Skip to content

Commit 664edea

Browse files
alambalamb
authored
Minor: Move test data into datafusion/core/tests/data (apache#4855)
* Minor: Move test data into tests/data
1 parent 71b9bae commit 664edea

File tree

20 files changed

+55
-54
lines changed

20 files changed

+55
-54
lines changed

‎datafusion/core/src/dataframe.rs‎

Lines changed: 27 additions & 27 deletions
Original file line numberDiff line numberDiff line change
@@ -63,7 +63,7 @@ use crate::prelude::SessionContext;
6363
/// # #[tokio::main]
6464
/// # async fn main() -> Result<()> {
6565
/// let ctx = SessionContext::new();
66-
/// let df = ctx.read_csv("tests/example.csv", CsvReadOptions::new()).await?;
66+
/// let df = ctx.read_csv("tests/data/example.csv", CsvReadOptions::new()).await?;
6767
/// let df = df.filter(col("a").lt_eq(col("b")))?
6868
/// .aggregate(vec![col("a")], vec![min(col("b"))])?
6969
/// .limit(0, Some(100))?;
@@ -100,7 +100,7 @@ impl DataFrame {
100100
/// # #[tokio::main]
101101
/// # async fn main() -> Result<()> {
102102
/// let ctx = SessionContext::new();
103-
/// let df = ctx.read_csv("tests/example.csv", CsvReadOptions::new()).await?;
103+
/// let df = ctx.read_csv("tests/data/example.csv", CsvReadOptions::new()).await?;
104104
/// let df = df.select_columns(&["a", "b"])?;
105105
/// # Ok(())
106106
/// # }
@@ -125,7 +125,7 @@ impl DataFrame {
125125
/// # #[tokio::main]
126126
/// # async fn main() -> Result<()> {
127127
/// let ctx = SessionContext::new();
128-
/// let df = ctx.read_csv("tests/example.csv", CsvReadOptions::new()).await?;
128+
/// let df = ctx.read_csv("tests/data/example.csv", CsvReadOptions::new()).await?;
129129
/// let df = df.select(vec![col("a") * col("b"), col("c")])?;
130130
/// # Ok(())
131131
/// # }
@@ -150,7 +150,7 @@ impl DataFrame {
150150
/// # #[tokio::main]
151151
/// # async fn main() -> Result<()> {
152152
/// let ctx = SessionContext::new();
153-
/// let df = ctx.read_csv("tests/example.csv", CsvReadOptions::new()).await?;
153+
/// let df = ctx.read_csv("tests/data/example.csv", CsvReadOptions::new()).await?;
154154
/// let df = df.filter(col("a").lt_eq(col("b")))?;
155155
/// # Ok(())
156156
/// # }
@@ -170,7 +170,7 @@ impl DataFrame {
170170
/// # #[tokio::main]
171171
/// # async fn main() -> Result<()> {
172172
/// let ctx = SessionContext::new();
173-
/// let df = ctx.read_csv("tests/example.csv", CsvReadOptions::new()).await?;
173+
/// let df = ctx.read_csv("tests/data/example.csv", CsvReadOptions::new()).await?;
174174
///
175175
/// // The following use is the equivalent of "SELECT MIN(b) GROUP BY a"
176176
/// let _ = df.clone().aggregate(vec![col("a")], vec![min(col("b"))])?;
@@ -202,7 +202,7 @@ impl DataFrame {
202202
/// # #[tokio::main]
203203
/// # async fn main() -> Result<()> {
204204
/// let ctx = SessionContext::new();
205-
/// let df = ctx.read_csv("tests/example.csv", CsvReadOptions::new()).await?;
205+
/// let df = ctx.read_csv("tests/data/example.csv", CsvReadOptions::new()).await?;
206206
/// let df = df.limit(0, Some(100))?;
207207
/// # Ok(())
208208
/// # }
@@ -223,7 +223,7 @@ impl DataFrame {
223223
/// # #[tokio::main]
224224
/// # async fn main() -> Result<()> {
225225
/// let ctx = SessionContext::new();
226-
/// let df = ctx.read_csv("tests/example.csv", CsvReadOptions::new()).await?;
226+
/// let df = ctx.read_csv("tests/data/example.csv", CsvReadOptions::new()).await?;
227227
/// let d2 = df.clone();
228228
/// let df = df.union(d2)?;
229229
/// # Ok(())
@@ -245,7 +245,7 @@ impl DataFrame {
245245
/// # #[tokio::main]
246246
/// # async fn main() -> Result<()> {
247247
/// let ctx = SessionContext::new();
248-
/// let df = ctx.read_csv("tests/example.csv", CsvReadOptions::new()).await?;
248+
/// let df = ctx.read_csv("tests/data/example.csv", CsvReadOptions::new()).await?;
249249
/// let d2 = df.clone();
250250
/// let df = df.union_distinct(d2)?;
251251
/// # Ok(())
@@ -268,7 +268,7 @@ impl DataFrame {
268268
/// # #[tokio::main]
269269
/// # async fn main() -> Result<()> {
270270
/// let ctx = SessionContext::new();
271-
/// let df = ctx.read_csv("tests/example.csv", CsvReadOptions::new()).await?;
271+
/// let df = ctx.read_csv("tests/data/example.csv", CsvReadOptions::new()).await?;
272272
/// let df = df.distinct()?;
273273
/// # Ok(())
274274
/// # }
@@ -289,7 +289,7 @@ impl DataFrame {
289289
/// # #[tokio::main]
290290
/// # async fn main() -> Result<()> {
291291
/// let ctx = SessionContext::new();
292-
/// let df = ctx.read_csv("tests/example.csv", CsvReadOptions::new()).await?;
292+
/// let df = ctx.read_csv("tests/data/example.csv", CsvReadOptions::new()).await?;
293293
/// let df = df.sort(vec![col("a").sort(true, true), col("b").sort(false, false)])?;
294294
/// # Ok(())
295295
/// # }
@@ -311,8 +311,8 @@ impl DataFrame {
311311
/// # #[tokio::main]
312312
/// # async fn main() -> Result<()> {
313313
/// let ctx = SessionContext::new();
314-
/// let left = ctx.read_csv("tests/example.csv", CsvReadOptions::new()).await?;
315-
/// let right = ctx.read_csv("tests/example.csv", CsvReadOptions::new()).await?
314+
/// let left = ctx.read_csv("tests/data/example.csv", CsvReadOptions::new()).await?;
315+
/// let right = ctx.read_csv("tests/data/example.csv", CsvReadOptions::new()).await?
316316
/// .select(vec![
317317
/// col("a").alias("a2"),
318318
/// col("b").alias("b2"),
@@ -349,7 +349,7 @@ impl DataFrame {
349349
/// # #[tokio::main]
350350
/// # async fn main() -> Result<()> {
351351
/// let ctx = SessionContext::new();
352-
/// let df = ctx.read_csv("tests/example.csv", CsvReadOptions::new()).await?;
352+
/// let df = ctx.read_csv("tests/data/example.csv", CsvReadOptions::new()).await?;
353353
/// let df1 = df.repartition(Partitioning::RoundRobinBatch(4))?;
354354
/// # Ok(())
355355
/// # }
@@ -370,7 +370,7 @@ impl DataFrame {
370370
/// # #[tokio::main]
371371
/// # async fn main() -> Result<()> {
372372
/// let ctx = SessionContext::new();
373-
/// let df = ctx.read_csv("tests/example.csv", CsvReadOptions::new()).await?;
373+
/// let df = ctx.read_csv("tests/data/example.csv", CsvReadOptions::new()).await?;
374374
/// let batches = df.collect().await?;
375375
/// # Ok(())
376376
/// # }
@@ -389,7 +389,7 @@ impl DataFrame {
389389
/// # #[tokio::main]
390390
/// # async fn main() -> Result<()> {
391391
/// let ctx = SessionContext::new();
392-
/// let df = ctx.read_csv("tests/example.csv", CsvReadOptions::new()).await?;
392+
/// let df = ctx.read_csv("tests/data/example.csv", CsvReadOptions::new()).await?;
393393
/// df.show().await?;
394394
/// # Ok(())
395395
/// # }
@@ -407,7 +407,7 @@ impl DataFrame {
407407
/// # #[tokio::main]
408408
/// # async fn main() -> Result<()> {
409409
/// let ctx = SessionContext::new();
410-
/// let df = ctx.read_csv("tests/example.csv", CsvReadOptions::new()).await?;
410+
/// let df = ctx.read_csv("tests/data/example.csv", CsvReadOptions::new()).await?;
411411
/// df.show_limit(10).await?;
412412
/// # Ok(())
413413
/// # }
@@ -429,7 +429,7 @@ impl DataFrame {
429429
/// # #[tokio::main]
430430
/// # async fn main() -> Result<()> {
431431
/// let ctx = SessionContext::new();
432-
/// let df = ctx.read_csv("tests/example.csv", CsvReadOptions::new()).await?;
432+
/// let df = ctx.read_csv("tests/data/example.csv", CsvReadOptions::new()).await?;
433433
/// let stream = df.execute_stream().await?;
434434
/// # Ok(())
435435
/// # }
@@ -449,7 +449,7 @@ impl DataFrame {
449449
/// # #[tokio::main]
450450
/// # async fn main() -> Result<()> {
451451
/// let ctx = SessionContext::new();
452-
/// let df = ctx.read_csv("tests/example.csv", CsvReadOptions::new()).await?;
452+
/// let df = ctx.read_csv("tests/data/example.csv", CsvReadOptions::new()).await?;
453453
/// let batches = df.collect_partitioned().await?;
454454
/// # Ok(())
455455
/// # }
@@ -468,7 +468,7 @@ impl DataFrame {
468468
/// # #[tokio::main]
469469
/// # async fn main() -> Result<()> {
470470
/// let ctx = SessionContext::new();
471-
/// let df = ctx.read_csv("tests/example.csv", CsvReadOptions::new()).await?;
471+
/// let df = ctx.read_csv("tests/data/example.csv", CsvReadOptions::new()).await?;
472472
/// let batches = df.execute_stream_partitioned().await?;
473473
/// # Ok(())
474474
/// # }
@@ -490,7 +490,7 @@ impl DataFrame {
490490
/// # #[tokio::main]
491491
/// # async fn main() -> Result<()> {
492492
/// let ctx = SessionContext::new();
493-
/// let df = ctx.read_csv("tests/example.csv", CsvReadOptions::new()).await?;
493+
/// let df = ctx.read_csv("tests/data/example.csv", CsvReadOptions::new()).await?;
494494
/// let schema = df.schema();
495495
/// # Ok(())
496496
/// # }
@@ -548,7 +548,7 @@ impl DataFrame {
548548
/// # #[tokio::main]
549549
/// # async fn main() -> Result<()> {
550550
/// let ctx = SessionContext::new();
551-
/// let df = ctx.read_csv("tests/example.csv", CsvReadOptions::new()).await?;
551+
/// let df = ctx.read_csv("tests/data/example.csv", CsvReadOptions::new()).await?;
552552
/// let batches = df.limit(0, Some(100))?.explain(false, false)?.collect().await?;
553553
/// # Ok(())
554554
/// # }
@@ -568,7 +568,7 @@ impl DataFrame {
568568
/// # #[tokio::main]
569569
/// # async fn main() -> Result<()> {
570570
/// let ctx = SessionContext::new();
571-
/// let df = ctx.read_csv("tests/example.csv", CsvReadOptions::new()).await?;
571+
/// let df = ctx.read_csv("tests/data/example.csv", CsvReadOptions::new()).await?;
572572
/// let f = df.registry();
573573
/// // use f.udf("name", vec![...]) to use the udf
574574
/// # Ok(())
@@ -586,7 +586,7 @@ impl DataFrame {
586586
/// # #[tokio::main]
587587
/// # async fn main() -> Result<()> {
588588
/// let ctx = SessionContext::new();
589-
/// let df = ctx.read_csv("tests/example.csv", CsvReadOptions::new()).await?;
589+
/// let df = ctx.read_csv("tests/data/example.csv", CsvReadOptions::new()).await?;
590590
/// let d2 = df.clone();
591591
/// let df = df.intersect(d2)?;
592592
/// # Ok(())
@@ -609,7 +609,7 @@ impl DataFrame {
609609
/// # #[tokio::main]
610610
/// # async fn main() -> Result<()> {
611611
/// let ctx = SessionContext::new();
612-
/// let df = ctx.read_csv("tests/example.csv", CsvReadOptions::new()).await?;
612+
/// let df = ctx.read_csv("tests/data/example.csv", CsvReadOptions::new()).await?;
613613
/// let d2 = df.clone();
614614
/// let df = df.except(d2)?;
615615
/// # Ok(())
@@ -655,7 +655,7 @@ impl DataFrame {
655655
/// # #[tokio::main]
656656
/// # async fn main() -> Result<()> {
657657
/// let ctx = SessionContext::new();
658-
/// let df = ctx.read_csv("tests/example.csv", CsvReadOptions::new()).await?;
658+
/// let df = ctx.read_csv("tests/data/example.csv", CsvReadOptions::new()).await?;
659659
/// let df = df.with_column("ab_sum", col("a") + col("b"))?;
660660
/// # Ok(())
661661
/// # }
@@ -705,7 +705,7 @@ impl DataFrame {
705705
/// # #[tokio::main]
706706
/// # async fn main() -> Result<()> {
707707
/// let ctx = SessionContext::new();
708-
/// let df = ctx.read_csv("tests/example.csv", CsvReadOptions::new()).await?;
708+
/// let df = ctx.read_csv("tests/data/example.csv", CsvReadOptions::new()).await?;
709709
/// let df = df.with_column_renamed("ab_sum", "total")?;
710710
/// # Ok(())
711711
/// # }
@@ -750,7 +750,7 @@ impl DataFrame {
750750
/// # #[tokio::main]
751751
/// # async fn main() -> Result<()> {
752752
/// let ctx = SessionContext::new();
753-
/// let df = ctx.read_csv("tests/example.csv", CsvReadOptions::new()).await?;
753+
/// let df = ctx.read_csv("tests/data/example.csv", CsvReadOptions::new()).await?;
754754
/// let df = df.cache().await?;
755755
/// # Ok(())
756756
/// # }

‎datafusion/core/src/execution/context.rs‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -120,7 +120,7 @@ use super::options::{
120120
/// # #[tokio::main]
121121
/// # async fn main() -> Result<()> {
122122
/// let ctx = SessionContext::new();
123-
/// let df = ctx.read_csv("tests/example.csv", CsvReadOptions::new()).await?;
123+
/// let df = ctx.read_csv("tests/data/example.csv", CsvReadOptions::new()).await?;
124124
/// let df = df.filter(col("a").lt_eq(col("b")))?
125125
/// .aggregate(vec![col("a")], vec![min(col("b"))])?
126126
/// .limit(0, Some(100))?;
@@ -138,7 +138,7 @@ use super::options::{
138138
/// # #[tokio::main]
139139
/// # async fn main() -> Result<()> {
140140
/// let mut ctx = SessionContext::new();
141-
/// ctx.register_csv("example", "tests/example.csv", CsvReadOptions::new()).await?;
141+
/// ctx.register_csv("example", "tests/data/example.csv", CsvReadOptions::new()).await?;
142142
/// let results = ctx.sql("SELECT a, MIN(b) FROM example GROUP BY a LIMIT 100").await?;
143143
/// # Ok(())
144144
/// # }

‎datafusion/core/src/lib.rs‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -37,7 +37,7 @@
3737
//! let ctx = SessionContext::new();
3838
//!
3939
//! // create the dataframe
40-
//! let df = ctx.read_csv("tests/example.csv", CsvReadOptions::new()).await?;
40+
//! let df = ctx.read_csv("tests/data/example.csv", CsvReadOptions::new()).await?;
4141
//!
4242
//! // create a plan
4343
//! let df = df.filter(col("a").lt_eq(col("b")))?
@@ -75,7 +75,7 @@
7575
//! # async fn main() -> Result<()> {
7676
//! let ctx = SessionContext::new();
7777
//!
78-
//! ctx.register_csv("example", "tests/example.csv", CsvReadOptions::new()).await?;
78+
//! ctx.register_csv("example", "tests/data/example.csv", CsvReadOptions::new()).await?;
7979
//!
8080
//! // create a plan
8181
//! let df = ctx.sql("SELECT a, MIN(b) FROM example GROUP BY a LIMIT 100").await?;

‎datafusion/core/src/physical_plan/mod.rs‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -321,7 +321,7 @@ pub fn with_new_children_if_necessary(
321321
/// let mut ctx = SessionContext::with_config(config);
322322
///
323323
/// // register the a table
324-
/// ctx.register_csv("example", "tests/example.csv", CsvReadOptions::new()).await.unwrap();
324+
/// ctx.register_csv("example", "tests/data/example.csv", CsvReadOptions::new()).await.unwrap();
325325
///
326326
/// // create a plan to run a SQL query
327327
/// let dataframe = ctx.sql("SELECT a FROM example WHERE a < 5").await.unwrap();
@@ -339,7 +339,7 @@ pub fn with_new_children_if_necessary(
339339
/// \n CoalesceBatchesExec: target_batch_size=8192\
340340
/// \n FilterExec: a@0 < 5\
341341
/// \n RepartitionExec: partitioning=RoundRobinBatch(3)\
342-
/// \n CsvExec: files={1 group: [[WORKING_DIR/tests/example.csv]]}, has_header=true, limit=None, projection=[a]",
342+
/// \n CsvExec: files={1 group: [[WORKING_DIR/tests/data/example.csv]]}, has_header=true, limit=None, projection=[a]",
343343
/// plan_string.trim());
344344
///
345345
/// let one_line = format!("{}", displayable_plan.one_line());

‎datafusion/core/src/scheduler/mod.rs‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -59,7 +59,7 @@
5959
//! let config = SessionConfig::new().with_target_partitions(4);
6060
//! let context = SessionContext::with_config(config);
6161
//!
62-
//! context.register_csv("example", "../core/tests/example.csv", CsvReadOptions::new()).await.unwrap();
62+
//! context.register_csv("example", "../core/tests/data/example.csv", CsvReadOptions::new()).await.unwrap();
6363
//! let plan = context.sql("SELECT MIN(b) FROM example")
6464
//! .await
6565
//! .unwrap()
@@ -345,7 +345,7 @@ mod tests {
345345
"select id, b from (select id, b from table1 union all select id, b from table2 where a > 100 order by id) as t where b > 10 order by id, b",
346346
"select id, MIN(b), MAX(b), AVG(b) from table1 group by id order by id",
347347
"select count(*) from table1 where table1.a > 4",
348-
"WITH gp AS (SELECT id FROM table1 GROUP BY id)
348+
"WITH gp AS (SELECT id FROM table1 GROUP BY id)
349349
SELECT COUNT(CAST(CAST(gp.id || 'xx' AS TIMESTAMP) AS BIGINT)) FROM gp",
350350
];
351351

datafusion/core/tests/aggregate_simple.csv renamed to datafusion/core/tests/data/aggregate_simple.csv

File renamed without changes.

datafusion/core/tests/aggregate_simple_pipe.csv renamed to datafusion/core/tests/data/aggregate_simple_pipe.csv

File renamed without changes.

datafusion/core/tests/capitalized_example.csv renamed to datafusion/core/tests/data/capitalized_example.csv

File renamed without changes.

datafusion/core/tests/customer.csv renamed to datafusion/core/tests/data/customer.csv

File renamed without changes.

datafusion/core/tests/decimal_data.csv renamed to datafusion/core/tests/data/decimal_data.csv

File renamed without changes.

0 commit comments

Comments
 (0)