andygrove commented on a change in pull request #8840: URL: https://github.com/apache/arrow/pull/8840#discussion_r537057816
########## File path: rust/datafusion/src/logical_plan/dfschema.rs ########## @@ -0,0 +1,415 @@ +// 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. + +//! DFSchema is an extended schema struct that DataFusion uses to provide support for +//! fields with optional relation names. + +use std::collections::HashSet; +use std::sync::Arc; + +use crate::error::{DataFusionError, Result}; + +use arrow::datatypes::{DataType, Field, Schema, SchemaRef}; +use std::fmt::{Display, Formatter}; + +/// A reference-counted reference to a `DFSchema`. +pub type DFSchemaRef = Arc<DFSchema>; + +/// DFSchema wraps an Arrow schema and adds relation names +#[derive(Debug, Clone, PartialEq, Eq)] +pub struct DFSchema { + /// Fields + fields: Vec<DFField>, +} + +impl DFSchema { + /// Creates an empty `DFSchema` + pub fn empty() -> Self { + Self { fields: vec![] } + } + + /// Create a new `DFSchema` + pub fn new(fields: Vec<DFField>) -> Result<Self> { + let mut qualified_names: HashSet<(&str, &str)> = HashSet::new(); + let mut unqualified_names: HashSet<&str> = HashSet::new(); + for field in &fields { + if let Some(qualifier) = field.qualifier() { + if !qualified_names.insert((qualifier, field.name())) { + return Err(DataFusionError::Plan(format!( + "Joined schema would contain duplicate qualified field name '{}'", + field.qualified_name() + ))); + } + } else { + if !unqualified_names.insert(field.name()) { + return Err(DataFusionError::Plan( + format!("Joined schema would contain duplicate unqualified field name '{}'", + field.name()) + )); + } + } + } + + // check for mix of qualified and unqualified field with same unqualified name + // note that we need to sort the contents of the HashSet first so that errors are + // deterministic + let mut qualified_names: Vec<&(&str, &str)> = qualified_names.iter().collect(); + qualified_names.sort_by(|a, b| { + let a = format!("{}.{}", a.0, a.1); + let b = format!("{}.{}", b.0, b.1); + a.cmp(&b) + }); + for (qualifier, name) in &qualified_names { + if unqualified_names.contains(name) { + return Err(DataFusionError::Plan(format!( + "Joined schema would contain qualified field name '{}.{}' \ + and unqualified field name '{}' which would be ambiguous", + qualifier, name, name + ))); + } + } + Ok(Self { fields }) + } + + /// Create a `DFSchema` from an Arrow schema + pub fn from(schema: &Schema) -> Result<Self> { + Self::new( + schema + .fields() + .iter() + .map(|f| DFField { + field: f.clone(), + qualifier: None, + }) + .collect(), + ) + } + + /// Create a `DFSchema` from an Arrow schema + pub fn from_qualified(qualifier: &str, schema: &Schema) -> Result<Self> { + Self::new( + schema + .fields() + .iter() + .map(|f| DFField { + field: f.clone(), + qualifier: Some(qualifier.to_owned()), + }) + .collect(), + ) + } + + /// Combine two schemas + pub fn join(&self, schema: &DFSchema) -> Result<Self> { + let mut fields = self.fields.clone(); + fields.extend_from_slice(schema.fields().as_slice()); Review comment: Actually, the very next line here is calling `Self::new` so we are doing the required validation and the tests are covering this. ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected]
