[arrow-pyarrow]: restore __arrow_c_array__ tuple error

Cargo.toml

@@ -68,7 +68,7 @@ exclude = [
 ]
 
 [workspace.package]
-version = "58.0.0"
+version = "58.1.0"
 homepage = "https://github.com/apache/arrow-rs"
 repository = "https://github.com/apache/arrow-rs"
 authors = ["Apache Arrow <dev@arrow.apache.org>"]
@@ -85,35 +85,37 @@ edition = "2024"
 rust-version = "1.85"
 
 [workspace.dependencies]
-arrow = { version = "58.0.0", path = "./arrow", default-features = false }
-arrow-arith = { version = "58.0.0", path = "./arrow-arith" }
-arrow-array = { version = "58.0.0", path = "./arrow-array" }
-arrow-buffer = { version = "58.0.0", path = "./arrow-buffer" }
-arrow-cast = { version = "58.0.0", path = "./arrow-cast" }
-arrow-csv = { version = "58.0.0", path = "./arrow-csv" }
-arrow-data = { version = "58.0.0", path = "./arrow-data" }
-arrow-ipc = { version = "58.0.0", path = "./arrow-ipc" }
-arrow-json = { version = "58.0.0", path = "./arrow-json" }
-arrow-ord = { version = "58.0.0", path = "./arrow-ord" }
-arrow-pyarrow = { version = "58.0.0", path = "./arrow-pyarrow" }
-arrow-row = { version = "58.0.0", path = "./arrow-row" }
-arrow-schema = { version = "58.0.0", path = "./arrow-schema" }
-arrow-select = { version = "58.0.0", path = "./arrow-select" }
-arrow-string = { version = "58.0.0", path = "./arrow-string" }
-parquet = { version = "58.0.0", path = "./parquet", default-features = false }
-parquet-geospatial = { version = "58.0.0", path = "./parquet-geospatial" }
-parquet-variant = { version = "58.0.0", path = "./parquet-variant" }
-parquet-variant-json = { version = "58.0.0", path = "./parquet-variant-json" }
-parquet-variant-compute = { version = "58.0.0", path = "./parquet-variant-compute" }
+arrow = { version = "58.1.0", path = "./arrow", default-features = false }
+arrow-arith = { version = "58.1.0", path = "./arrow-arith" }
+arrow-array = { version = "58.1.0", path = "./arrow-array" }
+arrow-buffer = { version = "58.1.0", path = "./arrow-buffer" }
+arrow-cast = { version = "58.1.0", path = "./arrow-cast" }
+arrow-csv = { version = "58.1.0", path = "./arrow-csv" }
+arrow-data = { version = "58.1.0", path = "./arrow-data" }
+arrow-ipc = { version = "58.1.0", path = "./arrow-ipc" }
+arrow-json = { version = "58.1.0", path = "./arrow-json" }
+arrow-ord = { version = "58.1.0", path = "./arrow-ord" }
+arrow-pyarrow = { version = "58.1.0", path = "./arrow-pyarrow" }
+arrow-row = { version = "58.1.0", path = "./arrow-row" }
+arrow-schema = { version = "58.1.0", path = "./arrow-schema" }
+arrow-select = { version = "58.1.0", path = "./arrow-select" }
+arrow-string = { version = "58.1.0", path = "./arrow-string" }
+parquet = { version = "58.1.0", path = "./parquet", default-features = false }
+parquet-geospatial = { version = "58.1.0", path = "./parquet-geospatial" }
+parquet-variant = { version = "58.1.0", path = "./parquet-variant" }
+parquet-variant-json = { version = "58.1.0", path = "./parquet-variant-json" }
+parquet-variant-compute = { version = "58.1.0", path = "./parquet-variant-compute" }
 
 chrono = { version = "0.4.40", default-features = false, features = ["clock"] }
 
-simdutf8 = { version = "0.1.5", default-features = false }
-
 criterion = { version = "0.8.0", default-features = false }
 
 insta = { version = "1.46.3", default-features = false }
 
+object_store = { version = "0.13.2", default-features = false }
+
+simdutf8 = { version = "0.1.5", default-features = false }
+
 # release inherited profile keeping debug information and symbols
 # for mem/cpu profiling
 [profile.profiling]

arrow-avro/Cargo.toml

@@ -56,7 +56,7 @@ arrow-buffer = { workspace = true }
 arrow-array = { workspace = true }
 arrow-select = { workspace = true, optional = true }
 
-object_store = { version = "0.13", default-features = false, optional = true }
+object_store = { workspace = true, optional = true }
 
 bytes = { version = "1.11.0", default-features = false, features = ["std"] }
 serde_json = { version = "1.0", default-features = false, features = ["std"] }
@@ -75,7 +75,7 @@ uuid = "1.17"
 indexmap = "2.10"
 rand = "0.9"
 md5 = { version = "0.8", optional = true }
-sha2 = { version = "0.10", optional = true }
+sha2 = { version = "0.11", optional = true }
 tokio = { version = "1.0", optional = true, default-features = false, features = ["macros", "rt", "io-util"] }
 
 [dev-dependencies]
@@ -93,7 +93,7 @@ futures = "0.3.31"
 async-stream = "0.3.6"
 apache-avro = "0.21.0"
 num-bigint = "0.4"
-object_store = { version = "0.13", default-features = false, features = ["fs"] }
+object_store = { workspace = true, features = ["fs"] }
 once_cell = "1.21.3"
 half = { version = "2.1", default-features = false }
 tokio = { version = "1.0", default-features = false, features = ["macros", "rt-multi-thread", "io-util", "fs"] }

arrow-buffer/src/buffer/mutable.rs

@@ -450,7 +450,13 @@ impl MutableBuffer {
 
     /// Clear all existing data from this buffer.
     pub fn clear(&mut self) {
-        self.len = 0
+        self.len = 0;
+        #[cfg(feature = "pool")]
+        {
+            if let Some(reservation) = self.reservation.lock().unwrap().as_mut() {
+                reservation.resize(self.len);
+            }
+        }
     }
 
     /// Returns the data stored in this buffer as a slice.
@@ -1371,7 +1377,7 @@ mod tests {
             assert_eq!(pool.used(), 40);
 
             // Truncate to zero
-            buffer.truncate(0);
+            buffer.clear();
             assert_eq!(buffer.len(), 0);
             assert_eq!(pool.used(), 0);
         }

arrow-cast/src/display.rs

@@ -80,6 +80,8 @@ pub struct FormatOptions<'a> {
     duration_format: DurationFormat,
     /// Show types in visual representation batches
     types_info: bool,
+    /// Whether string values should be quoted
+    quoted_strings: bool,
     /// Formatter factory used to instantiate custom [`ArrayFormatter`]s. This allows users to
     /// provide custom formatters.
     formatter_factory: Option<&'a dyn ArrayFormatterFactory>,
@@ -102,6 +104,7 @@ impl PartialEq for FormatOptions<'_> {
             && self.time_format == other.time_format
             && self.duration_format == other.duration_format
             && self.types_info == other.types_info
+            && self.quoted_strings == other.quoted_strings
             && match (self.formatter_factory, other.formatter_factory) {
                 (Some(f1), Some(f2)) => std::ptr::eq(f1, f2),
                 (None, None) => true,
@@ -123,6 +126,7 @@ impl Hash for FormatOptions<'_> {
         self.time_format.hash(state);
         self.duration_format.hash(state);
         self.types_info.hash(state);
+        self.quoted_strings.hash(state);
         self.formatter_factory
             .map(|f| f as *const dyn ArrayFormatterFactory)
             .hash(state);
@@ -142,6 +146,7 @@ impl<'a> FormatOptions<'a> {
             time_format: None,
             duration_format: DurationFormat::ISO8601,
             types_info: false,
+            quoted_strings: false,
             formatter_factory: None,
         }
     }
@@ -217,6 +222,17 @@ impl<'a> FormatOptions<'a> {
         Self { types_info, ..self }
     }
 
+    /// Sets whether string values should be quoted
+    ///
+    /// When `true`, strings are formatted using [`Debug`]-style with double quotes and escaping.
+    /// Defaults to `false`
+    pub const fn with_quoted_strings(self, quoted_strings: bool) -> Self {
+        Self {
+            quoted_strings,
+            ..self
+        }
+    }
+
     /// Overrides the [`ArrayFormatterFactory`] used to instantiate custom [`ArrayFormatter`]s.
     ///
     /// Using [`None`] causes pretty-printers to use the default [`ArrayFormatter`]s.
@@ -276,6 +292,11 @@ impl<'a> FormatOptions<'a> {
         self.types_info
     }
 
+    /// Returns whether string values should be quoted.
+    pub const fn quoted_strings(&self) -> bool {
+        self.quoted_strings
+    }
+
     /// Returns the [`ArrayFormatterFactory`] used to instantiate custom [`ArrayFormatter`]s.
     pub const fn formatter_factory(&self) -> Option<&'a dyn ArrayFormatterFactory> {
         self.formatter_factory
@@ -1081,16 +1102,38 @@ impl Display for MillisecondsFormatter<'_> {
     }
 }
 
-impl<O: OffsetSizeTrait> DisplayIndex for &GenericStringArray<O> {
-    fn write(&self, idx: usize, f: &mut dyn Write) -> FormatResult {
-        write!(f, "{}", self.value(idx))?;
+impl<'a, O: OffsetSizeTrait> DisplayIndexState<'a> for &'a GenericStringArray<O> {
+    type State = bool;
+
+    fn prepare(&self, options: &FormatOptions<'a>) -> Result<Self::State, ArrowError> {
+        Ok(options.quoted_strings())
+    }
+
+    fn write(&self, state: &Self::State, idx: usize, f: &mut dyn Write) -> FormatResult {
+        let value = self.value(idx);
+        if *state {
+            write!(f, "{:?}", value)?;
+        } else {
+            write!(f, "{}", value)?;
+        }
         Ok(())
     }
 }
 
-impl DisplayIndex for &StringViewArray {
-    fn write(&self, idx: usize, f: &mut dyn Write) -> FormatResult {
-        write!(f, "{}", self.value(idx))?;
+impl<'a> DisplayIndexState<'a> for &'a StringViewArray {
+    type State = bool;
+
+    fn prepare(&self, options: &FormatOptions<'a>) -> Result<Self::State, ArrowError> {
+        Ok(options.quoted_strings())
+    }
+
+    fn write(&self, state: &Self::State, idx: usize, f: &mut dyn Write) -> FormatResult {
+        let value = self.value(idx);
+        if *state {
+            write!(f, "{:?}", value)?;
+        } else {
+            write!(f, "{}", value)?;
+        }
         Ok(())
     }
 }

arrow-cast/src/pretty.rs

@@ -1665,4 +1665,158 @@ mod tests {
             .unwrap();
         insta::assert_snapshot!(error, @"Invalid argument error: Expected the same number of columns in a record batch (1) as the number of fields (2) in the schema");
     }
+
+    #[test]
+    fn test_quoted_strings() {
+        let schema = Arc::new(Schema::new(vec![Field::new(
+            "strings",
+            DataType::Utf8,
+            true,
+        )]));
+
+        let string_array = StringArray::from(vec![
+            Some("hello"),
+            Some("world"),
+            Some(""),
+            Some("tab\there"),
+            Some("newline\ntest"),
+            Some("quote\"test"),
+            Some("backslash\\test"),
+            None,
+        ]);
+
+        let batch = RecordBatch::try_new(schema.clone(), vec![Arc::new(string_array)]).unwrap();
+
+        let options_none = FormatOptions::new().with_null("NULL");
+        let table = pretty_format_batches_with_options(std::slice::from_ref(&batch), &options_none)
+            .unwrap()
+            .to_string();
+
+        insta::assert_snapshot!(table, @"
+        +----------------+
+        | strings        |
+        +----------------+
+        | hello          |
+        | world          |
+        |                |
+        | tab	here       |
+        | newline        |
+        | test           |
+        | quote\"test     |
+        | backslash\\test |
+        | NULL           |
+        +----------------+
+        ");
+
+        let options_quoted = FormatOptions::new()
+            .with_null("NULL")
+            .with_quoted_strings(true);
+
+        let table = pretty_format_batches_with_options(&[batch], &options_quoted)
+            .unwrap()
+            .to_string();
+
+        insta::assert_snapshot!(table, @r#"
+        +-------------------+
+        | strings           |
+        +-------------------+
+        | "hello"           |
+        | "world"           |
+        | ""                |
+        | "tab\there"       |
+        | "newline\ntest"   |
+        | "quote\"test"     |
+        | "backslash\\test" |
+        | NULL              |
+        +-------------------+
+        "#);
+    }
+
+    #[test]
+    fn test_string_view_quoted() {
+        let schema = Arc::new(Schema::new(vec![Field::new(
+            "view_strings",
+            DataType::Utf8View,
+            true,
+        )]));
+
+        let mut builder = StringViewBuilder::new();
+        builder.append_value("hello");
+        builder.append_null();
+        builder.append_value("quote\"test");
+
+        let array: ArrayRef = Arc::new(builder.finish());
+        let batch = RecordBatch::try_new(schema, vec![array]).unwrap();
+
+        let options = FormatOptions::new().with_quoted_strings(true);
+
+        let table = pretty_format_batches_with_options(&[batch], &options)
+            .unwrap()
+            .to_string();
+
+        insta::assert_snapshot!(table, @"
+        +---------------+
+        | view_strings  |
+        +---------------+
+        | \"hello\"       |
+        |               |
+        | \"quote\\\"test\" |
+        +---------------+
+        ");
+    }
+
+    #[test]
+    fn test_quoted_strings_in_struct() {
+        let string_builder = StringBuilder::new();
+        let mut name_builder = string_builder;
+        name_builder.append_value("Alice");
+        name_builder.append_value("");
+        name_builder.append_value("Bob");
+
+        let fields = vec![Field::new("name", DataType::Utf8, false)];
+        let mut struct_builder = StructBuilder::new(fields, vec![Box::new(name_builder)]);
+        struct_builder.append(true);
+        struct_builder.append(true);
+        struct_builder.append(true);
+
+        let struct_array = struct_builder.finish();
+
+        let schema = Arc::new(Schema::new(vec![Field::new(
+            "person",
+            struct_array.data_type().clone(),
+            false,
+        )]));
+
+        let batch = RecordBatch::try_new(schema, vec![Arc::new(struct_array)]).unwrap();
+
+        let options_none = FormatOptions::new();
+        let table = pretty_format_batches_with_options(std::slice::from_ref(&batch), &options_none)
+            .unwrap()
+            .to_string();
+
+        insta::assert_snapshot!(table, @"
+        +---------------+
+        | person        |
+        +---------------+
+        | {name: Alice} |
+        | {name: }      |
+        | {name: Bob}   |
+        +---------------+
+        ");
+
+        let options_quoted = FormatOptions::new().with_quoted_strings(true);
+        let table = pretty_format_batches_with_options(&[batch], &options_quoted)
+            .unwrap()
+            .to_string();
+
+        insta::assert_snapshot!(table, @"
+        +-----------------+
+        | person          |
+        +-----------------+
+        | {name: \"Alice\"} |
+        | {name: \"\"}      |
+        | {name: \"Bob\"}   |
+        +-----------------+
+        ");
+    }
 }

arrow-data/src/transform/mod.rs

@@ -813,8 +813,8 @@ impl<'a> MutableArrayData<'a> {
         };
 
         let nulls = match data.data_type {
-            // RunEndEncoded and Null arrays cannot have top-level null bitmasks
-            DataType::RunEndEncoded(_, _) | DataType::Null => None,
+            // RunEndEncoded, Null, and Union arrays cannot have top-level null bitmasks
+            DataType::RunEndEncoded(_, _) | DataType::Null | DataType::Union(_, _) => None,
             _ => data
                 .null_buffer
                 .map(|nulls| {