(arrow-datafusion) branch main updated: Optimize to_timestamp (with format) (#9090) (#9833)

[alamb]

This is an automated email from the ASF dual-hosted git repository.

alamb pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/arrow-datafusion.git


The following commit(s) were added to refs/heads/main by this push:
     new 666f7a5221 Optimize to_timestamp (with format) (#9090) (#9833)
666f7a5221 is described below

commit 666f7a5221ac9b4d5232cef7b8008ca71d2c1be9
Author: Vojtěch Toman <vojtech.to...@gmail.com>
AuthorDate: Thu Mar 28 17:57:16 2024 +0100

    Optimize to_timestamp (with format) (#9090) (#9833)
    
    Eliminate duplicate parsing of the input and format strings in some cases
    
    Co-authored-by: Vojtech Toman <vojtech.to...@graphaware.com>
---
 datafusion/functions/src/datetime/common.rs | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/datafusion/functions/src/datetime/common.rs 
b/datafusion/functions/src/datetime/common.rs
index 007ffd35ca..f0689ffd64 100644
--- a/datafusion/functions/src/datetime/common.rs
+++ b/datafusion/functions/src/datetime/common.rs
@@ -22,8 +22,9 @@ use arrow::array::{
 };
 use arrow::compute::kernels::cast_utils::string_to_timestamp_nanos;
 use arrow::datatypes::DataType;
+use chrono::format::{parse, Parsed, StrftimeItems};
 use chrono::LocalResult::Single;
-use chrono::{DateTime, NaiveDateTime, TimeZone, Utc};
+use chrono::{DateTime, TimeZone, Utc};
 use itertools::Either;
 
 use datafusion_common::cast::as_generic_string_array;
@@ -84,12 +85,15 @@ pub(crate) fn string_to_datetime_formatted<T: TimeZone>(
         ))
     };
 
+    let mut parsed = Parsed::new();
+    parse(&mut parsed, s, StrftimeItems::new(format)).map_err(|e| 
err(&e.to_string()))?;
+
     // attempt to parse the string assuming it has a timezone
-    let dt = DateTime::parse_from_str(s, format);
+    let dt = parsed.to_datetime();
 
     if let Err(e) = &dt {
         // no timezone or other failure, try without a timezone
-        let ndt = NaiveDateTime::parse_from_str(s, format);
+        let ndt = parsed.to_naive_datetime_with_offset(0);
         if let Err(e) = &ndt {
             return Err(err(&e.to_string()));
         }