move schema projection function from arrow into datafusion

Author: andygrove

rust/arrow/src/datatypes.rs

@@ -26,7 +26,6 @@ use std::mem::size_of;
 use std::ops::{Add, Div, Mul, Sub};
 use std::slice::from_raw_parts;
 use std::str::FromStr;
-use std::sync::Arc;
 
 use packed_simd::*;
 use serde_derive::{Deserialize, Serialize};
@@ -752,22 +751,6 @@ impl Schema {
             "fields": self.fields.iter().map(|field| field.to_json()).collect::<Vec<Value>>(),
         })
     }
-
-    /// Create a new schema by applying a projection to this schema's fields
-    pub fn projection(&self, projection: &[usize]) -> Result<Arc<Schema>> {
-        let mut fields: Vec<Field> = Vec::with_capacity(projection.len());
-        for i in projection {
-            if *i < self.fields().len() {
-                fields.push(self.field(*i).clone());
-            } else {
-                return Err(ArrowError::InvalidArgumentError(format!(
-                    "Invalid column index {} in projection",
-                    i
-                )));
-            }
-        }
-        Ok(Arc::new(Schema::new(fields)))
-    }
 }
 
 impl fmt::Display for Schema {

rust/datafusion/src/datasource/parquet.rs

@@ -208,7 +208,7 @@ impl ParquetFile {
             }
         };
 
-        let projected_schema = schema.projection(&projection)?;
+        let projected_schema = schema_projection(&schema, &projection)?;
 
         Ok(ParquetFile {
             reader: reader,
@@ -337,6 +337,22 @@ impl ParquetFile {
     }
 }
 
+/// Create a new schema by applying a projection to this schema's fields
+fn schema_projection(schema: &Schema, projection: &[usize]) -> Result<Arc<Schema>> {
+    let mut fields: Vec<Field> = Vec::with_capacity(projection.len());
+    for i in projection {
+        if *i < schema.fields().len() {
+            fields.push(schema.field(*i).clone());
+        } else {
+            return Err(ExecutionError::InvalidColumn(format!(
+                "Invalid column index {} in projection",
+                i
+            )));
+        }
+    }
+    Ok(Arc::new(Schema::new(fields)))
+}
+
 /// convert a Parquet INT96 to an Arrow timestamp in nanoseconds
 fn convert_int96_timestamp(v: &[u32]) -> i64 {
     const JULIAN_DAY_OF_EPOCH: i64 = 2_440_588;