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
// 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.
use std::sync::Arc;
use super::super::options::{ParquetReadOptions, ReadOptions};
use super::{DataFilePaths, DataFrame, ExecutionPlan, Result, SessionContext};
use crate::datasource::physical_plan::parquet::plan_to_parquet;
use parquet::file::properties::WriterProperties;
impl SessionContext {
/// Creates a [`DataFrame`] for reading a Parquet data source.
///
/// For more control such as reading multiple files, you can use
/// [`read_table`](Self::read_table) with a [`super::ListingTable`].
///
/// For an example, see [`read_csv`](Self::read_csv)
pub async fn read_parquet<P: DataFilePaths>(
&self,
table_paths: P,
options: ParquetReadOptions<'_>,
) -> Result<DataFrame> {
self._read_type(table_paths, options).await
}
/// Registers a Parquet file as a table that can be referenced from SQL
/// statements executed against this context.
pub async fn register_parquet(
&self,
name: &str,
table_path: &str,
options: ParquetReadOptions<'_>,
) -> Result<()> {
let listing_options = options
.to_listing_options(&self.copied_config(), self.copied_table_options());
self.register_listing_table(
name,
table_path,
listing_options,
options.schema.map(|s| Arc::new(s.to_owned())),
None,
)
.await?;
Ok(())
}
/// Executes a query and writes the results to a partitioned Parquet file.
pub async fn write_parquet(
&self,
plan: Arc<dyn ExecutionPlan>,
path: impl AsRef<str>,
writer_properties: Option<WriterProperties>,
) -> Result<()> {
plan_to_parquet(self.task_ctx(), plan, path, writer_properties).await
}
}
#[cfg(test)]
mod tests {
use super::*;
use crate::arrow::array::{Float32Array, Int32Array};
use crate::arrow::datatypes::{DataType, Field, Schema};
use crate::arrow::record_batch::RecordBatch;
use crate::dataframe::DataFrameWriteOptions;
use crate::parquet::basic::Compression;
use crate::test_util::parquet_test_data;
use datafusion_common::config::TableParquetOptions;
use datafusion_execution::config::SessionConfig;
use async_trait::async_trait;
use tempfile::tempdir;
#[tokio::test]
async fn read_with_glob_path() -> Result<()> {
let ctx = SessionContext::new();
let df = ctx
.read_parquet(
format!("{}/alltypes_plain*.parquet", parquet_test_data()),
ParquetReadOptions::default(),
)
.await?;
let results = df.collect().await?;
let total_rows: usize = results.iter().map(|rb| rb.num_rows()).sum();
// alltypes_plain.parquet = 8 rows, alltypes_plain.snappy.parquet = 2 rows, alltypes_dictionary.parquet = 2 rows
assert_eq!(total_rows, 10);
Ok(())
}
#[tokio::test]
async fn read_with_glob_path_issue_2465() -> Result<()> {
let config =
SessionConfig::from_string_hash_map(std::collections::HashMap::from([(
"datafusion.execution.listing_table_ignore_subdirectory".to_owned(),
"false".to_owned(),
)]))?;
let ctx = SessionContext::new_with_config(config);
let df = ctx
.read_parquet(
// it was reported that when a path contains // (two consecutive separator) no files were found
// in this test, regardless of parquet_test_data() value, our path now contains a //
format!("{}/..//*/alltypes_plain*.parquet", parquet_test_data()),
ParquetReadOptions::default(),
)
.await?;
let results = df.collect().await?;
let total_rows: usize = results.iter().map(|rb| rb.num_rows()).sum();
// alltypes_plain.parquet = 8 rows, alltypes_plain.snappy.parquet = 2 rows, alltypes_dictionary.parquet = 2 rows
assert_eq!(total_rows, 10);
Ok(())
}
#[tokio::test]
async fn read_from_registered_table_with_glob_path() -> Result<()> {
let ctx = SessionContext::new();
ctx.register_parquet(
"test",
&format!("{}/alltypes_plain*.parquet", parquet_test_data()),
ParquetReadOptions::default(),
)
.await?;
let df = ctx.sql("SELECT * FROM test").await?;
let results = df.collect().await?;
let total_rows: usize = results.iter().map(|rb| rb.num_rows()).sum();
// alltypes_plain.parquet = 8 rows, alltypes_plain.snappy.parquet = 2 rows, alltypes_dictionary.parquet = 2 rows
assert_eq!(total_rows, 10);
Ok(())
}
#[tokio::test]
async fn read_from_different_file_extension() -> Result<()> {
let ctx = SessionContext::new();
let sep = std::path::MAIN_SEPARATOR.to_string();
// Make up a new dataframe.
let write_df = ctx.read_batch(RecordBatch::try_new(
Arc::new(Schema::new(vec![
Field::new("purchase_id", DataType::Int32, false),
Field::new("price", DataType::Float32, false),
Field::new("quantity", DataType::Int32, false),
])),
vec![
Arc::new(Int32Array::from(vec![1, 2, 3, 4, 5])),
Arc::new(Float32Array::from(vec![1.12, 3.40, 2.33, 9.10, 6.66])),
Arc::new(Int32Array::from(vec![1, 3, 2, 4, 3])),
],
)?)?;
let temp_dir = tempdir()?;
let temp_dir_path = temp_dir.path();
let path1 = temp_dir_path
.join("output1.parquet")
.to_str()
.unwrap()
.to_string();
let path2 = temp_dir_path
.join("output2.parquet.snappy")
.to_str()
.unwrap()
.to_string();
let path3 = temp_dir_path
.join("output3.parquet.snappy.parquet")
.to_str()
.unwrap()
.to_string();
let path4 = temp_dir_path
.join("output4.parquet".to_owned() + &sep)
.to_str()
.unwrap()
.to_string();
let path5 = temp_dir_path
.join("bbb..bbb")
.join("filename.parquet")
.to_str()
.unwrap()
.to_string();
let dir = temp_dir_path
.join("bbb..bbb".to_owned() + &sep)
.to_str()
.unwrap()
.to_string();
std::fs::create_dir(dir).expect("create dir failed");
let mut options = TableParquetOptions::default();
options.global.compression = Some(Compression::SNAPPY.to_string());
// Write the dataframe to a parquet file named 'output1.parquet'
write_df
.clone()
.write_parquet(
&path1,
DataFrameWriteOptions::new().with_single_file_output(true),
Some(options.clone()),
)
.await?;
// Write the dataframe to a parquet file named 'output2.parquet.snappy'
write_df
.clone()
.write_parquet(
&path2,
DataFrameWriteOptions::new().with_single_file_output(true),
Some(options.clone()),
)
.await?;
// Write the dataframe to a parquet file named 'output3.parquet.snappy.parquet'
write_df
.clone()
.write_parquet(
&path3,
DataFrameWriteOptions::new().with_single_file_output(true),
Some(options.clone()),
)
.await?;
// Write the dataframe to a parquet file named 'bbb..bbb/filename.parquet'
write_df
.write_parquet(
&path5,
DataFrameWriteOptions::new().with_single_file_output(true),
Some(options),
)
.await?;
// Read the dataframe from 'output1.parquet' with the default file extension.
let read_df = ctx
.read_parquet(
&path1,
ParquetReadOptions {
..Default::default()
},
)
.await?;
let results = read_df.collect().await?;
let total_rows: usize = results.iter().map(|rb| rb.num_rows()).sum();
assert_eq!(total_rows, 5);
// Read the dataframe from 'output2.parquet.snappy' with the correct file extension.
let read_df = ctx
.read_parquet(
&path2,
ParquetReadOptions {
file_extension: "snappy",
..Default::default()
},
)
.await?;
let results = read_df.collect().await?;
let total_rows: usize = results.iter().map(|rb| rb.num_rows()).sum();
assert_eq!(total_rows, 5);
// Read the dataframe from 'output3.parquet.snappy.parquet' with the wrong file extension.
let read_df = ctx
.read_parquet(
&path2,
ParquetReadOptions {
..Default::default()
},
)
.await;
let binding = DataFilePaths::to_urls(&path2).unwrap();
let expexted_path = binding[0].as_str();
assert_eq!(
read_df.unwrap_err().strip_backtrace(),
format!("Execution error: File path '{}' does not match the expected extension '.parquet'", expexted_path)
);
// Read the dataframe from 'output3.parquet.snappy.parquet' with the correct file extension.
let read_df = ctx
.read_parquet(
&path3,
ParquetReadOptions {
..Default::default()
},
)
.await?;
let results = read_df.collect().await?;
let total_rows: usize = results.iter().map(|rb| rb.num_rows()).sum();
assert_eq!(total_rows, 5);
// Read the dataframe from 'output4/'
std::fs::create_dir(&path4)?;
let read_df = ctx
.read_parquet(
&path4,
ParquetReadOptions {
..Default::default()
},
)
.await?;
let results = read_df.collect().await?;
let total_rows: usize = results.iter().map(|rb| rb.num_rows()).sum();
assert_eq!(total_rows, 0);
// Read the datafram from doule dot folder;
let read_df = ctx
.read_parquet(
&path5,
ParquetReadOptions {
..Default::default()
},
)
.await?;
let results = read_df.collect().await?;
let total_rows: usize = results.iter().map(|rb| rb.num_rows()).sum();
assert_eq!(total_rows, 5);
Ok(())
}
// Test for compilation error when calling read_* functions from an #[async_trait] function.
// See https://github.com/apache/arrow-datafusion/issues/1154
#[async_trait]
trait CallReadTrait {
async fn call_read_parquet(&self) -> DataFrame;
}
struct CallRead {}
#[async_trait]
impl CallReadTrait for CallRead {
async fn call_read_parquet(&self) -> DataFrame {
let ctx = SessionContext::new();
ctx.read_parquet("dummy", ParquetReadOptions::default())
.await
.unwrap()
}
}
}