1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776
// Licensed to the Apache Software Foundation (ASF) under one
// or more contributor license agreements. See the NOTICE file
// distributed with this work for additional information
// regarding copyright ownership. The ASF licenses this file
// to you under the Apache License, Version 2.0 (the
// "License"); you may not use this file except in compliance
// with the License. You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing,
// software distributed under the License is distributed on an
// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
// KIND, either express or implied. See the License for the
// specific language governing permissions and limitations
// under the License.
//! Execution plans that read file formats
mod arrow_file;
mod avro;
mod csv;
mod file_groups;
mod file_scan_config;
mod file_stream;
mod json;
#[cfg(feature = "parquet")]
pub mod parquet;
mod statistics;
pub(crate) use self::csv::plan_to_csv;
pub(crate) use self::json::plan_to_json;
#[cfg(feature = "parquet")]
pub use self::parquet::{ParquetExec, ParquetFileMetrics, ParquetFileReaderFactory};
pub use arrow_file::ArrowExec;
pub use avro::AvroExec;
pub use csv::{CsvConfig, CsvExec, CsvOpener};
pub use file_groups::FileGroupPartitioner;
pub use file_scan_config::{
wrap_partition_type_in_dict, wrap_partition_value_in_dict, FileScanConfig,
};
pub use file_stream::{FileOpenFuture, FileOpener, FileStream, OnError};
pub use json::{JsonOpener, NdJsonExec};
use std::{
fmt::{Debug, Formatter, Result as FmtResult},
ops::Range,
sync::Arc,
vec,
};
use super::listing::ListingTableUrl;
use crate::error::Result;
use crate::physical_plan::{DisplayAs, DisplayFormatType};
use crate::{
datasource::{
listing::{FileRange, PartitionedFile},
object_store::ObjectStoreUrl,
},
physical_plan::display::{display_orderings, ProjectSchemaDisplay},
};
use arrow::datatypes::{DataType, SchemaRef};
use datafusion_physical_expr::expressions::Column;
use datafusion_physical_expr::PhysicalSortExpr;
use futures::StreamExt;
use log::debug;
use object_store::{path::Path, GetOptions, GetRange, ObjectMeta, ObjectStore};
/// The base configurations to provide when creating a physical plan for
/// writing to any given file format.
pub struct FileSinkConfig {
/// Object store URL, used to get an ObjectStore instance
pub object_store_url: ObjectStoreUrl,
/// A vector of [`PartitionedFile`] structs, each representing a file partition
pub file_groups: Vec<PartitionedFile>,
/// Vector of partition paths
pub table_paths: Vec<ListingTableUrl>,
/// The schema of the output file
pub output_schema: SchemaRef,
/// A vector of column names and their corresponding data types,
/// representing the partitioning columns for the file
pub table_partition_cols: Vec<(String, DataType)>,
/// Controls whether existing data should be overwritten by this sink
pub overwrite: bool,
}
impl FileSinkConfig {
/// Get output schema
pub fn output_schema(&self) -> &SchemaRef {
&self.output_schema
}
}
impl Debug for FileScanConfig {
fn fmt(&self, f: &mut Formatter<'_>) -> FmtResult {
write!(f, "object_store_url={:?}, ", self.object_store_url)?;
write!(f, "statistics={:?}, ", self.statistics)?;
DisplayAs::fmt_as(self, DisplayFormatType::Verbose, f)
}
}
impl DisplayAs for FileScanConfig {
fn fmt_as(&self, t: DisplayFormatType, f: &mut Formatter) -> FmtResult {
let (schema, _, orderings) = self.project();
write!(f, "file_groups=")?;
FileGroupsDisplay(&self.file_groups).fmt_as(t, f)?;
if !schema.fields().is_empty() {
write!(f, ", projection={}", ProjectSchemaDisplay(&schema))?;
}
if let Some(limit) = self.limit {
write!(f, ", limit={limit}")?;
}
display_orderings(f, &orderings)?;
Ok(())
}
}
/// A wrapper to customize partitioned file display
///
/// Prints in the format:
/// ```text
/// {NUM_GROUPS groups: [[file1, file2,...], [fileN, fileM, ...], ...]}
/// ```
#[derive(Debug)]
struct FileGroupsDisplay<'a>(&'a [Vec<PartitionedFile>]);
impl<'a> DisplayAs for FileGroupsDisplay<'a> {
fn fmt_as(&self, t: DisplayFormatType, f: &mut Formatter) -> FmtResult {
let n_groups = self.0.len();
let groups = if n_groups == 1 { "group" } else { "groups" };
write!(f, "{{{n_groups} {groups}: [")?;
match t {
DisplayFormatType::Default => {
// To avoid showing too many partitions
let max_groups = 5;
fmt_up_to_n_elements(self.0, max_groups, f, |group, f| {
FileGroupDisplay(group).fmt_as(t, f)
})?;
}
DisplayFormatType::Verbose => {
fmt_elements_split_by_commas(self.0.iter(), f, |group, f| {
FileGroupDisplay(group).fmt_as(t, f)
})?
}
}
write!(f, "]}}")
}
}
/// A wrapper to customize partitioned group of files display
///
/// Prints in the format:
/// ```text
/// [file1, file2,...]
/// ```
#[derive(Debug)]
pub(crate) struct FileGroupDisplay<'a>(pub &'a [PartitionedFile]);
impl<'a> DisplayAs for FileGroupDisplay<'a> {
fn fmt_as(&self, t: DisplayFormatType, f: &mut Formatter) -> FmtResult {
write!(f, "[")?;
match t {
DisplayFormatType::Default => {
// To avoid showing too many files
let max_files = 5;
fmt_up_to_n_elements(self.0, max_files, f, |pf, f| {
write!(f, "{}", pf.object_meta.location.as_ref())?;
if let Some(range) = pf.range.as_ref() {
write!(f, ":{}..{}", range.start, range.end)?;
}
Ok(())
})?
}
DisplayFormatType::Verbose => {
fmt_elements_split_by_commas(self.0.iter(), f, |pf, f| {
write!(f, "{}", pf.object_meta.location.as_ref())?;
if let Some(range) = pf.range.as_ref() {
write!(f, ":{}..{}", range.start, range.end)?;
}
Ok(())
})?
}
}
write!(f, "]")
}
}
/// helper to format an array of up to N elements
fn fmt_up_to_n_elements<E, F>(
elements: &[E],
n: usize,
f: &mut Formatter,
format_element: F,
) -> FmtResult
where
F: Fn(&E, &mut Formatter) -> FmtResult,
{
let len = elements.len();
fmt_elements_split_by_commas(elements.iter().take(n), f, |element, f| {
format_element(element, f)
})?;
// Remaining elements are showed as `...` (to indicate there is more)
if len > n {
write!(f, ", ...")?;
}
Ok(())
}
/// helper formatting array elements with a comma and a space between them
fn fmt_elements_split_by_commas<E, I, F>(
iter: I,
f: &mut Formatter,
format_element: F,
) -> FmtResult
where
I: Iterator<Item = E>,
F: Fn(E, &mut Formatter) -> FmtResult,
{
for (idx, element) in iter.enumerate() {
if idx > 0 {
write!(f, ", ")?;
}
format_element(element, f)?;
}
Ok(())
}
/// A single file or part of a file that should be read, along with its schema, statistics
pub struct FileMeta {
/// Path for the file (e.g. URL, filesystem path, etc)
pub object_meta: ObjectMeta,
/// An optional file range for a more fine-grained parallel execution
pub range: Option<FileRange>,
/// An optional field for user defined per object metadata
pub extensions: Option<Arc<dyn std::any::Any + Send + Sync>>,
}
impl FileMeta {
/// The full path to the object
pub fn location(&self) -> &Path {
&self.object_meta.location
}
}
impl From<ObjectMeta> for FileMeta {
fn from(object_meta: ObjectMeta) -> Self {
Self {
object_meta,
range: None,
extensions: None,
}
}
}
/// The various listing tables does not attempt to read all files
/// concurrently, instead they will read files in sequence within a
/// partition. This is an important property as it allows plans to
/// run against 1000s of files and not try to open them all
/// concurrently.
///
/// However, it means if we assign more than one file to a partition
/// the output sort order will not be preserved as illustrated in the
/// following diagrams:
///
/// When only 1 file is assigned to each partition, each partition is
/// correctly sorted on `(A, B, C)`
///
/// ```text
///┏ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ┓
/// ┌ ─ ─ ─ ─ ─ ─ ─ ─ ─ ┐ ┌ ─ ─ ─ ─ ─ ─ ─ ─ ─ ┌ ─ ─ ─ ─ ─ ─ ─ ─ ─ ┌ ─ ─ ─ ─ ─ ─ ─ ─ ┐
///┃ ┌───────────────┐ ┌──────────────┐ │ ┌──────────────┐ │ ┌─────────────┐ ┃
/// │ │ 1.parquet │ │ │ │ 2.parquet │ │ │ 3.parquet │ │ │ 4.parquet │ │
///┃ │ Sort: A, B, C │ │Sort: A, B, C │ │ │Sort: A, B, C │ │ │Sort: A, B, C│ ┃
/// │ └───────────────┘ │ │ └──────────────┘ │ └──────────────┘ │ └─────────────┘ │
///┃ │ │ ┃
/// │ │ │ │ │ │
///┃ │ │ ┃
/// │ │ │ │ │ │
///┃ │ │ ┃
/// │ │ │ │ │ │
///┃ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ┘ ─ ─ ─ ─ ─ ─ ─ ─ ─ ┘ ─ ─ ─ ─ ─ ─ ─ ─ ─ ┃
/// DataFusion DataFusion DataFusion DataFusion
///┃ Partition 1 Partition 2 Partition 3 Partition 4 ┃
/// ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━
///
/// ParquetExec
///```
///
/// However, when more than 1 file is assigned to each partition, each
/// partition is NOT correctly sorted on `(A, B, C)`. Once the second
/// file is scanned, the same values for A, B and C can be repeated in
/// the same sorted stream
///
///```text
///┏ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━
/// ┌ ─ ─ ─ ─ ─ ─ ─ ─ ─ ┐ ┌ ─ ─ ─ ─ ─ ─ ─ ─ ─ ┃
///┃ ┌───────────────┐ ┌──────────────┐ │
/// │ │ 1.parquet │ │ │ │ 2.parquet │ ┃
///┃ │ Sort: A, B, C │ │Sort: A, B, C │ │
/// │ └───────────────┘ │ │ └──────────────┘ ┃
///┃ ┌───────────────┐ ┌──────────────┐ │
/// │ │ 3.parquet │ │ │ │ 4.parquet │ ┃
///┃ │ Sort: A, B, C │ │Sort: A, B, C │ │
/// │ └───────────────┘ │ │ └──────────────┘ ┃
///┃ │
/// │ │ │ ┃
///┃ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ┘
/// DataFusion DataFusion ┃
///┃ Partition 1 Partition 2
/// ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ━ ┛
///
/// ParquetExec
///```
fn get_projected_output_ordering(
base_config: &FileScanConfig,
projected_schema: &SchemaRef,
) -> Vec<Vec<PhysicalSortExpr>> {
let mut all_orderings = vec![];
for output_ordering in &base_config.output_ordering {
let mut new_ordering = vec![];
for PhysicalSortExpr { expr, options } in output_ordering {
if let Some(col) = expr.as_any().downcast_ref::<Column>() {
let name = col.name();
if let Some((idx, _)) = projected_schema.column_with_name(name) {
// Compute the new sort expression (with correct index) after projection:
new_ordering.push(PhysicalSortExpr {
expr: Arc::new(Column::new(name, idx)),
options: *options,
});
continue;
}
}
// Cannot find expression in the projected_schema, stop iterating
// since rest of the orderings are violated
break;
}
// do not push empty entries
// otherwise we may have `Some(vec![])` at the output ordering.
if new_ordering.is_empty() {
continue;
}
// Check if any file groups are not sorted
if base_config.file_groups.iter().any(|group| {
if group.len() <= 1 {
// File groups with <= 1 files are always sorted
return false;
}
let statistics = match statistics::MinMaxStatistics::new_from_files(
&new_ordering,
projected_schema,
base_config.projection.as_deref(),
group,
) {
Ok(statistics) => statistics,
Err(e) => {
log::trace!("Error fetching statistics for file group: {e}");
// we can't prove that it's ordered, so we have to reject it
return true;
}
};
!statistics.is_sorted()
}) {
debug!(
"Skipping specified output ordering {:?}. \
Some file groups couldn't be determined to be sorted: {:?}",
base_config.output_ordering[0], base_config.file_groups
);
continue;
}
all_orderings.push(new_ordering);
}
all_orderings
}
/// Represents the possible outcomes of a range calculation.
///
/// This enum is used to encapsulate the result of calculating the range of
/// bytes to read from an object (like a file) in an object store.
///
/// Variants:
/// - `Range(Option<Range<usize>>)`:
/// Represents a range of bytes to be read. It contains an `Option` wrapping a
/// `Range<usize>`. `None` signifies that the entire object should be read,
/// while `Some(range)` specifies the exact byte range to read.
/// - `TerminateEarly`:
/// Indicates that the range calculation determined no further action is
/// necessary, possibly because the calculated range is empty or invalid.
enum RangeCalculation {
Range(Option<Range<usize>>),
TerminateEarly,
}
/// Calculates an appropriate byte range for reading from an object based on the
/// provided metadata.
///
/// This asynchronous function examines the `FileMeta` of an object in an object store
/// and determines the range of bytes to be read. The range calculation may adjust
/// the start and end points to align with meaningful data boundaries (like newlines).
///
/// Returns a `Result` wrapping a `RangeCalculation`, which is either a calculated byte range or an indication to terminate early.
///
/// Returns an `Error` if any part of the range calculation fails, such as issues in reading from the object store or invalid range boundaries.
async fn calculate_range(
file_meta: &FileMeta,
store: &Arc<dyn ObjectStore>,
) -> Result<RangeCalculation> {
let location = file_meta.location();
let file_size = file_meta.object_meta.size;
match file_meta.range {
None => Ok(RangeCalculation::Range(None)),
Some(FileRange { start, end }) => {
let (start, end) = (start as usize, end as usize);
let start_delta = if start != 0 {
find_first_newline(store, location, start - 1, file_size).await?
} else {
0
};
let end_delta = if end != file_size {
find_first_newline(store, location, end - 1, file_size).await?
} else {
0
};
let range = start + start_delta..end + end_delta;
if range.start == range.end {
return Ok(RangeCalculation::TerminateEarly);
}
Ok(RangeCalculation::Range(Some(range)))
}
}
}
/// Asynchronously finds the position of the first newline character in a specified byte range
/// within an object, such as a file, in an object store.
///
/// This function scans the contents of the object starting from the specified `start` position
/// up to the `end` position, looking for the first occurrence of a newline (`'\n'`) character.
/// It returns the position of the first newline relative to the start of the range.
///
/// Returns a `Result` wrapping a `usize` that represents the position of the first newline character found within the specified range. If no newline is found, it returns the length of the scanned data, effectively indicating the end of the range.
///
/// The function returns an `Error` if any issues arise while reading from the object store or processing the data stream.
///
async fn find_first_newline(
object_store: &Arc<dyn ObjectStore>,
location: &Path,
start: usize,
end: usize,
) -> Result<usize> {
let options = GetOptions {
range: Some(GetRange::Bounded(start..end)),
..Default::default()
};
let result = object_store.get_opts(location, options).await?;
let mut result_stream = result.into_stream();
let mut index = 0;
while let Some(chunk) = result_stream.next().await.transpose()? {
if let Some(position) = chunk.iter().position(|&byte| byte == b'\n') {
return Ok(index + position);
}
index += chunk.len();
}
Ok(index)
}
#[cfg(test)]
mod tests {
use super::*;
use crate::physical_plan::{DefaultDisplay, VerboseDisplay};
use arrow_array::cast::AsArray;
use arrow_array::types::{Float32Type, Float64Type, UInt32Type};
use arrow_array::{
BinaryArray, BooleanArray, Float32Array, Int32Array, Int64Array, RecordBatch,
StringArray, UInt64Array,
};
use arrow_schema::{Field, Schema};
use crate::datasource::schema_adapter::{
DefaultSchemaAdapterFactory, SchemaAdapterFactory,
};
use chrono::Utc;
#[test]
fn schema_mapping_map_batch() {
let table_schema = Arc::new(Schema::new(vec![
Field::new("c1", DataType::Utf8, true),
Field::new("c2", DataType::UInt32, true),
Field::new("c3", DataType::Float64, true),
]));
let adapter = DefaultSchemaAdapterFactory::default().create(table_schema.clone());
let file_schema = Schema::new(vec![
Field::new("c1", DataType::Utf8, true),
Field::new("c2", DataType::UInt64, true),
Field::new("c3", DataType::Float32, true),
]);
let (mapping, _) = adapter.map_schema(&file_schema).expect("map schema failed");
let c1 = StringArray::from(vec!["hello", "world"]);
let c2 = UInt64Array::from(vec![9_u64, 5_u64]);
let c3 = Float32Array::from(vec![2.0_f32, 7.0_f32]);
let batch = RecordBatch::try_new(
Arc::new(file_schema),
vec![Arc::new(c1), Arc::new(c2), Arc::new(c3)],
)
.unwrap();
let mapped_batch = mapping.map_batch(batch).unwrap();
assert_eq!(mapped_batch.schema(), table_schema);
assert_eq!(mapped_batch.num_columns(), 3);
assert_eq!(mapped_batch.num_rows(), 2);
let c1 = mapped_batch.column(0).as_string::<i32>();
let c2 = mapped_batch.column(1).as_primitive::<UInt32Type>();
let c3 = mapped_batch.column(2).as_primitive::<Float64Type>();
assert_eq!(c1.value(0), "hello");
assert_eq!(c1.value(1), "world");
assert_eq!(c2.value(0), 9_u32);
assert_eq!(c2.value(1), 5_u32);
assert_eq!(c3.value(0), 2.0_f64);
assert_eq!(c3.value(1), 7.0_f64);
}
#[test]
fn schema_adapter_map_schema_with_projection() {
let table_schema = Arc::new(Schema::new(vec![
Field::new("c0", DataType::Utf8, true),
Field::new("c1", DataType::Utf8, true),
Field::new("c2", DataType::Float64, true),
Field::new("c3", DataType::Int32, true),
Field::new("c4", DataType::Float32, true),
]));
let file_schema = Schema::new(vec![
Field::new("id", DataType::Int32, true),
Field::new("c1", DataType::Boolean, true),
Field::new("c2", DataType::Float32, true),
Field::new("c3", DataType::Binary, true),
Field::new("c4", DataType::Int64, true),
]);
let indices = vec![1, 2, 4];
let schema = SchemaRef::from(table_schema.project(&indices).unwrap());
let adapter = DefaultSchemaAdapterFactory::default().create(schema);
let (mapping, projection) = adapter.map_schema(&file_schema).unwrap();
let id = Int32Array::from(vec![Some(1), Some(2), Some(3)]);
let c1 = BooleanArray::from(vec![Some(true), Some(false), Some(true)]);
let c2 = Float32Array::from(vec![Some(2.0_f32), Some(7.0_f32), Some(3.0_f32)]);
let c3 = BinaryArray::from_opt_vec(vec![
Some(b"hallo"),
Some(b"danke"),
Some(b"super"),
]);
let c4 = Int64Array::from(vec![1, 2, 3]);
let batch = RecordBatch::try_new(
Arc::new(file_schema),
vec![
Arc::new(id),
Arc::new(c1),
Arc::new(c2),
Arc::new(c3),
Arc::new(c4),
],
)
.unwrap();
let rows_num = batch.num_rows();
let projected = batch.project(&projection).unwrap();
let mapped_batch = mapping.map_batch(projected).unwrap();
assert_eq!(
mapped_batch.schema(),
Arc::new(table_schema.project(&indices).unwrap())
);
assert_eq!(mapped_batch.num_columns(), indices.len());
assert_eq!(mapped_batch.num_rows(), rows_num);
let c1 = mapped_batch.column(0).as_string::<i32>();
let c2 = mapped_batch.column(1).as_primitive::<Float64Type>();
let c4 = mapped_batch.column(2).as_primitive::<Float32Type>();
assert_eq!(c1.value(0), "true");
assert_eq!(c1.value(1), "false");
assert_eq!(c1.value(2), "true");
assert_eq!(c2.value(0), 2.0_f64);
assert_eq!(c2.value(1), 7.0_f64);
assert_eq!(c2.value(2), 3.0_f64);
assert_eq!(c4.value(0), 1.0_f32);
assert_eq!(c4.value(1), 2.0_f32);
assert_eq!(c4.value(2), 3.0_f32);
}
#[test]
fn file_groups_display_empty() {
let expected = "{0 groups: []}";
assert_eq!(DefaultDisplay(FileGroupsDisplay(&[])).to_string(), expected);
}
#[test]
fn file_groups_display_one() {
let files = [vec![partitioned_file("foo"), partitioned_file("bar")]];
let expected = "{1 group: [[foo, bar]]}";
assert_eq!(
DefaultDisplay(FileGroupsDisplay(&files)).to_string(),
expected
);
}
#[test]
fn file_groups_display_many_default() {
let files = [
vec![partitioned_file("foo"), partitioned_file("bar")],
vec![partitioned_file("baz")],
vec![],
];
let expected = "{3 groups: [[foo, bar], [baz], []]}";
assert_eq!(
DefaultDisplay(FileGroupsDisplay(&files)).to_string(),
expected
);
}
#[test]
fn file_groups_display_many_verbose() {
let files = [
vec![partitioned_file("foo"), partitioned_file("bar")],
vec![partitioned_file("baz")],
vec![],
];
let expected = "{3 groups: [[foo, bar], [baz], []]}";
assert_eq!(
VerboseDisplay(FileGroupsDisplay(&files)).to_string(),
expected
);
}
#[test]
fn file_groups_display_too_many_default() {
let files = [
vec![partitioned_file("foo"), partitioned_file("bar")],
vec![partitioned_file("baz")],
vec![partitioned_file("qux")],
vec![partitioned_file("quux")],
vec![partitioned_file("quuux")],
vec![partitioned_file("quuuux")],
vec![],
];
let expected = "{7 groups: [[foo, bar], [baz], [qux], [quux], [quuux], ...]}";
assert_eq!(
DefaultDisplay(FileGroupsDisplay(&files)).to_string(),
expected
);
}
#[test]
fn file_groups_display_too_many_verbose() {
let files = [
vec![partitioned_file("foo"), partitioned_file("bar")],
vec![partitioned_file("baz")],
vec![partitioned_file("qux")],
vec![partitioned_file("quux")],
vec![partitioned_file("quuux")],
vec![partitioned_file("quuuux")],
vec![],
];
let expected =
"{7 groups: [[foo, bar], [baz], [qux], [quux], [quuux], [quuuux], []]}";
assert_eq!(
VerboseDisplay(FileGroupsDisplay(&files)).to_string(),
expected
);
}
#[test]
fn file_group_display_many_default() {
let files = vec![partitioned_file("foo"), partitioned_file("bar")];
let expected = "[foo, bar]";
assert_eq!(
DefaultDisplay(FileGroupDisplay(&files)).to_string(),
expected
);
}
#[test]
fn file_group_display_too_many_default() {
let files = vec![
partitioned_file("foo"),
partitioned_file("bar"),
partitioned_file("baz"),
partitioned_file("qux"),
partitioned_file("quux"),
partitioned_file("quuux"),
];
let expected = "[foo, bar, baz, qux, quux, ...]";
assert_eq!(
DefaultDisplay(FileGroupDisplay(&files)).to_string(),
expected
);
}
#[test]
fn file_group_display_too_many_verbose() {
let files = vec![
partitioned_file("foo"),
partitioned_file("bar"),
partitioned_file("baz"),
partitioned_file("qux"),
partitioned_file("quux"),
partitioned_file("quuux"),
];
let expected = "[foo, bar, baz, qux, quux, quuux]";
assert_eq!(
VerboseDisplay(FileGroupDisplay(&files)).to_string(),
expected
);
}
/// create a PartitionedFile for testing
fn partitioned_file(path: &str) -> PartitionedFile {
let object_meta = ObjectMeta {
location: object_store::path::Path::parse(path).unwrap(),
last_modified: Utc::now(),
size: 42,
e_tag: None,
version: None,
};
PartitionedFile {
object_meta,
partition_values: vec![],
range: None,
statistics: None,
extensions: None,
}
}
}