(arrow-rs) branch master updated: Extend string parsing support for Date32 to encompass the timestamp format (#5282)

[tustvold]

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

tustvold pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/arrow-rs.git


The following commit(s) were added to refs/heads/master by this push:
     new 72d8a78317 Extend string parsing support for Date32 to encompass the 
timestamp format (#5282)
72d8a78317 is described below

commit 72d8a783176219f0864022daba70e84ceab7e221
Author: Marko Grujic <mark...@gmail.com>
AuthorDate: Thu Jan 11 12:00:12 2024 +0100

    Extend string parsing support for Date32 to encompass the timestamp format 
(#5282)
---
 arrow-cast/src/cast.rs  | 12 +++++++-----
 arrow-cast/src/parse.rs | 17 ++++++++++++++---
 2 files changed, 21 insertions(+), 8 deletions(-)

diff --git a/arrow-cast/src/cast.rs b/arrow-cast/src/cast.rs
index 92b9071a67..bd35096e06 100644
--- a/arrow-cast/src/cast.rs
+++ b/arrow-cast/src/cast.rs
@@ -7482,9 +7482,9 @@ mod tests {
 
         let a = StringArray::from(vec![
             "2000-01-01",          // valid date with leading 0s
+            "2000-01-01T12:00:00", // valid datetime, will throw away the time 
part
             "2000-2-2",            // valid date without leading 0s
             "2000-00-00",          // invalid month and day
-            "2000-01-01T12:00:00", // date + time is invalid
             "2000",                // just a year is invalid
         ]);
         let array = Arc::new(a) as ArrayRef;
@@ -7500,17 +7500,19 @@ mod tests {
         assert!(c.is_valid(0)); // "2000-01-01"
         assert_eq!(date_value, c.value(0));
 
+        assert!(c.is_valid(1)); // "2000-01-01T12:00:00"
+        assert_eq!(date_value, c.value(1));
+
         let date_value = since(
             NaiveDate::from_ymd_opt(2000, 2, 2).unwrap(),
             from_ymd(1970, 1, 1).unwrap(),
         )
         .num_days() as i32;
-        assert!(c.is_valid(1)); // "2000-2-2"
-        assert_eq!(date_value, c.value(1));
+        assert!(c.is_valid(2)); // "2000-2-2"
+        assert_eq!(date_value, c.value(2));
 
         // test invalid inputs
-        assert!(!c.is_valid(2)); // "2000-00-00"
-        assert!(!c.is_valid(3)); // "2000-01-01T12:00:00"
+        assert!(!c.is_valid(3)); // "2000-00-00"
         assert!(!c.is_valid(4)); // "2000"
     }
 
diff --git a/arrow-cast/src/parse.rs b/arrow-cast/src/parse.rs
index 3d2e47ed95..50e9fda672 100644
--- a/arrow-cast/src/parse.rs
+++ b/arrow-cast/src/parse.rs
@@ -546,8 +546,11 @@ const ERR_NANOSECONDS_NOT_SUPPORTED: &str = "The dates 
that can be represented a
 
 fn parse_date(string: &str) -> Option<NaiveDate> {
     if string.len() > 10 {
-        return None;
-    }
+        // Try to parse as datetime and return just the date part
+        return string_to_datetime(&Utc, string)
+            .map(|dt| dt.date_naive())
+            .ok();
+    };
     let mut digits = [0; 10];
     let mut mask = 0;
 
@@ -1488,10 +1491,13 @@ mod tests {
             "2020-9-08",
             "2020-12-1",
             "1690-2-5",
+            "2020-09-08 01:02:03",
         ];
         for case in cases {
             let v = 
date32_to_datetime(Date32Type::parse(case).unwrap()).unwrap();
-            let expected: NaiveDate = case.parse().unwrap();
+            let expected = NaiveDate::parse_from_str(case, "%Y-%m-%d")
+                .or(NaiveDate::parse_from_str(case, "%Y-%m-%d %H:%M:%S"))
+                .unwrap();
             assert_eq!(v.date(), expected);
         }
 
@@ -1503,6 +1509,11 @@ mod tests {
             "2020-09-08-03",
             "2020--04-03",
             "2020--",
+            "2020-09-08 01",
+            "2020-09-08 01:02",
+            "2020-09-08 01-02-03",
+            "2020-9-8 01:02:03",
+            "2020-09-08 1:2:3",
         ];
         for case in err_cases {
             assert_eq!(Date32Type::parse(case), None);