-
Notifications
You must be signed in to change notification settings - Fork 1.9k
perf: optimize bit_length for string arrays #19598
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Changes from all commits
File filter
Filter by extension
Conversations
Jump to
Diff view
Diff view
There are no files selected for viewing
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -28,6 +28,11 @@ use datafusion_expr::{ | |
| TypeSignatureClass, Volatility, | ||
| }; | ||
| use datafusion_macros::user_doc; | ||
| use arrow::array::{ | ||
| Array, StringArray, LargeStringArray, Int32Builder, | ||
| }; | ||
| use std::sync::Arc; | ||
|
|
||
|
|
||
| #[user_doc( | ||
| doc_section(label = "String Functions"), | ||
|
|
@@ -90,17 +95,44 @@ impl ScalarUDFImpl for BitLengthFunc { | |
| let [array] = take_function_args(self.name(), &args.args)?; | ||
|
|
||
| match array { | ||
| ColumnarValue::Array(v) => Ok(ColumnarValue::Array(bit_length(v.as_ref())?)), | ||
| ColumnarValue::Array(v) => { | ||
| if let Some(arr) = v.as_any().downcast_ref::<StringArray>() { | ||
| let mut builder = Int32Builder::with_capacity(arr.len()); | ||
| for i in 0..arr.len() { | ||
| if arr.is_null(i) { | ||
| builder.append_null(); | ||
| } else { | ||
| let byte_len = arr.value(i).as_bytes().len(); | ||
|
Member
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Is |
||
| builder.append_value((byte_len * 8) as i32); | ||
|
Comment on lines
+105
to
+106
|
||
| } | ||
| } | ||
| Ok(ColumnarValue::Array(Arc::new(builder.finish()))) | ||
| } else if let Some(arr) = v.as_any().downcast_ref::<LargeStringArray>() { | ||
| let mut builder = Int32Builder::with_capacity(arr.len()); | ||
| for i in 0..arr.len() { | ||
| if arr.is_null(i) { | ||
| builder.append_null(); | ||
| } else { | ||
| let byte_len = arr.value(i).as_bytes().len(); | ||
| builder.append_value((byte_len * 8) as i32); | ||
| } | ||
| } | ||
| Ok(ColumnarValue::Array(Arc::new(builder.finish()))) | ||
|
Comment on lines
+110
to
+120
|
||
| } else { | ||
| // fallback for Utf8View, Dictionary, Binary, etc. | ||
| Ok(ColumnarValue::Array(bit_length(v.as_ref())?)) | ||
| } | ||
| } | ||
| ColumnarValue::Scalar(v) => match v { | ||
| ScalarValue::Utf8(v) => Ok(ColumnarValue::Scalar(ScalarValue::Int32( | ||
| v.as_ref().map(|x| (x.len() * 8) as i32), | ||
| ))), | ||
| ScalarValue::LargeUtf8(v) => Ok(ColumnarValue::Scalar( | ||
| ScalarValue::Int64(v.as_ref().map(|x| (x.len() * 8) as i64)), | ||
| )), | ||
| ScalarValue::Utf8View(v) => Ok(ColumnarValue::Scalar( | ||
| ScalarValue::Int32(v.as_ref().map(|x| (x.len() * 8) as i32)), | ||
| )), | ||
| ScalarValue::LargeUtf8(v) => Ok(ColumnarValue::Scalar(ScalarValue::Int64( | ||
| v.as_ref().map(|x| (x.len() * 8) as i64), | ||
| ))), | ||
| ScalarValue::Utf8View(v) => Ok(ColumnarValue::Scalar(ScalarValue::Int32( | ||
| v.as_ref().map(|x| (x.len() * 8) as i32), | ||
| ))), | ||
| _ => unreachable!("bit length"), | ||
| }, | ||
| } | ||
|
|
||
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.