Merge remote-tracking branch 'up/main' into tracing

Author: forsaken628

.github/workflows/links.yml

@@ -22,15 +22,19 @@ jobs:
 
       - name: Link Checker
         id: lychee
-        uses: lycheeverse/lychee-action@v1.8.0
+        uses: lycheeverse/lychee-action@v2.8.0
         with:
           args: >-
-            --base .
+            --accept 100..=103,200..=299,429
             --cache
             --max-cache-age 1d .
+            --exclude-all-private
             --exclude 'https://github\.com/datafuselabs/databend/issues/.*'
             --exclude 'https?://github\.com/databendlabs/databend/issues/.*'
             --exclude 'https?://twitter\.com(?:/.*$)?$'
+            --exclude-path './src/query/ast/tests/it/testdata/'
+            --exclude-path './src/query/service/tests/it/storages/testdata/'
+
       - name: Save lychee cache
         uses: actions/cache/save@v3
         if: always()

Cargo.lock

@@ -246,7 +246,7 @@ derive-visitor = { version = "0.4.0", features = ["std-types-drive"] }
 derive_more = { version = "1.0.0", features = ["full"] }
 display-more = { version = "0.2.1" }
 divan = "0.1.21"
-dtparse = { git = "https://github.com/datafuse-extras/dtparse.git", rev = "30e28ca" }
+dtparse = { git = "https://github.com/datafuse-extras/dtparse.git", rev = "7a9e40f" }
 dyn-clone = "1.0.9"
 educe = { version = "1.0.0", features = ["default", "full"], package = "databend_educe" }
 either = "1.9"
@@ -497,6 +497,7 @@ volo-thrift = "0.10"
 walkdir = "2.3.2"
 wiremock = "0.6"
 wkt = "0.14.0"
+xorf = "0.12.0"
 xorfilter-rs = { version = "0.5", features = ["cbordata"] }
 zerocopy = { version = "0.8.26", features = ["derive"] }
 zip = "3.0.0"

Cargo.toml

@@ -48,12 +48,12 @@ where K: Eq + Hash
 impl<K, V> TtlHashMap<K, V>
 where K: Eq + Hash
 {
-    /// Create `TtlHashMap` with time-to-leval, `CleanPolicy::ReadModify` will be take for this initialization
+    /// Create `TtlHashMap` with time-to-live, `CleanPolicy::ReadModify` will be take for this initialization
     pub fn new(ttl: Duration) -> Self {
         Self::new_with_clean_policy(ttl, CleanPolicy::ReadModify)
     }
 
-    /// Create `TtlHashMap` with time-to-leval and `CleanPolicy`
+    /// Create `TtlHashMap` with time-to-live and `CleanPolicy`
     pub fn new_with_clean_policy(ttl: Duration, clean_policy: CleanPolicy) -> Self {
         TtlHashMap {
             map: HashMap::new(),

src/common/base/src/containers/ttlhmap.rs

@@ -23,6 +23,7 @@ pub const NAN_BYTES_SNAKE: &str = "NaN";
 pub const NAN_BYTES_LOWER: &str = "nan";
 pub const INF_BYTES_LOWER: &str = "inf";
 pub const INF_BYTES_LONG: &str = "Infinity";
+pub const NEG_INF_BYTES_LONG: &str = "-Infinity";
 
 // The size of the I/O read/write block buffer by default.
 pub const DEFAULT_BLOCK_BUFFER_SIZE: usize = 125 * 1024 * 1024;

src/common/io/src/constants.rs

@@ -88,6 +88,32 @@ setting binary_output_format to 'UTF-8-LOSSY'."
     }
 }
 
+#[derive(Debug, Clone, Copy, PartialEq, Eq, Default)]
+pub enum HttpHandlerDataFormat {
+    #[default]
+    Display,
+    Driver,
+}
+
+impl HttpHandlerDataFormat {
+    pub fn parse(s: &str) -> Result<Self, ErrorCode> {
+        match s.to_ascii_lowercase().as_str() {
+            "display" => Ok(HttpHandlerDataFormat::Display),
+            "driver" => Ok(HttpHandlerDataFormat::Driver),
+            other => Err(ErrorCode::InvalidArgument(format!(
+                "Invalid http json result mode '{other}', valid values: DISPLAY | DRIVER"
+            ))),
+        }
+    }
+
+    pub fn as_str(&self) -> &'static str {
+        match self {
+            HttpHandlerDataFormat::Display => "display",
+            HttpHandlerDataFormat::Driver => "driver",
+        }
+    }
+}
+
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct InputFormatSettings {
     pub jiff_timezone: TimeZone,
@@ -116,6 +142,7 @@ pub struct OutputFormatSettings {
     pub jiff_timezone: TimeZone,
     pub geometry_format: GeometryDataType,
     pub binary_format: BinaryDisplayFormat,
+    pub http_json_result_mode: HttpHandlerDataFormat,
 
     // used only in http handler response
     pub format_null_as_str: bool,
@@ -127,6 +154,7 @@ impl Default for OutputFormatSettings {
             jiff_timezone: TimeZone::UTC,
             geometry_format: GeometryDataType::default(),
             binary_format: BinaryDisplayFormat::Hex,
+            http_json_result_mode: HttpHandlerDataFormat::Display,
             format_null_as_str: false,
         }
     }

src/common/io/src/format_settings.rs

@@ -21,6 +21,7 @@ pub use crate::binary_write::put_uvarint;
 pub use crate::bincode_serialization::*;
 pub use crate::borsh_serialization::*;
 pub use crate::format_settings::BinaryDisplayFormat;
+pub use crate::format_settings::HttpHandlerDataFormat;
 pub use crate::format_settings::InputFormatSettings;
 pub use crate::format_settings::OutputFormatSettings;
 pub use crate::position::*;

src/common/io/src/prelude.rs

@@ -15,6 +15,7 @@ enum-as-inner = { workspace = true }
 ethnum = { workspace = true }
 fast-float2 = { workspace = true }
 fastrace = { workspace = true }
+hex = { workspace = true }
 indent = { workspace = true }
 itertools = { workspace = true }
 logos = { workspace = true }

src/query/ast/Cargo.toml

@@ -1029,6 +1029,7 @@ pub enum Literal {
     },
     // Quoted string literal value
     String(String),
+    Binary(Vec<u8>),
     Boolean(bool),
     Null,
 }
@@ -1077,6 +1078,9 @@ impl Display for Literal {
             Literal::String(val) => {
                 write!(f, "{}", QuotedString(val, '\''))
             }
+            Literal::Binary(val) => {
+                write!(f, "X'{}'", hex::encode_upper(val))
+            }
             Literal::Boolean(val) => {
                 if *val {
                     write!(f, "TRUE")

src/query/ast/src/ast/expr.rs

@@ -183,6 +183,23 @@ impl From<ParseIntError> for ErrorKind {
     }
 }
 
+impl From<hex::FromHexError> for ErrorKind {
+    fn from(err: hex::FromHexError) -> Self {
+        let msg = match err {
+            hex::FromHexError::InvalidHexCharacter { .. } => {
+                "unable to parse hex literal because it contains invalid characters"
+            }
+            hex::FromHexError::OddLength => {
+                "unable to parse hex literal because it has an odd number of digits"
+            }
+            hex::FromHexError::InvalidStringLength => {
+                "unable to parse hex literal because it has an invalid length"
+            }
+        };
+        ErrorKind::Other(msg)
+    }
+}
+
 /// Suggests corrections using intelligent syntax pattern matching
 fn suggest_keyword_correction(
     _span_text: &str,