Revive CI after misconfigured GHA job

.github/workflows/rust.yml

@@ -31,7 +31,7 @@ jobs:
     strategy:
       matrix:
         arch: [amd64]
-        rust: [nightly-2022-06-22]
+        rust: [nightly-2024-01-29]
     container:
       image: ${{ matrix.arch }}/rust
       env:
@@ -73,7 +73,7 @@ jobs:
     strategy:
       matrix:
         arch: [amd64]
-        rust: [nightly-2022-06-22]
+        rust: [nightly-2024-01-29]
     container:
       image: ${{ matrix.arch }}/rust
       env:
@@ -120,61 +120,61 @@ jobs:
           cargo run --example read_csv_infer_schema
 
   # test the --features "simd" of the arrow crate. This requires nightly.
-  linux-test-simd:
-    name: Test SIMD on AMD64 Rust ${{ matrix.rust }}
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        arch: [amd64]
-        rust: []
-    container:
-      image: ${{ matrix.arch }}/rust
-      env:
-        # Disable full debug symbol generation to speed up CI build and keep memory down
-        # "1" means line tables only, which is useful for panic tracebacks.
-        RUSTFLAGS: "-C debuginfo=1"
-        ARROW_TEST_DATA: /__w/arrow-rs/arrow-rs/testing/data
-    steps:
-      - uses: actions/checkout@v2
-        with:
-          submodules: true
-      - name: Cache Cargo
-        uses: actions/cache@v2
-        with:
-          path: /github/home/.cargo
-          # this key equals the ones on `linux-build-lib` for re-use
-          key: cargo-cache-
-      - name: Cache Rust dependencies
-        uses: actions/cache@v2
-        with:
-          path: /github/home/target
-          # this key equals the ones on `linux-build-lib` for re-use
-          key: ${{ runner.os }}-${{ matrix.arch }}-target-cache-${{ matrix.rust }}
-      - name: Setup Rust toolchain
-        run: |
-          rustup toolchain install ${{ matrix.rust }}
-          rustup default ${{ matrix.rust }}
-          rustup component add rustfmt
-      - name: Run tests
-        run: |
-          export CARGO_HOME="/github/home/.cargo"
-          export CARGO_TARGET_DIR="/github/home/target"
-          cd arrow
-          cargo test --features "simd"
-      - name: Check new project build with simd features
-        run: |
-          export CARGO_HOME="/github/home/.cargo"
-          export CARGO_TARGET_DIR="/github/home/target"
-          cd arrow/test/dependency/simd
-          cargo check
+#  linux-test-simd:
+#    name: Test SIMD on AMD64 Rust ${{ matrix.rust }}
+#    runs-on: ubuntu-latest
+#    strategy:
+#      matrix:
+#        arch: [amd64]
+#        rust: []
+#    container:
+#      image: ${{ matrix.arch }}/rust
+#      env:
+#        # Disable full debug symbol generation to speed up CI build and keep memory down
+#        # "1" means line tables only, which is useful for panic tracebacks.
+#        RUSTFLAGS: "-C debuginfo=1"
+#        ARROW_TEST_DATA: /__w/arrow-rs/arrow-rs/testing/data
+#    steps:
+#      - uses: actions/checkout@v2
+#        with:
+#          submodules: true
+#      - name: Cache Cargo
+#        uses: actions/cache@v2
+#        with:
+#          path: /github/home/.cargo
+#          # this key equals the ones on `linux-build-lib` for re-use
+#          key: cargo-cache-
+#      - name: Cache Rust dependencies
+#        uses: actions/cache@v2
+#        with:
+#          path: /github/home/target
+#          # this key equals the ones on `linux-build-lib` for re-use
+#          key: ${{ runner.os }}-${{ matrix.arch }}-target-cache-${{ matrix.rust }}
+#      - name: Setup Rust toolchain
+#        run: |
+#          rustup toolchain install ${{ matrix.rust }}
+#          rustup default ${{ matrix.rust }}
+#          rustup component add rustfmt
+#      - name: Run tests
+#        run: |
+#          export CARGO_HOME="/github/home/.cargo"
+#          export CARGO_TARGET_DIR="/github/home/target"
+#          cd arrow
+#          cargo test --features "simd"
+#      - name: Check new project build with simd features
+#        run: |
+#          export CARGO_HOME="/github/home/.cargo"
+#          export CARGO_TARGET_DIR="/github/home/target"
+#          cd arrow/test/dependency/simd
+#          cargo check
 
   windows-and-macos:
     name: Test on ${{ matrix.os }} Rust ${{ matrix.rust }}
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
         os: [windows-latest, macos-latest]
-        rust: [nightly-2022-06-22]
+        rust: [nightly-2024-01-29]
     steps:
       - uses: actions/checkout@v2
         with:
@@ -202,7 +202,7 @@ jobs:
     strategy:
       matrix:
         arch: [amd64]
-        rust: [nightly-2022-06-22]
+        rust: [nightly-2024-01-29]
     container:
       image: ${{ matrix.arch }}/rust
       env:
@@ -257,7 +257,7 @@ jobs:
     strategy:
       matrix:
         arch: [amd64]
-        rust: [nightly-2022-06-22]
+        rust: [nightly-2024-01-29]
     steps:
       - uses: actions/checkout@v2
         with:
@@ -297,7 +297,7 @@ jobs:
     strategy:
       matrix:
         arch: [amd64]
-        rust: [nightly-2022-06-22]
+        rust: [nightly-2024-01-29]
     container:
       image: ${{ matrix.arch }}/rust
       env:
@@ -341,7 +341,7 @@ jobs:
     strategy:
       matrix:
         arch: [amd64]
-        rust: [nightly-2022-06-22]
+        rust: [nightly-2024-01-29]
     container:
       image: ${{ matrix.arch }}/rust
       env:

arrow-flight/Cargo.toml

@@ -46,3 +46,10 @@ proc-macro2 = "1.0.27"
 #[lib]
 #name = "flight"
 #path = "src/lib.rs"
+
+# Just silence all of prolematic rules in original code
+# This list should be updated during rebasing on new release, before our commits, but after toolchain updates
+# That way we would disable only the rules that are violated by upstream code, but not by ours
+
+[lints.clippy]
+needless_borrow = "allow"

arrow/Cargo.toml

@@ -76,6 +76,7 @@ memory-check = []
 [dev-dependencies]
 criterion = "0.3"
 flate2 = "1"
+rand = "0.8"
 tempfile = "3"
 
 [build-dependencies]
@@ -163,3 +164,50 @@ harness = false
 [[bench]]
 name = "buffer_create"
 harness = false
+
+
+# Just silence all of prolematic rules in original code
+# This list should be updated during rebasing on new release, before our commits, but after toolchain updates
+# That way we would disable only the rules that are violated by upstream code, but not by ours
+
+[lints.rust]
+deprecated = "allow"
+unreachable_patterns = "allow"
+unused_imports = "allow"
+unused_must_use = "allow"
+
+[lints.clippy]
+# Can drop this rule after rebase on commit 55d6073 "Require Send+Sync bounds for Allocation trait (#1945)", first released in 18.0.0
+arc_with_non_send_sync = "allow"
+borrow_deref_ref = "allow"
+derivable_impls = "allow"
+get_first = "allow"
+err_expect = "allow"
+extra_unused_lifetimes = "allow"
+extra_unused_type_parameters = "allow"
+into_iter_on_ref = "allow"
+manual_bits = "allow"
+manual_slice_size_calculation = "allow"
+map_flatten = "allow"
+needless_borrow = "allow"
+needless_borrowed_reference = "allow"
+needless_borrows_for_generic_args = "allow"
+needless_late_init = "allow"
+needless_lifetimes = "allow"
+needless_question_mark = "allow"
+needless_return = "allow"
+non_canonical_partial_ord_impl = "allow"
+non_minimal_cfg = "allow"
+nonminimal_bool = "allow"
+only_used_in_recursion = "allow"
+partialeq_to_none = "allow"
+redundant_closure = "allow"
+redundant_closure_call = "allow"
+seek_from_current = "allow"
+suspicious_doc_comments = "allow"
+to_string_in_format_args = "allow"
+unnecessary_cast = "allow"
+unnecessary_fallible_conversions = "allow"
+unwrap_or_default = "allow"
+useless_conversion = "allow"
+useless_vec = "allow"

arrow/src/compute/kernels/comparison.rs

@@ -217,7 +217,7 @@ where
 /// use arrow::compute::like_utf8;
 ///
 /// let strings = StringArray::from(vec!["Arrow", "Arrow", "Arrow", "Ar"]);
-/// let patterns = StringArray::from(vec!["A%", "B%", "A.", "A."]);
+/// let patterns = StringArray::from(vec!["A%", "B%", "A.", "A_"]);
 ///
 /// let result = like_utf8(&strings, &patterns).unwrap();
 /// assert_eq!(result, BooleanArray::from(vec![true, false, false, true]));

arrow/src/compute/kernels/substring.rs

@@ -244,11 +244,11 @@ mod tests {
 
         cases.into_iter().try_for_each::<_, Result<()>>(
             |(array, start, length, expected)| {
-                let array = StringArray::from(array);
+                let array = T::from(array.iter().copied().map(Some).collect());
                 let result = substring(&array, start, &length)?;
                 assert_eq!(array.len(), result.len());
-                let result = result.as_any().downcast_ref::<StringArray>().unwrap();
-                let expected = StringArray::from(expected);
+                let result = result.as_any().downcast_ref::<T>().unwrap();
+                let expected = T::from(expected.iter().copied().map(Some).collect());
                 assert_eq!(&expected, result,);
                 Ok(())
             },

arrow/src/ffi.rs

@@ -132,9 +132,9 @@ unsafe extern "C" fn release_schema(schema: *mut FFI_ArrowSchema) {
     let schema = &mut *schema;
 
     // take ownership back to release it.
-    CString::from_raw(schema.format as *mut c_char);
+    drop(CString::from_raw(schema.format as *mut c_char));
     if !schema.name.is_null() {
-        CString::from_raw(schema.name as *mut c_char);
+        drop(CString::from_raw(schema.name as *mut c_char));
     }
     if !schema.private_data.is_null() {
         let private_data = Box::from_raw(schema.private_data as *mut SchemaPrivateData);

arrow/src/json/reader.rs

@@ -2350,7 +2350,7 @@ mod tests {
         let re = builder.build(Cursor::new(json_content));
         assert_eq!(
             re.err().unwrap().to_string(),
-            r#"Json error: Expected JSON record to be an object, found Array([Number(1), String("hello")])"#,
+            r#"Json error: Expected JSON record to be an object, found Array [Number(1), String("hello")]"#,
         );
     }
 

arrow/src/json/writer.rs

@@ -947,7 +947,7 @@ mod tests {
 
         assert_eq!(
             String::from_utf8(buf).unwrap(),
-            r#"{"duration_sec":"PT120S","duration_msec":"PT0.120S","duration_usec":"PT0.000120S","duration_nsec":"PT0.000000120S","name":"a"}
+            r#"{"duration_sec":"PT120S","duration_msec":"PT0.12S","duration_usec":"PT0.00012S","duration_nsec":"PT0.00000012S","name":"a"}
 {"name":"b"}
 "#
         );

arrow/src/util/integration_util.rs

@@ -249,14 +249,6 @@ impl ArrowJsonBatch {
                         let arr = Int64Array::from(arr.data().clone());
                         arr.equals_json(&json_array.iter().collect::<Vec<&Value>>()[..])
                     }
-                    DataType::Int64
-                    | DataType::Date64
-                    | DataType::Time64(_)
-                    | DataType::Timestamp(_, _)
-                    | DataType::Duration(_) => {
-                        let arr = Int64Array::from(arr.data().clone());
-                        arr.equals_json(&json_array.iter().collect::<Vec<&Value>>()[..])
-                    }
                     DataType::Interval(IntervalUnit::YearMonth) => {
                         let arr = IntervalYearMonthArray::from(arr.data().clone());
                         arr.equals_json(&json_array.iter().collect::<Vec<&Value>>()[..])

integration-testing/Cargo.toml

@@ -43,3 +43,14 @@ serde_json = { version = "1.0", features = ["preserve_order"] }
 tokio = { version = "1.0", features = ["macros", "rt", "rt-multi-thread"] }
 tonic = "0.4"
 tracing-subscriber = { version = "0.2.15", optional = true }
+
+# Just silence all of prolematic rules in original code
+# This list should be updated during rebasing on new release, before our commits, but after toolchain updates
+# That way we would disable only the rules that are violated by upstream code, but not by ours
+
+[lints.rust]
+dead_code = "allow"
+
+[lints.clippy]
+get_first = "allow"
+needless_borrow = "allow"

parquet/Cargo.toml

@@ -83,4 +83,38 @@ harness = false
 
 [[bench]]
 name = "arrow_array_reader"
-harness = false
+harness = false
+
+# Just silence all of prolematic rules in original code
+# This list should be updated during rebasing on new release, before our commits, but after toolchain updates
+# That way we would disable only the rules that are violated by upstream code, but not by ours
+
+[lints.rust]
+deprecated = "allow"
+unused_imports = "allow"
+unused_mut = "allow"
+
+[lints.clippy]
+# Can drop this rule after rebase on commit 55d6073 "Require Send+Sync bounds for Allocation trait (#1945)", first released in 18.0.0
+arc_with_non_send_sync = "allow"
+derivable_impls = "allow"
+enum_variant_names = "allow"
+extra_unused_lifetimes = "allow"
+get_first = "allow"
+let_and_return = "allow"
+needless_borrow = "allow"
+needless_borrowed_reference = "allow"
+needless_borrows_for_generic_args = "allow"
+needless_lifetimes = "allow"
+needless_return = "allow"
+nonminimal_bool = "allow"
+partialeq_to_none = "allow"
+seek_from_current = "allow"
+should_implement_trait = "allow"
+unnecessary_cast = "allow"
+unnecessary_to_owned = "allow"
+unused_io_amount = "allow"
+useless_conversion = "allow"
+useless_format = "allow"
+useless_vec = "allow"
+wrong_self_convention = "allow"

parquet/src/column/page.rs

@@ -209,7 +209,11 @@ pub trait PageWriter {
     ///
     /// This method is called for every compressed page we write into underlying buffer,
     /// either data page or dictionary page.
-    fn write_page(&mut self, page: CompressedPage, aad_page_ordinal: Option<u16>) -> Result<PageWriteSpec>;
+    fn write_page(
+        &mut self,
+        page: CompressedPage,
+        aad_page_ordinal: Option<u16>,
+    ) -> Result<PageWriteSpec>;
 
     /// Writes column chunk metadata into the output stream/sink.
     ///