format empty df (#3719)

polars/polars-arrow/Cargo.toml

@@ -9,9 +9,9 @@ description = "Arrow interfaces for Polars DataFrame library"
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
 
 [dependencies]
-# arrow = { package = "arrow2", git = "https://github.com/jorgecarleitao/arrow2", rev = "39db6fb7514364bfea08d594793b23e1ed5a7def", features = ["compute_concatenate"], default-features = false }
+arrow = { package = "arrow2", git = "https://github.com/jorgecarleitao/arrow2", rev = "d4873fcb9b201d591049055c0e554dbdd2c45ad3", features = ["compute_concatenate"], default-features = false }
 # arrow = { package = "arrow2", path = "../../../arrow2", features = ["compute_concatenate"], default-features = false }
-arrow = { package = "arrow2", git = "https://github.com/ritchie46/arrow2", branch = "arity_assign", features = ["compute_concatenate"], default-features = false }
+# arrow = { package = "arrow2", git = "https://github.com/ritchie46/arrow2", branch = "arity_assign", features = ["compute_concatenate"], default-features = false }
 # arrow = { package = "arrow2", version = "0.12", default-features = false, features = ["compute_concatenate"] }
 hashbrown = "0.12"
 num = "^0.4"

polars/polars-core/Cargo.toml

@@ -171,11 +171,11 @@ thiserror = "^1.0"
 
 [dependencies.arrow]
 package = "arrow2"
-# git = "https://github.com/jorgecarleitao/arrow2"
-git = "https://github.com/ritchie46/arrow2"
-# rev = "39db6fb7514364bfea08d594793b23e1ed5a7def"
+git = "https://github.com/jorgecarleitao/arrow2"
+# git = "https://github.com/ritchie46/arrow2"
+rev = "d4873fcb9b201d591049055c0e554dbdd2c45ad3"
 # path = "../../../arrow2"
-branch = "arity_assign"
+# branch = "arity_assign"
 # version = "0.12"
 default-features = false
 features = [

polars/polars-core/src/functions.rs

@@ -132,6 +132,10 @@ pub fn concat_str(s: &[Series], delimiter: &str) -> Result<Utf8Chunked> {
             "expected multiple series in concat_str function".into(),
         ));
     }
+    if s[0].is_empty() {
+        return Ok(Utf8Chunked::full_null(s[0].name(), 0));
+    }
+
     let len = s.iter().map(|s| s.len()).max().unwrap();
 
     let cas = s

polars/polars-io/Cargo.toml

@@ -35,8 +35,8 @@ private = ["polars-time/private"]
 [dependencies]
 ahash = "0.7"
 anyhow = "1.0"
-# arrow = { package = "arrow2", git = "https://github.com/jorgecarleitao/arrow2", rev = "39db6fb7514364bfea08d594793b23e1ed5a7def", default-features = false }
-arrow = { package = "arrow2", git = "https://github.com/ritchie46/arrow2", branch = "arity_assign", default-features = false }
+arrow = { package = "arrow2", git = "https://github.com/jorgecarleitao/arrow2", rev = "d4873fcb9b201d591049055c0e554dbdd2c45ad3", default-features = false }
+# arrow = { package = "arrow2", git = "https://github.com/ritchie46/arrow2", branch = "arity_assign", default-features = false }
 # arrow = { package = "arrow2", version = "0.12", default-features = false }
 # arrow = { package = "arrow2", path = "../../../arrow2", default-features = false }
 csv-core = { version = "0.1.10", optional = true }

py-polars/tests/test_strings.py

@@ -85,3 +85,18 @@ def test_ljust_and_rjust() -> None:
         "ljust": ["foo       ", "longer_foo", "longest_fooooooo", "hi        "],
         "ljust_len": [10, 10, 16, 10],
     }
+
+
+def test_format_empty_df() -> None:
+    df = pl.DataFrame(
+        [
+            pl.Series("val1", [], dtype=pl.Categorical),
+            pl.Series("val2", [], dtype=pl.Categorical),
+        ]
+    ).select(
+        [
+            pl.format("{}:{}", pl.col("val1"), pl.col("val2")).alias("cat"),
+        ]
+    )
+    assert df.shape == (0, 1)
+    assert df.dtypes == [pl.Utf8]