This is an automated email from the ASF dual-hosted git repository.
alamb pushed a commit to branch string-view2
in repository https://gitbox.apache.org/repos/asf/datafusion.git
The following commit(s) were added to refs/heads/string-view2 by this push:
new bb780b3cb0 Add support for Utf8View for date/temporal codepaths
(#11518)
bb780b3cb0 is described below
commit bb780b3cb00842178cbc1ac7fb183cf331cf6aa8
Author: Andrew Duffy <[email protected]>
AuthorDate: Mon Jul 22 13:42:35 2024 -0400
Add support for Utf8View for date/temporal codepaths (#11518)
* Add StringView support for date_part and make_date funcs
* run cargo update in datafusion-cli
* cargo fmt
---------
Co-authored-by: Andrew Lamb <[email protected]>
---
Cargo.toml | 24 ++--
datafusion-cli/Cargo.lock | 122 +++++++++++----------
datafusion-cli/Cargo.toml | 24 ++--
datafusion/expr/src/type_coercion/binary.rs | 26 +++--
datafusion/functions/src/datetime/date_part.rs | 30 ++++-
datafusion/functions/src/datetime/date_trunc.rs | 25 ++++-
datafusion/functions/src/datetime/make_date.rs | 4 +-
datafusion/functions/src/utils.rs | 8 +-
.../src/engines/datafusion_engine/normalize.rs | 5 +
datafusion/sqllogictest/test_files/string_view.slt | 21 ++++
10 files changed, 191 insertions(+), 98 deletions(-)
diff --git a/Cargo.toml b/Cargo.toml
index b1f07aa531..b9bc3c3fc0 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -157,15 +157,15 @@ unused_imports = "deny"
## Temporary arrow-rs patch until 52.2.0 is released
[patch.crates-io]
-arrow = { git = "https://github.com/apache/arrow-rs.git";, rev =
"66390ff8ec15bb6ed585f353f67a19574da4375a" }
-arrow-array = { git = "https://github.com/apache/arrow-rs.git";, rev =
"66390ff8ec15bb6ed585f353f67a19574da4375a" }
-arrow-buffer = { git = "https://github.com/apache/arrow-rs.git";, rev =
"66390ff8ec15bb6ed585f353f67a19574da4375a" }
-arrow-cast = { git = "https://github.com/apache/arrow-rs.git";, rev =
"66390ff8ec15bb6ed585f353f67a19574da4375a" }
-arrow-data = { git = "https://github.com/apache/arrow-rs.git";, rev =
"66390ff8ec15bb6ed585f353f67a19574da4375a" }
-arrow-ipc = { git = "https://github.com/apache/arrow-rs.git";, rev =
"66390ff8ec15bb6ed585f353f67a19574da4375a" }
-arrow-schema = { git = "https://github.com/apache/arrow-rs.git";, rev =
"66390ff8ec15bb6ed585f353f67a19574da4375a" }
-arrow-select = { git = "https://github.com/apache/arrow-rs.git";, rev =
"66390ff8ec15bb6ed585f353f67a19574da4375a" }
-arrow-string = { git = "https://github.com/apache/arrow-rs.git";, rev =
"66390ff8ec15bb6ed585f353f67a19574da4375a" }
-arrow-ord = { git = "https://github.com/apache/arrow-rs.git";, rev =
"66390ff8ec15bb6ed585f353f67a19574da4375a" }
-arrow-flight = { git = "https://github.com/apache/arrow-rs.git";, rev =
"66390ff8ec15bb6ed585f353f67a19574da4375a" }
-parquet = { git = "https://github.com/apache/arrow-rs.git";, rev =
"66390ff8ec15bb6ed585f353f67a19574da4375a" }
+arrow = { git = "https://github.com/apache/arrow-rs.git";, rev =
"8a5be1330e30e6dd7760dba910737550d760e612" }
+arrow-array = { git = "https://github.com/apache/arrow-rs.git";, rev =
"8a5be1330e30e6dd7760dba910737550d760e612" }
+arrow-buffer = { git = "https://github.com/apache/arrow-rs.git";, rev =
"8a5be1330e30e6dd7760dba910737550d760e612" }
+arrow-cast = { git = "https://github.com/apache/arrow-rs.git";, rev =
"8a5be1330e30e6dd7760dba910737550d760e612" }
+arrow-data = { git = "https://github.com/apache/arrow-rs.git";, rev =
"8a5be1330e30e6dd7760dba910737550d760e612" }
+arrow-ipc = { git = "https://github.com/apache/arrow-rs.git";, rev =
"8a5be1330e30e6dd7760dba910737550d760e612" }
+arrow-schema = { git = "https://github.com/apache/arrow-rs.git";, rev =
"8a5be1330e30e6dd7760dba910737550d760e612" }
+arrow-select = { git = "https://github.com/apache/arrow-rs.git";, rev =
"8a5be1330e30e6dd7760dba910737550d760e612" }
+arrow-string = { git = "https://github.com/apache/arrow-rs.git";, rev =
"8a5be1330e30e6dd7760dba910737550d760e612" }
+arrow-ord = { git = "https://github.com/apache/arrow-rs.git";, rev =
"8a5be1330e30e6dd7760dba910737550d760e612" }
+arrow-flight = { git = "https://github.com/apache/arrow-rs.git";, rev =
"8a5be1330e30e6dd7760dba910737550d760e612" }
+parquet = { git = "https://github.com/apache/arrow-rs.git";, rev =
"8a5be1330e30e6dd7760dba910737550d760e612" }
diff --git a/datafusion-cli/Cargo.lock b/datafusion-cli/Cargo.lock
index af5d358b50..3c3d3a40a2 100644
--- a/datafusion-cli/Cargo.lock
+++ b/datafusion-cli/Cargo.lock
@@ -118,9 +118,9 @@ dependencies = [
[[package]]
name = "arrayref"
-version = "0.3.7"
+version = "0.3.8"
source = "registry+https://github.com/rust-lang/crates.io-index";
-checksum = "6b4930d2cb77ce62f89ee5d5289b4ac049559b1c45539271f5ed4fdc7db34545"
+checksum = "9d151e35f61089500b617991b791fc8bfd237ae50cd5950803758a179b41e67a"
[[package]]
name = "arrayvec"
@@ -131,7 +131,7 @@ checksum =
"96d30a06541fbafbc7f82ed10c06164cfbd2c401138f6addd8404629c4b16711"
[[package]]
name = "arrow"
version = "52.1.0"
-source =
"git+https://github.com/apache/arrow-rs.git?rev=66390ff8ec15bb6ed585f353f67a19574da4375a#66390ff8ec15bb6ed585f353f67a19574da4375a";
+source =
"git+https://github.com/apache/arrow-rs.git?rev=8a5be1330e30e6dd7760dba910737550d760e612#8a5be1330e30e6dd7760dba910737550d760e612";
dependencies = [
"arrow-arith",
"arrow-array",
@@ -151,7 +151,7 @@ dependencies = [
[[package]]
name = "arrow-arith"
version = "52.1.0"
-source =
"git+https://github.com/apache/arrow-rs.git?rev=66390ff8ec15bb6ed585f353f67a19574da4375a#66390ff8ec15bb6ed585f353f67a19574da4375a";
+source =
"git+https://github.com/apache/arrow-rs.git?rev=8a5be1330e30e6dd7760dba910737550d760e612#8a5be1330e30e6dd7760dba910737550d760e612";
dependencies = [
"arrow-array",
"arrow-buffer",
@@ -165,7 +165,7 @@ dependencies = [
[[package]]
name = "arrow-array"
version = "52.1.0"
-source =
"git+https://github.com/apache/arrow-rs.git?rev=66390ff8ec15bb6ed585f353f67a19574da4375a#66390ff8ec15bb6ed585f353f67a19574da4375a";
+source =
"git+https://github.com/apache/arrow-rs.git?rev=8a5be1330e30e6dd7760dba910737550d760e612#8a5be1330e30e6dd7760dba910737550d760e612";
dependencies = [
"ahash",
"arrow-buffer",
@@ -181,7 +181,7 @@ dependencies = [
[[package]]
name = "arrow-buffer"
version = "52.1.0"
-source =
"git+https://github.com/apache/arrow-rs.git?rev=66390ff8ec15bb6ed585f353f67a19574da4375a#66390ff8ec15bb6ed585f353f67a19574da4375a";
+source =
"git+https://github.com/apache/arrow-rs.git?rev=8a5be1330e30e6dd7760dba910737550d760e612#8a5be1330e30e6dd7760dba910737550d760e612";
dependencies = [
"bytes",
"half",
@@ -191,7 +191,7 @@ dependencies = [
[[package]]
name = "arrow-cast"
version = "52.1.0"
-source =
"git+https://github.com/apache/arrow-rs.git?rev=66390ff8ec15bb6ed585f353f67a19574da4375a#66390ff8ec15bb6ed585f353f67a19574da4375a";
+source =
"git+https://github.com/apache/arrow-rs.git?rev=8a5be1330e30e6dd7760dba910737550d760e612#8a5be1330e30e6dd7760dba910737550d760e612";
dependencies = [
"arrow-array",
"arrow-buffer",
@@ -211,7 +211,7 @@ dependencies = [
[[package]]
name = "arrow-csv"
version = "52.1.0"
-source =
"git+https://github.com/apache/arrow-rs.git?rev=66390ff8ec15bb6ed585f353f67a19574da4375a#66390ff8ec15bb6ed585f353f67a19574da4375a";
+source =
"git+https://github.com/apache/arrow-rs.git?rev=8a5be1330e30e6dd7760dba910737550d760e612#8a5be1330e30e6dd7760dba910737550d760e612";
dependencies = [
"arrow-array",
"arrow-buffer",
@@ -229,7 +229,7 @@ dependencies = [
[[package]]
name = "arrow-data"
version = "52.1.0"
-source =
"git+https://github.com/apache/arrow-rs.git?rev=66390ff8ec15bb6ed585f353f67a19574da4375a#66390ff8ec15bb6ed585f353f67a19574da4375a";
+source =
"git+https://github.com/apache/arrow-rs.git?rev=8a5be1330e30e6dd7760dba910737550d760e612#8a5be1330e30e6dd7760dba910737550d760e612";
dependencies = [
"arrow-buffer",
"arrow-schema",
@@ -240,7 +240,7 @@ dependencies = [
[[package]]
name = "arrow-ipc"
version = "52.1.0"
-source =
"git+https://github.com/apache/arrow-rs.git?rev=66390ff8ec15bb6ed585f353f67a19574da4375a#66390ff8ec15bb6ed585f353f67a19574da4375a";
+source =
"git+https://github.com/apache/arrow-rs.git?rev=8a5be1330e30e6dd7760dba910737550d760e612#8a5be1330e30e6dd7760dba910737550d760e612";
dependencies = [
"arrow-array",
"arrow-buffer",
@@ -254,7 +254,7 @@ dependencies = [
[[package]]
name = "arrow-json"
version = "52.1.0"
-source =
"git+https://github.com/apache/arrow-rs.git?rev=66390ff8ec15bb6ed585f353f67a19574da4375a#66390ff8ec15bb6ed585f353f67a19574da4375a";
+source =
"git+https://github.com/apache/arrow-rs.git?rev=8a5be1330e30e6dd7760dba910737550d760e612#8a5be1330e30e6dd7760dba910737550d760e612";
dependencies = [
"arrow-array",
"arrow-buffer",
@@ -273,7 +273,7 @@ dependencies = [
[[package]]
name = "arrow-ord"
version = "52.1.0"
-source =
"git+https://github.com/apache/arrow-rs.git?rev=66390ff8ec15bb6ed585f353f67a19574da4375a#66390ff8ec15bb6ed585f353f67a19574da4375a";
+source =
"git+https://github.com/apache/arrow-rs.git?rev=8a5be1330e30e6dd7760dba910737550d760e612#8a5be1330e30e6dd7760dba910737550d760e612";
dependencies = [
"arrow-array",
"arrow-buffer",
@@ -287,7 +287,7 @@ dependencies = [
[[package]]
name = "arrow-row"
version = "52.1.0"
-source =
"git+https://github.com/apache/arrow-rs.git?rev=66390ff8ec15bb6ed585f353f67a19574da4375a#66390ff8ec15bb6ed585f353f67a19574da4375a";
+source =
"git+https://github.com/apache/arrow-rs.git?rev=8a5be1330e30e6dd7760dba910737550d760e612#8a5be1330e30e6dd7760dba910737550d760e612";
dependencies = [
"ahash",
"arrow-array",
@@ -300,12 +300,12 @@ dependencies = [
[[package]]
name = "arrow-schema"
version = "52.1.0"
-source =
"git+https://github.com/apache/arrow-rs.git?rev=66390ff8ec15bb6ed585f353f67a19574da4375a#66390ff8ec15bb6ed585f353f67a19574da4375a";
+source =
"git+https://github.com/apache/arrow-rs.git?rev=8a5be1330e30e6dd7760dba910737550d760e612#8a5be1330e30e6dd7760dba910737550d760e612";
[[package]]
name = "arrow-select"
version = "52.1.0"
-source =
"git+https://github.com/apache/arrow-rs.git?rev=66390ff8ec15bb6ed585f353f67a19574da4375a#66390ff8ec15bb6ed585f353f67a19574da4375a";
+source =
"git+https://github.com/apache/arrow-rs.git?rev=8a5be1330e30e6dd7760dba910737550d760e612#8a5be1330e30e6dd7760dba910737550d760e612";
dependencies = [
"ahash",
"arrow-array",
@@ -318,7 +318,7 @@ dependencies = [
[[package]]
name = "arrow-string"
version = "52.1.0"
-source =
"git+https://github.com/apache/arrow-rs.git?rev=66390ff8ec15bb6ed585f353f67a19574da4375a#66390ff8ec15bb6ed585f353f67a19574da4375a";
+source =
"git+https://github.com/apache/arrow-rs.git?rev=8a5be1330e30e6dd7760dba910737550d760e612#8a5be1330e30e6dd7760dba910737550d760e612";
dependencies = [
"arrow-array",
"arrow-buffer",
@@ -348,9 +348,9 @@ dependencies = [
[[package]]
name = "async-compression"
-version = "0.4.11"
+version = "0.4.12"
source = "registry+https://github.com/rust-lang/crates.io-index";
-checksum = "cd066d0b4ef8ecb03a55319dc13aa6910616d0f44008a045bb1835af830abff5"
+checksum = "fec134f64e2bc57411226dfc4e52dec859ddfc7e711fc5e07b612584f000e4aa"
dependencies = [
"bzip2",
"flate2",
@@ -372,7 +372,7 @@ checksum =
"6e0c28dcc82d7c8ead5cb13beb15405b57b8546e93215673ff8ca0349a028107"
dependencies = [
"proc-macro2",
"quote",
- "syn 2.0.71",
+ "syn 2.0.72",
]
[[package]]
@@ -860,9 +860,9 @@ dependencies = [
[[package]]
name = "cc"
-version = "1.1.5"
+version = "1.1.6"
source = "registry+https://github.com/rust-lang/crates.io-index";
-checksum = "324c74f2155653c90b04f25b2a47a8a631360cb908f92a772695f430c7e31052"
+checksum = "2aba8f4e9906c7ce3c73463f62a7f0c65183ada1a2d47e397cc8810827f9694f"
dependencies = [
"jobserver",
"libc",
@@ -1089,7 +1089,7 @@ source =
"registry+https://github.com/rust-lang/crates.io-index";
checksum = "edb49164822f3ee45b17acd4a208cfc1251410cf0cad9a833234c9890774dd9f"
dependencies = [
"quote",
- "syn 2.0.71",
+ "syn 2.0.72",
]
[[package]]
@@ -1146,7 +1146,7 @@ dependencies = [
"half",
"hashbrown 0.14.5",
"indexmap 2.2.6",
- "itertools",
+ "itertools 0.12.1",
"log",
"num-traits",
"num_cpus",
@@ -1272,7 +1272,7 @@ dependencies = [
"datafusion-expr",
"hashbrown 0.14.5",
"hex",
- "itertools",
+ "itertools 0.12.1",
"log",
"md-5",
"rand",
@@ -1312,7 +1312,7 @@ dependencies = [
"datafusion-expr",
"datafusion-functions",
"datafusion-functions-aggregate",
- "itertools",
+ "itertools 0.12.1",
"log",
"paste",
]
@@ -1329,7 +1329,7 @@ dependencies = [
"datafusion-physical-expr",
"hashbrown 0.14.5",
"indexmap 2.2.6",
- "itertools",
+ "itertools 0.12.1",
"log",
"paste",
"regex-syntax",
@@ -1356,7 +1356,7 @@ dependencies = [
"hashbrown 0.14.5",
"hex",
"indexmap 2.2.6",
- "itertools",
+ "itertools 0.12.1",
"log",
"paste",
"petgraph",
@@ -1398,7 +1398,7 @@ dependencies = [
"half",
"hashbrown 0.14.5",
"indexmap 2.2.6",
- "itertools",
+ "itertools 0.12.1",
"log",
"once_cell",
"parking_lot",
@@ -1678,7 +1678,7 @@ checksum =
"87750cf4b7a4c0625b1529e4c543c2182106e4dedc60a2a6455e00d212c489ac"
dependencies = [
"proc-macro2",
"quote",
- "syn 2.0.71",
+ "syn 2.0.72",
]
[[package]]
@@ -2114,6 +2114,15 @@ dependencies = [
"either",
]
+[[package]]
+name = "itertools"
+version = "0.13.0"
+source = "registry+https://github.com/rust-lang/crates.io-index";
+checksum = "413ee7dfc52ee1a4949ceeb7dbc8a33f2d6c088194d9f922fb8318faf1f01186"
+dependencies = [
+ "either",
+]
+
[[package]]
name = "itoa"
version = "1.0.11"
@@ -2484,9 +2493,9 @@ dependencies = [
[[package]]
name = "object_store"
-version = "0.10.1"
+version = "0.10.2"
source = "registry+https://github.com/rust-lang/crates.io-index";
-checksum = "fbebfd32c213ba1907fa7a9c9138015a8de2b43e30c5aa45b18f7deb46786ad6"
+checksum = "e6da452820c715ce78221e8202ccc599b4a52f3e1eb3eedb487b680c81a8e3f3"
dependencies = [
"async-trait",
"base64 0.22.1",
@@ -2495,7 +2504,7 @@ dependencies = [
"futures",
"humantime",
"hyper 1.4.1",
- "itertools",
+ "itertools 0.13.0",
"md-5",
"parking_lot",
"percent-encoding",
@@ -2572,7 +2581,7 @@ dependencies = [
[[package]]
name = "parquet"
version = "52.1.0"
-source =
"git+https://github.com/apache/arrow-rs.git?rev=66390ff8ec15bb6ed585f353f67a19574da4375a#66390ff8ec15bb6ed585f353f67a19574da4375a";
+source =
"git+https://github.com/apache/arrow-rs.git?rev=8a5be1330e30e6dd7760dba910737550d760e612#8a5be1330e30e6dd7760dba910737550d760e612";
dependencies = [
"ahash",
"arrow-array",
@@ -2690,7 +2699,7 @@ checksum =
"2f38a4412a78282e09a2cf38d195ea5420d15ba0602cb375210efbc877243965"
dependencies = [
"proc-macro2",
"quote",
- "syn 2.0.71",
+ "syn 2.0.72",
]
[[package]]
@@ -2794,9 +2803,9 @@ checksum =
"658fa1faf7a4cc5f057c9ee5ef560f717ad9d8dc66d975267f709624d6e1ab88"
[[package]]
name = "quick-xml"
-version = "0.31.0"
+version = "0.36.0"
source = "registry+https://github.com/rust-lang/crates.io-index";
-checksum = "1004a344b30a54e2ee58d66a71b32d2db2feb0a31f9a2d302bf0536f15de2a33"
+checksum = "4091e032efecb09d7b1f711f487b85ab925632a842627e3200fb088382cde32c"
dependencies = [
"memchr",
"serde",
@@ -2838,14 +2847,13 @@ dependencies = [
[[package]]
name = "quinn-udp"
-version = "0.5.2"
+version = "0.5.3"
source = "registry+https://github.com/rust-lang/crates.io-index";
-checksum = "9096629c45860fc7fb143e125eb826b5e721e10be3263160c7d60ca832cf8c46"
+checksum = "25a78e6f726d84fcf960409f509ae354a32648f090c8d32a2ea8b1a1bc3bab14"
dependencies = [
"libc",
"once_cell",
"socket2",
- "tracing",
"windows-sys 0.52.0",
]
@@ -3302,7 +3310,7 @@ checksum =
"e0cd7e117be63d3c3678776753929474f3b04a43a080c744d6b0ae2a8c28e222"
dependencies = [
"proc-macro2",
"quote",
- "syn 2.0.71",
+ "syn 2.0.72",
]
[[package]]
@@ -3437,7 +3445,7 @@ checksum =
"01b2e185515564f15375f593fb966b5718bc624ba77fe49fa4616ad619690554"
dependencies = [
"proc-macro2",
"quote",
- "syn 2.0.71",
+ "syn 2.0.72",
]
[[package]]
@@ -3483,7 +3491,7 @@ dependencies = [
"proc-macro2",
"quote",
"rustversion",
- "syn 2.0.71",
+ "syn 2.0.72",
]
[[package]]
@@ -3496,7 +3504,7 @@ dependencies = [
"proc-macro2",
"quote",
"rustversion",
- "syn 2.0.71",
+ "syn 2.0.72",
]
[[package]]
@@ -3518,9 +3526,9 @@ dependencies = [
[[package]]
name = "syn"
-version = "2.0.71"
+version = "2.0.72"
source = "registry+https://github.com/rust-lang/crates.io-index";
-checksum = "b146dcf730474b4bcd16c311627b31ede9ab149045db4d6088b3becaea046462"
+checksum = "dc4b9b9bf2add8093d3f2c0204471e951b2285580335de42f9d2534f3ae7a8af"
dependencies = [
"proc-macro2",
"quote",
@@ -3568,22 +3576,22 @@ checksum =
"23d434d3f8967a09480fb04132ebe0a3e088c173e6d0ee7897abbdf4eab0f8b9"
[[package]]
name = "thiserror"
-version = "1.0.62"
+version = "1.0.63"
source = "registry+https://github.com/rust-lang/crates.io-index";
-checksum = "f2675633b1499176c2dff06b0856a27976a8f9d436737b4cf4f312d4d91d8bbb"
+checksum = "c0342370b38b6a11b6cc11d6a805569958d54cfa061a29969c3b5ce2ea405724"
dependencies = [
"thiserror-impl",
]
[[package]]
name = "thiserror-impl"
-version = "1.0.62"
+version = "1.0.63"
source = "registry+https://github.com/rust-lang/crates.io-index";
-checksum = "d20468752b09f49e909e55a5d338caa8bedf615594e9d80bc4c565d30faf798c"
+checksum = "a4558b58466b9ad7ca0f102865eccc95938dca1a74a856f2b57b6629050da261"
dependencies = [
"proc-macro2",
"quote",
- "syn 2.0.71",
+ "syn 2.0.72",
]
[[package]]
@@ -3678,7 +3686,7 @@ checksum =
"5f5ae998a069d4b5aba8ee9dad856af7d520c3699e6159b185c2acd48155d39a"
dependencies = [
"proc-macro2",
"quote",
- "syn 2.0.71",
+ "syn 2.0.72",
]
[[package]]
@@ -3775,7 +3783,7 @@ checksum =
"34704c8d6ebcbc939824180af020566b01a7c01f80641264eba0999f6c2b6be7"
dependencies = [
"proc-macro2",
"quote",
- "syn 2.0.71",
+ "syn 2.0.72",
]
[[package]]
@@ -3820,7 +3828,7 @@ checksum =
"f03ca4cb38206e2bef0700092660bb74d696f808514dae47fa1467cbfe26e96e"
dependencies = [
"proc-macro2",
"quote",
- "syn 2.0.71",
+ "syn 2.0.72",
]
[[package]]
@@ -3974,7 +3982,7 @@ dependencies = [
"once_cell",
"proc-macro2",
"quote",
- "syn 2.0.71",
+ "syn 2.0.72",
"wasm-bindgen-shared",
]
@@ -4008,7 +4016,7 @@ checksum =
"e94f17b526d0a461a191c78ea52bbce64071ed5c04c9ffe424dcb38f74171bb7"
dependencies = [
"proc-macro2",
"quote",
- "syn 2.0.71",
+ "syn 2.0.72",
"wasm-bindgen-backend",
"wasm-bindgen-shared",
]
@@ -4273,7 +4281,7 @@ checksum =
"fa4f8080344d4671fb4e831a13ad1e68092748387dfc4f55e356242fae12ce3e"
dependencies = [
"proc-macro2",
"quote",
- "syn 2.0.71",
+ "syn 2.0.72",
]
[[package]]
@@ -4332,4 +4340,4 @@ dependencies = [
[[patch.unused]]
name = "arrow-flight"
version = "52.1.0"
-source =
"git+https://github.com/apache/arrow-rs.git?rev=66390ff8ec15bb6ed585f353f67a19574da4375a#66390ff8ec15bb6ed585f353f67a19574da4375a";
+source =
"git+https://github.com/apache/arrow-rs.git?rev=8a5be1330e30e6dd7760dba910737550d760e612#8a5be1330e30e6dd7760dba910737550d760e612";
diff --git a/datafusion-cli/Cargo.toml b/datafusion-cli/Cargo.toml
index 10bea5f4ce..958941743e 100644
--- a/datafusion-cli/Cargo.toml
+++ b/datafusion-cli/Cargo.toml
@@ -64,15 +64,15 @@ predicates = "3.0"
rstest = "0.17"
[patch.crates-io]
-arrow = { git = "https://github.com/apache/arrow-rs.git";, rev =
"66390ff8ec15bb6ed585f353f67a19574da4375a" }
-arrow-array = { git = "https://github.com/apache/arrow-rs.git";, rev =
"66390ff8ec15bb6ed585f353f67a19574da4375a" }
-arrow-buffer = { git = "https://github.com/apache/arrow-rs.git";, rev =
"66390ff8ec15bb6ed585f353f67a19574da4375a" }
-arrow-cast = { git = "https://github.com/apache/arrow-rs.git";, rev =
"66390ff8ec15bb6ed585f353f67a19574da4375a" }
-arrow-data = { git = "https://github.com/apache/arrow-rs.git";, rev =
"66390ff8ec15bb6ed585f353f67a19574da4375a" }
-arrow-ipc = { git = "https://github.com/apache/arrow-rs.git";, rev =
"66390ff8ec15bb6ed585f353f67a19574da4375a" }
-arrow-schema = { git = "https://github.com/apache/arrow-rs.git";, rev =
"66390ff8ec15bb6ed585f353f67a19574da4375a" }
-arrow-select = { git = "https://github.com/apache/arrow-rs.git";, rev =
"66390ff8ec15bb6ed585f353f67a19574da4375a" }
-arrow-string = { git = "https://github.com/apache/arrow-rs.git";, rev =
"66390ff8ec15bb6ed585f353f67a19574da4375a" }
-arrow-ord = { git = "https://github.com/apache/arrow-rs.git";, rev =
"66390ff8ec15bb6ed585f353f67a19574da4375a" }
-arrow-flight = { git = "https://github.com/apache/arrow-rs.git";, rev =
"66390ff8ec15bb6ed585f353f67a19574da4375a" }
-parquet = { git = "https://github.com/apache/arrow-rs.git";, rev =
"66390ff8ec15bb6ed585f353f67a19574da4375a" }
+arrow = { git = "https://github.com/apache/arrow-rs.git";, rev =
"8a5be1330e30e6dd7760dba910737550d760e612" }
+arrow-array = { git = "https://github.com/apache/arrow-rs.git";, rev =
"8a5be1330e30e6dd7760dba910737550d760e612" }
+arrow-buffer = { git = "https://github.com/apache/arrow-rs.git";, rev =
"8a5be1330e30e6dd7760dba910737550d760e612" }
+arrow-cast = { git = "https://github.com/apache/arrow-rs.git";, rev =
"8a5be1330e30e6dd7760dba910737550d760e612" }
+arrow-data = { git = "https://github.com/apache/arrow-rs.git";, rev =
"8a5be1330e30e6dd7760dba910737550d760e612" }
+arrow-ipc = { git = "https://github.com/apache/arrow-rs.git";, rev =
"8a5be1330e30e6dd7760dba910737550d760e612" }
+arrow-schema = { git = "https://github.com/apache/arrow-rs.git";, rev =
"8a5be1330e30e6dd7760dba910737550d760e612" }
+arrow-select = { git = "https://github.com/apache/arrow-rs.git";, rev =
"8a5be1330e30e6dd7760dba910737550d760e612" }
+arrow-string = { git = "https://github.com/apache/arrow-rs.git";, rev =
"8a5be1330e30e6dd7760dba910737550d760e612" }
+arrow-ord = { git = "https://github.com/apache/arrow-rs.git";, rev =
"8a5be1330e30e6dd7760dba910737550d760e612" }
+arrow-flight = { git = "https://github.com/apache/arrow-rs.git";, rev =
"8a5be1330e30e6dd7760dba910737550d760e612" }
+parquet = { git = "https://github.com/apache/arrow-rs.git";, rev =
"8a5be1330e30e6dd7760dba910737550d760e612" }
diff --git a/datafusion/expr/src/type_coercion/binary.rs
b/datafusion/expr/src/type_coercion/binary.rs
index 70139aaa4a..4e5ed42f98 100644
--- a/datafusion/expr/src/type_coercion/binary.rs
+++ b/datafusion/expr/src/type_coercion/binary.rs
@@ -527,7 +527,7 @@ fn string_numeric_coercion(lhs_type: &DataType, rhs_type:
&DataType) -> Option<D
}
/// Coerce `lhs_type` and `rhs_type` to a common type for the purposes of a
comparison operation
-/// where one is temporal and one is `Utf8`/`LargeUtf8`.
+/// where one is temporal and one is `Utf8View`/`Utf8`/`LargeUtf8`.
///
/// Note this cannot be performed in case of arithmetic as there is
insufficient information
/// to correctly determine the type of argument. Consider
@@ -547,19 +547,21 @@ fn string_temporal_coercion(
fn match_rule(l: &DataType, r: &DataType) -> Option<DataType> {
match (l, r) {
- // Coerce Utf8/LargeUtf8 to Date32/Date64/Time32/Time64/Timestamp
- (Utf8, temporal) | (LargeUtf8, temporal) => match temporal {
- Date32 | Date64 => Some(temporal.clone()),
- Time32(_) | Time64(_) => {
- if is_time_with_valid_unit(temporal.to_owned()) {
- Some(temporal.to_owned())
- } else {
- None
+ // Coerce Utf8View/Utf8/LargeUtf8 to
Date32/Date64/Time32/Time64/Timestamp
+ (Utf8, temporal) | (LargeUtf8, temporal) | (Utf8View, temporal) =>
{
+ match temporal {
+ Date32 | Date64 => Some(temporal.clone()),
+ Time32(_) | Time64(_) => {
+ if is_time_with_valid_unit(temporal.to_owned()) {
+ Some(temporal.to_owned())
+ } else {
+ None
+ }
}
+ Timestamp(_, tz) => Some(Timestamp(TimeUnit::Nanosecond,
tz.clone())),
+ _ => None,
}
- Timestamp(_, tz) => Some(Timestamp(TimeUnit::Nanosecond,
tz.clone())),
- _ => None,
- },
+ }
_ => None,
}
}
diff --git a/datafusion/functions/src/datetime/date_part.rs
b/datafusion/functions/src/datetime/date_part.rs
index e1efb4811e..e24b11aeb7 100644
--- a/datafusion/functions/src/datetime/date_part.rs
+++ b/datafusion/functions/src/datetime/date_part.rs
@@ -21,7 +21,7 @@ use std::sync::Arc;
use arrow::array::{Array, ArrayRef, Float64Array};
use arrow::compute::{binary, cast, date_part, DatePart};
use arrow::datatypes::DataType::{
- Date32, Date64, Float64, Time32, Time64, Timestamp, Utf8,
+ Date32, Date64, Float64, Time32, Time64, Timestamp, Utf8, Utf8View,
};
use arrow::datatypes::TimeUnit::{Microsecond, Millisecond, Nanosecond, Second};
use arrow::datatypes::{DataType, TimeUnit};
@@ -56,31 +56,57 @@ impl DatePartFunc {
signature: Signature::one_of(
vec![
Exact(vec![Utf8, Timestamp(Nanosecond, None)]),
+ Exact(vec![Utf8View, Timestamp(Nanosecond, None)]),
Exact(vec![
Utf8,
Timestamp(Nanosecond, Some(TIMEZONE_WILDCARD.into())),
]),
+ Exact(vec![
+ Utf8View,
+ Timestamp(Nanosecond, Some(TIMEZONE_WILDCARD.into())),
+ ]),
Exact(vec![Utf8, Timestamp(Millisecond, None)]),
+ Exact(vec![Utf8View, Timestamp(Millisecond, None)]),
Exact(vec![
Utf8,
Timestamp(Millisecond, Some(TIMEZONE_WILDCARD.into())),
]),
+ Exact(vec![
+ Utf8View,
+ Timestamp(Millisecond, Some(TIMEZONE_WILDCARD.into())),
+ ]),
Exact(vec![Utf8, Timestamp(Microsecond, None)]),
+ Exact(vec![Utf8View, Timestamp(Microsecond, None)]),
Exact(vec![
Utf8,
Timestamp(Microsecond, Some(TIMEZONE_WILDCARD.into())),
]),
+ Exact(vec![
+ Utf8View,
+ Timestamp(Microsecond, Some(TIMEZONE_WILDCARD.into())),
+ ]),
Exact(vec![Utf8, Timestamp(Second, None)]),
+ Exact(vec![Utf8View, Timestamp(Second, None)]),
Exact(vec![
Utf8,
Timestamp(Second, Some(TIMEZONE_WILDCARD.into())),
]),
+ Exact(vec![
+ Utf8View,
+ Timestamp(Second, Some(TIMEZONE_WILDCARD.into())),
+ ]),
Exact(vec![Utf8, Date64]),
+ Exact(vec![Utf8View, Date64]),
Exact(vec![Utf8, Date32]),
+ Exact(vec![Utf8View, Date32]),
Exact(vec![Utf8, Time32(Second)]),
+ Exact(vec![Utf8View, Time32(Second)]),
Exact(vec![Utf8, Time32(Millisecond)]),
+ Exact(vec![Utf8View, Time32(Millisecond)]),
Exact(vec![Utf8, Time64(Microsecond)]),
+ Exact(vec![Utf8View, Time64(Microsecond)]),
Exact(vec![Utf8, Time64(Nanosecond)]),
+ Exact(vec![Utf8View, Time64(Nanosecond)]),
],
Volatility::Immutable,
),
@@ -114,6 +140,8 @@ impl ScalarUDFImpl for DatePartFunc {
let part = if let ColumnarValue::Scalar(ScalarValue::Utf8(Some(v))) =
part {
v
+ } else if let ColumnarValue::Scalar(ScalarValue::Utf8View(Some(v))) =
part {
+ v
} else {
return exec_err!(
"First argument of `DATE_PART` must be non-null scalar Utf8"
diff --git a/datafusion/functions/src/datetime/date_trunc.rs
b/datafusion/functions/src/datetime/date_trunc.rs
index 6b52507a9c..308ea668d3 100644
--- a/datafusion/functions/src/datetime/date_trunc.rs
+++ b/datafusion/functions/src/datetime/date_trunc.rs
@@ -29,7 +29,7 @@ use arrow::array::types::{
TimestampNanosecondType, TimestampSecondType,
};
use arrow::array::{Array, PrimitiveArray};
-use arrow::datatypes::DataType::{self, Null, Timestamp, Utf8};
+use arrow::datatypes::DataType::{self, Null, Timestamp, Utf8, Utf8View};
use arrow::datatypes::TimeUnit::{self, Microsecond, Millisecond, Nanosecond,
Second};
use datafusion_common::cast::as_primitive_array;
use datafusion_common::{exec_err, plan_err, DataFusionError, Result,
ScalarValue};
@@ -61,25 +61,45 @@ impl DateTruncFunc {
signature: Signature::one_of(
vec![
Exact(vec![Utf8, Timestamp(Nanosecond, None)]),
+ Exact(vec![Utf8View, Timestamp(Nanosecond, None)]),
Exact(vec![
Utf8,
Timestamp(Nanosecond, Some(TIMEZONE_WILDCARD.into())),
]),
+ Exact(vec![
+ Utf8View,
+ Timestamp(Nanosecond, Some(TIMEZONE_WILDCARD.into())),
+ ]),
Exact(vec![Utf8, Timestamp(Microsecond, None)]),
+ Exact(vec![Utf8View, Timestamp(Microsecond, None)]),
Exact(vec![
Utf8,
Timestamp(Microsecond, Some(TIMEZONE_WILDCARD.into())),
]),
+ Exact(vec![
+ Utf8View,
+ Timestamp(Microsecond, Some(TIMEZONE_WILDCARD.into())),
+ ]),
Exact(vec![Utf8, Timestamp(Millisecond, None)]),
+ Exact(vec![Utf8View, Timestamp(Millisecond, None)]),
Exact(vec![
Utf8,
Timestamp(Millisecond, Some(TIMEZONE_WILDCARD.into())),
]),
+ Exact(vec![
+ Utf8View,
+ Timestamp(Millisecond, Some(TIMEZONE_WILDCARD.into())),
+ ]),
Exact(vec![Utf8, Timestamp(Second, None)]),
+ Exact(vec![Utf8View, Timestamp(Second, None)]),
Exact(vec![
Utf8,
Timestamp(Second, Some(TIMEZONE_WILDCARD.into())),
]),
+ Exact(vec![
+ Utf8View,
+ Timestamp(Second, Some(TIMEZONE_WILDCARD.into())),
+ ]),
],
Volatility::Immutable,
),
@@ -119,6 +139,9 @@ impl ScalarUDFImpl for DateTruncFunc {
let granularity = if let
ColumnarValue::Scalar(ScalarValue::Utf8(Some(v))) =
granularity
+ {
+ v.to_lowercase()
+ } else if let ColumnarValue::Scalar(ScalarValue::Utf8View(Some(v))) =
granularity
{
v.to_lowercase()
} else {
diff --git a/datafusion/functions/src/datetime/make_date.rs
b/datafusion/functions/src/datetime/make_date.rs
index 6aa72572bc..ded7b454f9 100644
--- a/datafusion/functions/src/datetime/make_date.rs
+++ b/datafusion/functions/src/datetime/make_date.rs
@@ -23,7 +23,7 @@ use arrow::array::cast::AsArray;
use arrow::array::types::{Date32Type, Int32Type};
use arrow::array::PrimitiveArray;
use arrow::datatypes::DataType;
-use arrow::datatypes::DataType::{Date32, Int32, Int64, UInt32, UInt64, Utf8};
+use arrow::datatypes::DataType::{Date32, Int32, Int64, UInt32, UInt64, Utf8,
Utf8View};
use chrono::prelude::*;
use datafusion_common::{exec_err, Result, ScalarValue};
@@ -45,7 +45,7 @@ impl MakeDateFunc {
Self {
signature: Signature::uniform(
3,
- vec![Int32, Int64, UInt32, UInt64, Utf8],
+ vec![Int32, Int64, UInt32, UInt64, Utf8, Utf8View],
Volatility::Immutable,
),
}
diff --git a/datafusion/functions/src/utils.rs
b/datafusion/functions/src/utils.rs
index 393dcc456a..6fcb9c6f08 100644
--- a/datafusion/functions/src/utils.rs
+++ b/datafusion/functions/src/utils.rs
@@ -15,12 +15,14 @@
// specific language governing permissions and limitations
// under the License.
+use std::sync::Arc;
+
use arrow::array::ArrayRef;
use arrow::datatypes::DataType;
+
use datafusion_common::{Result, ScalarValue};
use datafusion_expr::function::Hint;
use datafusion_expr::{ColumnarValue, ScalarFunctionImplementation};
-use std::sync::Arc;
/// Creates a function to identify the optimal return type of a string
function given
/// the type of its first argument.
@@ -29,6 +31,8 @@ use std::sync::Arc;
/// `$largeUtf8Type`,
///
/// If the input type is `Utf8` or `Binary` the return type is `$utf8Type`,
+///
+/// If the input type is `Utf8View` the return type is `Utf8View`,
macro_rules! get_optimal_return_type {
($FUNC:ident, $largeUtf8Type:expr, $utf8Type:expr) => {
pub(crate) fn $FUNC(arg_type: &DataType, name: &str) ->
Result<DataType> {
@@ -37,6 +41,8 @@ macro_rules! get_optimal_return_type {
DataType::LargeUtf8 | DataType::LargeBinary => $largeUtf8Type,
// Binary inputs are automatically coerced to Utf8
DataType::Utf8 | DataType::Binary => $utf8Type,
+ // Utf8View inputs will yield Utf8View outputs
+ DataType::Utf8View => DataType::Utf8View,
DataType::Null => DataType::Null,
DataType::Dictionary(_, value_type) => match **value_type {
DataType::LargeUtf8 | DataType::LargeBinary =>
$largeUtf8Type,
diff --git a/datafusion/sqllogictest/src/engines/datafusion_engine/normalize.rs
b/datafusion/sqllogictest/src/engines/datafusion_engine/normalize.rs
index 520b6b53b3..66ffeadf8c 100644
--- a/datafusion/sqllogictest/src/engines/datafusion_engine/normalize.rs
+++ b/datafusion/sqllogictest/src/engines/datafusion_engine/normalize.rs
@@ -233,6 +233,11 @@ pub fn cell_to_string(col: &ArrayRef, row: usize) ->
Result<String> {
DataType::Utf8 => {
Ok(varchar_to_str(get_row_value!(array::StringArray, col,
row)))
}
+ DataType::Utf8View => Ok(varchar_to_str(get_row_value!(
+ array::StringViewArray,
+ col,
+ row
+ ))),
_ => {
let f = ArrayFormatter::try_new(col.as_ref(),
&DEFAULT_FORMAT_OPTIONS);
Ok(f.unwrap().value(row).to_string())
diff --git a/datafusion/sqllogictest/test_files/string_view.slt
b/datafusion/sqllogictest/test_files/string_view.slt
index 3ba4e271c2..3f9a4793f6 100644
--- a/datafusion/sqllogictest/test_files/string_view.slt
+++ b/datafusion/sqllogictest/test_files/string_view.slt
@@ -324,3 +324,24 @@ logical_plan
statement ok
drop table test;
+
+# coercion from stringview to integer, as input to make_date
+query D
+select make_date(arrow_cast('2024', 'Utf8View'), arrow_cast('01', 'Utf8View'),
arrow_cast('23', 'Utf8View'))
+----
+2024-01-23
+
+# coercions between stringview and date types
+statement ok
+create table dates (dt date) as values
+ (date '2024-01-23'),
+ (date '2023-11-30');
+
+query D
+select t.dt from dates t where arrow_cast('2024-01-01', 'Utf8View') < t.dt;
+----
+2024-01-23
+
+
+statement ok
+drop table dates;
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
