From 80e3ba86b81503b39178d28a095dd7d1fc6cb4f9 Mon Sep 17 00:00:00 2001
From: Joel Natividad <1980690+jqnatividad@users.noreply.github.com>
Date: Mon, 18 Sep 2023 05:21:47 -0400
Subject: [PATCH 1/4] `deps`: bump polars to 0.33 from 0.32

https://github.com/pola-rs/polars/releases/tag/rs-0.33.0
---
 Cargo.lock | 107 ++++++++++++++++++++++++++---------------------------
 Cargo.toml |   2 +-
 2 files changed, 54 insertions(+), 55 deletions(-)

diff --git a/Cargo.lock b/Cargo.lock
index 4e9644e4e..f7f3caeb3 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -474,9 +474,9 @@ dependencies = [
 
 [[package]]
 name = "arrow2"
-version = "0.17.4"
+version = "0.18.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "59c468daea140b747d781a1da9f7db5f0a8e6636d4af20cc539e43d05b0604fa"
+checksum = "963fef509b757bcbbf9e5ffa23bcb345614d99f4f6f531f97417b27b8604d389"
 dependencies = [
  "ahash 0.8.3",
  "arrow-format",
@@ -491,13 +491,14 @@ dependencies = [
  "futures",
  "getrandom",
  "hash_hasher",
+ "hashbrown 0.14.0",
  "lexical-core",
  "lz4",
  "multiversion",
  "num-traits",
  "parquet2",
  "regex",
- "regex-syntax 0.6.29",
+ "regex-syntax 0.7.5",
  "rustc_version",
  "simdutf8",
  "streaming-iterator",
@@ -557,7 +558,7 @@ checksum = "16e62a023e7c117e27523144c5d2459f4397fcc3cab0085af8e2224f643a0193"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.35",
+ "syn 2.0.37",
 ]
 
 [[package]]
@@ -568,7 +569,7 @@ checksum = "bc00ceb34980c03614e35a3a4e218276a0a824e911d07651cd0d858a51e8c0f0"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.35",
+ "syn 2.0.37",
 ]
 
 [[package]]
@@ -647,7 +648,7 @@ dependencies = [
  "regex",
  "rustc-hash",
  "shlex",
- "syn 2.0.35",
+ "syn 2.0.37",
  "which",
 ]
 
@@ -826,7 +827,7 @@ checksum = "965ab7eb5f8f97d2a083c799f3a1b994fc397b2fe2da5d1da1626ce15a39f2b1"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.35",
+ "syn 2.0.37",
 ]
 
 [[package]]
@@ -1578,7 +1579,7 @@ dependencies = [
  "once_cell",
  "proc-macro2",
  "quote",
- "syn 2.0.35",
+ "syn 2.0.37",
 ]
 
 [[package]]
@@ -1883,7 +1884,7 @@ checksum = "89ca545a94061b6365f2c7355b4b32bd20df3ff95f02da9329b34ccc3bd6ee72"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.35",
+ "syn 2.0.37",
 ]
 
 [[package]]
@@ -2697,13 +2698,12 @@ checksum = "1a9bad9f94746442c783ca431b22403b519cd7fbeed0533fdd6328b2f2212128"
 
 [[package]]
 name = "local-channel"
-version = "0.1.3"
+version = "0.1.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7f303ec0e94c6c54447f84f3b0ef7af769858a9c4ef56ef2a986d3dcd4c3fc9c"
+checksum = "e0a493488de5f18c8ffcba89eebb8532ffc562dc400490eb65b84893fae0b178"
 dependencies = [
  "futures-core",
  "futures-sink",
- "futures-util",
  "local-waker",
 ]
 
@@ -3308,7 +3308,7 @@ checksum = "4359fd9c9171ec6e8c62926d6faaf553a8dc3f64e1507e76da7911b4f6a04405"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.35",
+ "syn 2.0.37",
 ]
 
 [[package]]
@@ -3340,9 +3340,9 @@ dependencies = [
 
 [[package]]
 name = "polars"
-version = "0.32.1"
+version = "0.33.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b1362d4a136c0ebacb40d88a37ba361738b222fd8a2ee9340a3d8642f698c52b"
+checksum = "3030de163b9ff2c9dac9a12dcb9be25cc0f2bc7c8e7cd2e4b2592ebed458ce6a"
 dependencies = [
  "getrandom",
  "polars-core",
@@ -3356,9 +3356,9 @@ dependencies = [
 
 [[package]]
 name = "polars-arrow"
-version = "0.32.1"
+version = "0.33.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f967c901fa5da4ca7f64e813d1268488ba97e9b3004cefc579ff851c197a1138"
+checksum = "35cd38a64fb389fd990e4efd433a36331c995c981d353bfef83b5de4d87f1828"
 dependencies = [
  "arrow2",
  "hashbrown 0.14.0",
@@ -3371,9 +3371,9 @@ dependencies = [
 
 [[package]]
 name = "polars-core"
-version = "0.32.1"
+version = "0.33.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b24f92fc5b167f668ff85ab9607dfa72e2c09664cacef59297ee8601dee60126"
+checksum = "08367c014c07fa8f141680e024f926cab3a1fe839605a8fcf2223647eb45ca71"
 dependencies = [
  "ahash 0.8.3",
  "arrow2",
@@ -3402,9 +3402,9 @@ dependencies = [
 
 [[package]]
 name = "polars-error"
-version = "0.32.1"
+version = "0.33.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "40d09c3a7337e53b38c37b57999038440fa39c6801b9ba48afaecd8e16f7ac0a"
+checksum = "9b20a09651a299979354945819dc2ce017964b80b916954e9d2ce39002a5f949"
 dependencies = [
  "arrow2",
  "regex",
@@ -3413,17 +3413,15 @@ dependencies = [
 
 [[package]]
 name = "polars-io"
-version = "0.32.1"
+version = "0.33.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "92cab0df9f2a35702fa5aec99edfaabf9ae8e9cdd0acf69e143ad2d132f34f9c"
+checksum = "88cf4a89c18a90ac20dfbcdfd19ab50ad4ac5a76fc7bb775d3c28bb738cf1f34"
 dependencies = [
  "ahash 0.8.3",
  "arrow2",
- "async-trait",
  "bytes",
  "chrono",
  "fast-float",
- "futures",
  "home",
  "lexical",
  "lexical-core",
@@ -3442,14 +3440,13 @@ dependencies = [
  "serde_json",
  "simd-json",
  "simdutf8",
- "tokio",
 ]
 
 [[package]]
 name = "polars-json"
-version = "0.32.1"
+version = "0.33.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9e58094557cf6446808c7348dcb797885db61815857f6ea02924b35505566e94"
+checksum = "d6d5666176d681706aef5a06a57597c83391948b3d958f9fbe9b4cf016527eb8"
 dependencies = [
  "ahash 0.8.3",
  "arrow2",
@@ -3465,9 +3462,9 @@ dependencies = [
 
 [[package]]
 name = "polars-lazy"
-version = "0.32.1"
+version = "0.33.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2c33762ec2a55e01c9f8776b34db86257c70a0a3b3929bd4eb91a52aacf61456"
+checksum = "5110eab438848c981cc5f541fbc5b21bb263fd707000b4715233074fb2630fcf"
 dependencies = [
  "ahash 0.8.3",
  "bitflags 2.4.0",
@@ -3489,9 +3486,9 @@ dependencies = [
 
 [[package]]
 name = "polars-ops"
-version = "0.32.1"
+version = "0.33.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e825575c96302d2daedfc205a0062180033c92c55bcd6aafc4e109d4d8849ed0"
+checksum = "7740d7bc4c2ca08044f9ef599638e116fdd7d687e80d1974b698e390c6ce4252"
 dependencies = [
  "argminmax",
  "arrow2",
@@ -3501,15 +3498,16 @@ dependencies = [
  "polars-arrow",
  "polars-core",
  "polars-utils",
+ "regex",
  "smartstring",
  "version_check",
 ]
 
 [[package]]
 name = "polars-pipe"
-version = "0.32.1"
+version = "0.33.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1f2bc9a12da9ed043fb0cb51dbcb87b365e4845b7ab6399d7a81e838460c6974"
+checksum = "1f30c5e77c5594ddc958a46fe2e021da2feba9c94e767e1d798bd82ac5a33c3b"
 dependencies = [
  "crossbeam-channel",
  "crossbeam-queue",
@@ -3530,9 +3528,9 @@ dependencies = [
 
 [[package]]
 name = "polars-plan"
-version = "0.32.1"
+version = "0.33.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fb67b014f0295e8e9dbb84404a91d666d477b3bc248a2ed51bc442833b16da35"
+checksum = "678cbeb730e29e50f0f8d844102d15454fc6113a74c667eab046c0e4a4322a9e"
 dependencies = [
  "ahash 0.8.3",
  "arrow2",
@@ -3552,9 +3550,9 @@ dependencies = [
 
 [[package]]
 name = "polars-row"
-version = "0.32.1"
+version = "0.33.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "27f54c1956027bf6301948fb4f2837cf6d6b638d8dd1edf3aaeaa19906a986be"
+checksum = "c52ef8885b9d13f848839594fbab21ad79fc63f7e11c19cdc2cfe9bb03c313ac"
 dependencies = [
  "arrow2",
  "polars-error",
@@ -3563,9 +3561,9 @@ dependencies = [
 
 [[package]]
 name = "polars-sql"
-version = "0.32.1"
+version = "0.33.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "dbfcb15cf8eebd25ea1724109d0153817cd484c6326290585f0736b4e7fcf2f4"
+checksum = "4d716855267e3516f722287f68cf10e650e33f7197df83a79e680602471456fc"
 dependencies = [
  "polars-arrow",
  "polars-core",
@@ -3578,9 +3576,9 @@ dependencies = [
 
 [[package]]
 name = "polars-time"
-version = "0.32.1"
+version = "0.33.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "53f42d2632f5971c9575041d33cbcfb1f996900c40bbf58bc6eb0a0c5efbecea"
+checksum = "a2eb75a24f11b55a400b52dc19a2a3e949aaaa46a911f99496de4485b1127063"
 dependencies = [
  "arrow2",
  "atoi",
@@ -3597,11 +3595,12 @@ dependencies = [
 
 [[package]]
 name = "polars-utils"
-version = "0.32.1"
+version = "0.33.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c326708a370d71dc6e11a8f4bbc10a8479e1c314dc048ba73543b815cd0bf339"
+checksum = "2a4a5e743509096322cad39104d56e329fe2748483a3354a0f0c354724f3cef6"
 dependencies = [
  "ahash 0.8.3",
+ "bytemuck",
  "hashbrown 0.14.0",
  "num-traits",
  "once_cell",
@@ -3674,7 +3673,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ae005bd773ab59b4725093fd7df83fd7892f7d8eafb48dbd7de6e024e4215f9d"
 dependencies = [
  "proc-macro2",
- "syn 2.0.35",
+ "syn 2.0.37",
 ]
 
 [[package]]
@@ -4535,7 +4534,7 @@ checksum = "4eca7ac642d82aa35b60049a6eccb4be6be75e599bd2e9adb5f875a737654af2"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.35",
+ "syn 2.0.37",
 ]
 
 [[package]]
@@ -4607,7 +4606,7 @@ checksum = "91d129178576168c589c9ec973feedf7d3126c01ac2bf08795109aa35b69fb8f"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.35",
+ "syn 2.0.37",
 ]
 
 [[package]]
@@ -4920,7 +4919,7 @@ dependencies = [
  "proc-macro2",
  "quote",
  "rustversion",
- "syn 2.0.35",
+ "syn 2.0.37",
 ]
 
 [[package]]
@@ -4942,9 +4941,9 @@ dependencies = [
 
 [[package]]
 name = "syn"
-version = "2.0.35"
+version = "2.0.37"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "59bf04c28bee9043ed9ea1e41afc0552288d3aba9c6efdd78903b802926f4879"
+checksum = "7303ef2c05cd654186cb250d29049a24840ca25d2747c25c0381c8d9e2f582e8"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -5044,7 +5043,7 @@ checksum = "49922ecae66cc8a249b77e68d1d0623c1b2c514f0060c27cdc68bd62a1219d35"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.35",
+ "syn 2.0.37",
 ]
 
 [[package]]
@@ -5152,7 +5151,7 @@ checksum = "630bdcf245f78637c13ec01ffae6187cca34625e8c63150d424b59e55af2675e"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.35",
+ "syn 2.0.37",
 ]
 
 [[package]]
@@ -5474,7 +5473,7 @@ dependencies = [
  "once_cell",
  "proc-macro2",
  "quote",
- "syn 2.0.35",
+ "syn 2.0.37",
  "wasm-bindgen-shared",
 ]
 
@@ -5508,7 +5507,7 @@ checksum = "54681b18a46765f095758388f2d0cf16eb8d4169b639ab575a8f5693af210c7b"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.35",
+ "syn 2.0.37",
  "wasm-bindgen-backend",
  "wasm-bindgen-shared",
 ]
diff --git a/Cargo.toml b/Cargo.toml
index 8fae1799a..2431a4465 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -129,7 +129,7 @@ mlua = { version = "0.9", features = [
 ], optional = true }
 num_cpus = "1"
 odht = "0.3"
-polars = { version = "0.32", features = [
+polars = { version = "0.33", features = [
     "lazy",
     "streaming",
     "object",

From 3930294de908b7e1b882612aba099abf12aa21fd Mon Sep 17 00:00:00 2001
From: Joel Natividad <1980690+jqnatividad@users.noreply.github.com>
Date: Mon, 18 Sep 2023 05:23:09 -0400
Subject: [PATCH 2/4] `sqlp` & `joinp`: OptState struct has two new members

`fast_projection: true` and
`eager: false`
---
 src/cmd/joinp.rs | 2 ++
 src/cmd/sqlp.rs  | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/src/cmd/joinp.rs b/src/cmd/joinp.rs
index 8ab2807cb..380308d4d 100644
--- a/src/cmd/joinp.rs
+++ b/src/cmd/joinp.rs
@@ -389,6 +389,8 @@ impl JoinStruct {
                 comm_subplan_elim:   true,
                 comm_subexpr_elim:   true,
                 streaming:           self.streaming,
+                fast_projection:     true,
+                eager:               false,
             }
         };
         log::debug!("Optimization state: {optimization_state:?}");
diff --git a/src/cmd/sqlp.rs b/src/cmd/sqlp.rs
index 460b4dc65..f7e73063a 100644
--- a/src/cmd/sqlp.rs
+++ b/src/cmd/sqlp.rs
@@ -393,6 +393,8 @@ pub fn run(argv: &[&str]) -> CliResult<()> {
             comm_subplan_elim:   !args.flag_low_memory,
             comm_subexpr_elim:   true,
             streaming:           args.flag_low_memory,
+            fast_projection:     true,
+            eager:               false,
         }
     };
     // gated by log::log_enabled!(log::Level::Debug) to avoid the

From 94ca07bd009d6a7dcebb6269675b756901f939f9 Mon Sep 17 00:00:00 2001
From: Joel Natividad <1980690+jqnatividad@users.noreply.github.com>
Date: Mon, 18 Sep 2023 05:24:15 -0400
Subject: [PATCH 3/4] `sqlp`: --try-parsedates is stricter now, needed to add
 `--ignore-errors` to pass tests

see https://github.com/pola-rs/polars/pull/10877
---
 tests/test_sqlp.rs | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/tests/test_sqlp.rs b/tests/test_sqlp.rs
index 8fc13c3cd..c08c1cf83 100644
--- a/tests/test_sqlp.rs
+++ b/tests/test_sqlp.rs
@@ -582,10 +582,13 @@ fn sqlp_boston311_try_parsedates() {
     let test_file = wrk.load_test_file("boston311-100.csv");
 
     let mut cmd = wrk.command("sqlp");
-    cmd.arg(&test_file).arg("--try-parsedates").arg(
-        "select ward, cast(avg(closed_dt - open_dt) as float) as avg_tat from _t_1 where \
-         case_status = 'Closed' group by ward order by avg_tat desc, ward asc",
-    );
+    cmd.arg(&test_file)
+        .arg("--try-parsedates")
+        .arg(
+            "select ward, cast(avg(closed_dt - open_dt) as float) as avg_tat from _t_1 where \
+             case_status = 'Closed' group by ward order by avg_tat desc, ward asc",
+        )
+        .arg("--ignore-errors");
 
     let got: Vec<Vec<String>> = wrk.read_stdout(&mut cmd);
     let expected = vec![
@@ -644,7 +647,8 @@ fn sqlp_boston311_try_parsedates_precision() {
         .arg(
             "select ward, cast(avg(closed_dt - open_dt) as float) as avg_tat from _t_1 where \
              case_status = 'Closed' group by ward order by avg_tat desc, ward asc limit 5",
-        );
+        )
+        .arg("--ignore-errors");
 
     let got: Vec<Vec<String>> = wrk.read_stdout(&mut cmd);
     let expected = vec![
@@ -667,7 +671,8 @@ fn sqlp_boston311_try_parsedates_format() {
     cmd.arg(&test_file)
         .arg("--try-parsedates")
         .args(["--datetime-format", "%a %Y-%m-%d %H:%M:%S"])
-        .arg("select closed_dt, open_dt from _t_1 where case_status = 'Closed' limit 5");
+        .arg("select closed_dt, open_dt from _t_1 where case_status = 'Closed' limit 5")
+        .arg("--ignore-errors");
 
     let got: Vec<Vec<String>> = wrk.read_stdout(&mut cmd);
     let expected = vec![

From d7e643f4f61c2c6927756a3c34ee08965d19e558 Mon Sep 17 00:00:00 2001
From: Joel Natividad <1980690+jqnatividad@users.noreply.github.com>
Date: Mon, 18 Sep 2023 05:31:08 -0400
Subject: [PATCH 4/4] `sqlp`:  add note about `--try-parsedates` and
 `--ignore-errors`

---
 src/cmd/sqlp.rs | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/src/cmd/sqlp.rs b/src/cmd/sqlp.rs
index f7e73063a..19b563a0e 100644
--- a/src/cmd/sqlp.rs
+++ b/src/cmd/sqlp.rs
@@ -111,6 +111,9 @@ sqlp options:
                               POLARS CSV PARSING OPTIONS:
     --try-parsedates          Automatically try to parse dates/datetimes and time.
                               If parsing fails, columns remain as strings.
+                              Note that if dates are not well-formatted in your CSV,
+                              that you may want to try to set `--ignore-errors` to relax
+                              the CSV parsing of dates.
     --infer-len <arg>         The number of rows to scan when inferring the schema of the CSV.
                               Set to 0 to do a full table scan (warning: very slow).
                               (default: 250)