|
| 1 | +// Licensed to the Apache Software Foundation (ASF) under one |
| 2 | +// or more contributor license agreements. See the NOTICE file |
| 3 | +// distributed with this work for additional information |
| 4 | +// regarding copyright ownership. The ASF licenses this file |
| 5 | +// to you under the Apache License, Version 2.0 (the |
| 6 | +// "License"); you may not use this file except in compliance |
| 7 | +// with the License. You may obtain a copy of the License at |
| 8 | +// |
| 9 | +// http://www.apache.org/licenses/LICENSE-2.0 |
| 10 | +// |
| 11 | +// Unless required by applicable law or agreed to in writing, |
| 12 | +// software distributed under the License is distributed on an |
| 13 | +// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY |
| 14 | +// KIND, either express or implied. See the License for the |
| 15 | +// specific language governing permissions and limitations |
| 16 | +// under the License. |
| 17 | + |
| 18 | +use std::fmt::{self, Display}; |
| 19 | +use std::str::FromStr; |
| 20 | + |
| 21 | +use crate::config::{ConfigField, Visit}; |
| 22 | +use crate::error::{DataFusionError, Result}; |
| 23 | + |
| 24 | +/// Parquet writer version options for controlling the Parquet file format version |
| 25 | +/// |
| 26 | +/// This enum validates parquet writer version values at configuration time, |
| 27 | +/// ensuring only valid versions ("1.0" or "2.0") can be set via `SET` commands |
| 28 | +/// or proto deserialization. |
| 29 | +#[derive(Debug, Clone, Copy, PartialEq, Eq, Default)] |
| 30 | +pub enum DFParquetWriterVersion { |
| 31 | + /// Parquet format version 1.0 |
| 32 | + #[default] |
| 33 | + V1_0, |
| 34 | + /// Parquet format version 2.0 |
| 35 | + V2_0, |
| 36 | +} |
| 37 | + |
| 38 | +/// Implement parsing strings to `DFParquetWriterVersion` |
| 39 | +impl FromStr for DFParquetWriterVersion { |
| 40 | + type Err = DataFusionError; |
| 41 | + |
| 42 | + fn from_str(s: &str) -> Result<Self, Self::Err> { |
| 43 | + match s.to_lowercase().as_str() { |
| 44 | + "1.0" => Ok(DFParquetWriterVersion::V1_0), |
| 45 | + "2.0" => Ok(DFParquetWriterVersion::V2_0), |
| 46 | + other => Err(DataFusionError::Configuration(format!( |
| 47 | + "Invalid parquet writer version: {other}. Expected one of: 1.0, 2.0" |
| 48 | + ))), |
| 49 | + } |
| 50 | + } |
| 51 | +} |
| 52 | + |
| 53 | +impl Display for DFParquetWriterVersion { |
| 54 | + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { |
| 55 | + let s = match self { |
| 56 | + DFParquetWriterVersion::V1_0 => "1.0", |
| 57 | + DFParquetWriterVersion::V2_0 => "2.0", |
| 58 | + }; |
| 59 | + write!(f, "{s}") |
| 60 | + } |
| 61 | +} |
| 62 | + |
| 63 | +impl ConfigField for DFParquetWriterVersion { |
| 64 | + fn visit<V: Visit>(&self, v: &mut V, key: &str, description: &'static str) { |
| 65 | + v.some(key, self, description) |
| 66 | + } |
| 67 | + |
| 68 | + fn set(&mut self, _: &str, value: &str) -> Result<()> { |
| 69 | + *self = DFParquetWriterVersion::from_str(value)?; |
| 70 | + Ok(()) |
| 71 | + } |
| 72 | +} |
| 73 | + |
| 74 | +/// Convert `DFParquetWriterVersion` to parquet crate's `WriterVersion` |
| 75 | +/// |
| 76 | +/// This conversion is infallible since `DFParquetWriterVersion` only contains |
| 77 | +/// valid values that have been validated at configuration time. |
| 78 | +#[cfg(feature = "parquet")] |
| 79 | +impl From<DFParquetWriterVersion> for parquet::file::properties::WriterVersion { |
| 80 | + fn from(value: DFParquetWriterVersion) -> Self { |
| 81 | + match value { |
| 82 | + DFParquetWriterVersion::V1_0 => { |
| 83 | + parquet::file::properties::WriterVersion::PARQUET_1_0 |
| 84 | + } |
| 85 | + DFParquetWriterVersion::V2_0 => { |
| 86 | + parquet::file::properties::WriterVersion::PARQUET_2_0 |
| 87 | + } |
| 88 | + } |
| 89 | + } |
| 90 | +} |
| 91 | + |
| 92 | +/// Convert parquet crate's `WriterVersion` to `DFParquetWriterVersion` |
| 93 | +/// |
| 94 | +/// This is used when converting from existing parquet writer properties, |
| 95 | +/// such as when reading from proto or test code. |
| 96 | +#[cfg(feature = "parquet")] |
| 97 | +impl From<parquet::file::properties::WriterVersion> for DFParquetWriterVersion { |
| 98 | + fn from(version: parquet::file::properties::WriterVersion) -> Self { |
| 99 | + match version { |
| 100 | + parquet::file::properties::WriterVersion::PARQUET_1_0 => { |
| 101 | + DFParquetWriterVersion::V1_0 |
| 102 | + } |
| 103 | + parquet::file::properties::WriterVersion::PARQUET_2_0 => { |
| 104 | + DFParquetWriterVersion::V2_0 |
| 105 | + } |
| 106 | + } |
| 107 | + } |
| 108 | +} |
0 commit comments