-----------------------------------------------------------------+--------------+--------------------+-----------------------+-----------------+-----------+-------------+------------+----------------+------------+-----------+-----------+------------------+----------------------+-----------------+-----------------+--------------------+--------------------------+-------------------+------------------------+------------------+-----------------------+-------------------------+",
"| ../parquet-testing/data/data_index_bloom_encoding_stats.parquet | 0 | 14 | 1 | 163 | 0 | 4 | 14 | \"String\" | BYTE_ARRAY | Hello | today | 0 | | Hello | today | GZIP(GzipLevel(6)) | [BIT_PACKED, RLE, PLAIN] | | | 4 | 152 | 163 |",
"+-----------------------------------------------------------------+--------------+--------------------+-----------------------+-----------------+-----------+-------------+------------+----------------+------------+-----------+-----------+------------------+----------------------+-----------------+-----------------+--------------------+--------------------------+-------------------+------------------------+------------------+-----------------------+-------------------------+"
];
assert_batches_eq!(excepted, &rbs);
assert_snapshot!(batches_to_string(&rbs),@r#"
+-----------------------------------------------------------------+--------------+--------------------+-----------------------+-----------------+-----------+-------------+------------+----------------+------------+-----------+-----------+------------------+----------------------+-----------------+-----------------+--------------------+--------------------------+-------------------+------------------------+------------------+-----------------------+-------------------------+
| filename | row_group_id | row_group_num_rows | row_group_num_columns | row_group_bytes | column_id | file_offset | num_values | path_in_schema | type | stats_min | stats_max | stats_null_count | stats_distinct_count | stats_min_value | stats_max_value | compression | encodings | index_page_offset | dictionary_page_offset | data_page_offset | total_compressed_size | total_uncompressed_size |
+-----------------------------------------------------------------+--------------+--------------------+-----------------------+-----------------+-----------+-------------+------------+----------------+------------+-----------+-----------+------------------+----------------------+-----------------+-----------------+--------------------+--------------------------+-------------------+------------------------+------------------+-----------------------+-------------------------+
| ../parquet-testing/data/data_index_bloom_encoding_stats.parquet | 0 | 14 | 1 | 163 | 0 | 4 | 14 | "String" | BYTE_ARRAY | Hello | today | 0 | | Hello | today | GZIP(GzipLevel(6)) | [BIT_PACKED, RLE, PLAIN] | | | 4 | 152 | 163 |
+-----------------------------------------------------------------+--------------+--------------------+-----------------------+-----------------+-----------+-------------+------------+----------------+------------+-----------+-----------+------------------+----------------------+-----------------+-----------------+--------------------+--------------------------+-------------------+------------------------+------------------+-----------------------+-------------------------+
"#);

Ok(())
}
Expand Down
1 change: 1 addition & 0 deletions datafusion/common/Cargo.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -73,4 +73,5 @@ web-time = "1.1.0"

[dev-dependencies]
chrono = { workspace = true }
insta = { workspace = true }
rand = { workspace = true }
73 changes: 34 additions & 39 deletions datafusion/common/src/scalar/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,6 +38,7 @@ use crate::cast::{
as_fixed_size_binary_array, as_fixed_size_list_array,
};
use crate::error::{DataFusionError, Result, _exec_err, _internal_err, _not_impl_err};
use crate::format::DEFAULT_CAST_OPTIONS;
use crate::hash_utils::create_hashes;
use crate::utils::SingleRowListArrayBuilder;
use arrow::array::{
Expand All @@ -58,8 +59,6 @@ use arrow::datatypes::{
UInt8Type, UnionFields, UnionMode, DECIMAL128_MAX_PRECISION,
};
use arrow::util::display::{array_value_to_string, ArrayFormatter, FormatOptions};

use crate::format::DEFAULT_CAST_OPTIONS;
use half::f16;
pub use struct_builder::ScalarStructBuilder;

Expand Down Expand Up @@ -3976,14 +3975,15 @@ mod tests {
as_map_array, as_string_array, as_struct_array, as_uint32_array, as_uint64_array,
};

use crate::assert_batches_eq;
use crate::test_util::batches_to_string;
use arrow::array::{types::Float64Type, NullBufferBuilder};
use arrow::buffer::{Buffer, OffsetBuffer};
use arrow::compute::{is_null, kernels};
use arrow::datatypes::Fields;
use arrow::error::ArrowError;
use arrow::util::pretty::pretty_format_columns;
use chrono::NaiveDate;
use insta::assert_snapshot;
use rand::Rng;

#[test]
Expand Down Expand Up @@ -6910,14 +6910,13 @@ mod tests {

//verify compared to arrow display
let batch = RecordBatch::try_from_iter(vec![("s", arr as _)]).unwrap();
let expected = [
"+-------------+",
"| s |",
"+-------------+",
"| {a: 1, b: } |",
"+-------------+",
];
assert_batches_eq!(&expected, &[batch]);
assert_snapshot!(batches_to_string(&[batch]), @r"
+-------------+
| s |
+-------------+
| {a: 1, b: } |
+-------------+
");
}

#[test]
Expand Down Expand Up @@ -6946,14 +6945,13 @@ mod tests {

//verify compared to arrow display
let batch = RecordBatch::try_from_iter(vec![("s", arr as _)]).unwrap();
let expected = [
"+--------------+",
"| s |",
"+--------------+",
"| {a: 1, b: 2} |",
"+--------------+",
];
assert_batches_eq!(&expected, &[batch]);
assert_snapshot!(batches_to_string(&[batch]), @r"
+--------------+
| s |
+--------------+
| {a: 1, b: 2} |
+--------------+
");
}

#[test]
Expand All @@ -6969,15 +6967,13 @@ mod tests {
//verify compared to arrow display
let batch = RecordBatch::try_from_iter(vec![("s", arr as _)]).unwrap();

#[rustfmt::skip]
let expected = [
"+---+",
"| s |",
"+---+",
"| |",
"+---+",
];
assert_batches_eq!(&expected, &[batch]);
assert_snapshot!(batches_to_string(&[batch]), @r"
+---+
| s |
+---+
| |
+---+
");
}

#[test]
Expand Down Expand Up @@ -7011,17 +7007,16 @@ mod tests {

//verify compared to arrow display
let batch = RecordBatch::try_from_iter(vec![("m", arr as _)]).unwrap();
let expected = [
"+--------------------+",
"| m |",
"+--------------------+",
"| {joe: 1} |",
"| {blogs: 2, foo: 4} |",
"| {} |",
"| |",
"+--------------------+",
];
assert_batches_eq!(&expected, &[batch]);
assert_snapshot!(batches_to_string(&[batch]), @r"
+--------------------+
| m |
+--------------------+
| {joe: 1} |
| {blogs: 2, foo: 4} |
| {} |
| |
+--------------------+
");
}

#[test]
Expand Down
18 changes: 9 additions & 9 deletions datafusion/core/src/execution/context/csv.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -89,8 +89,9 @@ impl SessionContext {
#[cfg(test)]
mod tests {
use super::*;
use crate::assert_batches_eq;
use crate::test_util::{plan_and_collect, populate_csv_partitions};
use datafusion_common::test_util::batches_to_string;
use insta::assert_snapshot;

use tempfile::TempDir;

Expand All @@ -115,14 +116,13 @@ mod tests {
plan_and_collect(&ctx, "SELECT sum(c1), sum(c2), count(*) FROM test").await?;

assert_eq!(results.len(), 1);
let expected = [
"+--------------+--------------+----------+",
"| sum(test.c1) | sum(test.c2) | count(*) |",
"+--------------+--------------+----------+",
"| 10 | 110 | 20 |",
"+--------------+--------------+----------+",
];
assert_batches_eq!(expected, &results);
assert_snapshot!(batches_to_string(&results), @r"
+--------------+--------------+----------+
| sum(test.c1) | sum(test.c2) | count(*) |
+--------------+--------------+----------+
| 10 | 110 | 20 |
+--------------+--------------+----------+
");

Ok(())
}
Expand Down
Loading