add iso strptime patterns (#3265)

pola-rs · Apr 30, 2022 · aabc5dc · aabc5dc
1 parent c5b1a7a
commit aabc5dc
Show file tree

Hide file tree

Showing 2 changed files with 40 additions and 0 deletions.
diff --git a/polars/polars-time/src/chunkedarray/utf8/patterns.rs b/polars/polars-time/src/chunkedarray/utf8/patterns.rs
@@ -21,11 +21,17 @@ pub(super) static DATE_Y_M_D: &[&str] = &[
 /// NOTE: don't use single letter dates like %F
 /// polars parsers does not support them, so it will be slower
 pub(super) static DATETIME_D_M_Y: &[&str] = &[
+    // --
+    // supported by polars' parser
+    // ---
     // 31/12/21 12:54:98
     "%d/%m/%y %H:%M:%S",
     // 31-12-2021 24:58:01
     "%d-%m-%Y %H:%M:%S",
     // 31-04-2021T02:45:55.555000000
+    // milliseconds
+    "%d-%m-%YT%H:%M:%S.%3f",
+    "%d-%m-%yT%H:%M:%S.%3f",
     // microseconds
     "%d-%m-%YT%H:%M:%S.%6f",
     // 31-04-21T02:45:55.555000000
@@ -67,9 +73,17 @@ pub(super) static DATETIME_Y_M_D: &[&str] = &[
     "%Y-%m-%dT%H:%M:%S.%6f",
     // nanoseconds
     "%Y-%m-%dT%H:%M:%S.%9f",
+    "%Y-%m-%dT%H:%M:%S.%3f",
     // no times
     "%Y-%m-%d",
     "%Y/%m/%d",
+    // --
+    // not supported by polars' parser
+    // ---
+    "%+",
+    // we cannot know this one, because polars needs to know
+    // the length of the parsed fmt
+    "%FT%H:%M:%S%.f",
 ];
 
 #[derive(Eq, Hash, PartialEq, Clone, Copy, Debug)]

diff --git a/py-polars/tests/test_datelike.py b/py-polars/tests/test_datelike.py
@@ -847,3 +847,29 @@ def test_from_time_arrow() -> None:
         time(0, 0, 20),
         time(0, 0, 30),
     ]
+
+
+def test_datetime_strptime_patterns() -> None:
+    # note that all should be year first
+    df = pl.Series(
+        "date",
+        [
+            "09-05-2019" "2018-09-05",
+            "2018-09-05T04:05:01",
+            "2018-09-05T04:24:01.9",
+            "2018-09-05T04:24:02.11",
+            "2018-09-05T14:24:02.123",
+            "2018-09-05T14:24:02.123Z",
+            "2019-04-18T02:45:55.555000000",
+            "2019-04-18T22:45:55.555123",
+        ],
+    ).to_frame()
+    s = df.with_columns(
+        [
+            pl.col("date")
+            .str.strptime(pl.Datetime, fmt=None, strict=False)
+            .alias("parsed"),
+        ]
+    )["parsed"]
+    assert s.null_count() == 1
+    assert s[0] is None