feat(data-pipeline)!: CSS Trace Filters

.gitignore

@@ -32,3 +32,4 @@ examples/cxx/exporter_manager.exe
 examples/cxx/profiling
 examples/cxx/profiling.exe
 profile.pprof
+*.snap.new

LICENSE-3rdparty.csv

@@ -85,6 +85,7 @@ colorchoice,https://github.com/rust-cli/anstyle,MIT OR Apache-2.0,The colorchoic
 colored,https://github.com/mackwic/colored,MPL-2.0,Thomas Wickham <mackwic@gmail.com>
 combine,https://github.com/Marwes/combine,MIT,Markus Westerlind <marwes91@gmail.com>
 concurrent-queue,https://github.com/smol-rs/concurrent-queue,Apache-2.0 OR MIT,"Stjepan Glavina <stjepang@gmail.com>, Taiki Endo <te316e89@gmail.com>, John Nunley <dev@notgull.net>"
+console,https://github.com/console-rs/console,MIT,The console Authors
 console-api,https://github.com/tokio-rs/console,MIT,"Eliza Weisman <eliza@buoyant.io>, Tokio Contributors <team@tokio.rs>"
 console-subscriber,https://github.com/tokio-rs/console,MIT,"Eliza Weisman <eliza@buoyant.io>, Tokio Contributors <team@tokio.rs>"
 const_format,https://github.com/rodrimati1992/const_format_crates,Zlib,rodrimati1992 <rodrimatt1985@gmail.com>
@@ -125,6 +126,7 @@ dispatch2,https://github.com/madsmtm/objc2,Zlib OR Apache-2.0 OR MIT,"Mads Marqu
 displaydoc,https://github.com/yaahc/displaydoc,MIT OR Apache-2.0,Jane Lusby <jlusby@yaah.dev>
 dyn-clone,https://github.com/dtolnay/dyn-clone,MIT OR Apache-2.0,David Tolnay <dtolnay@gmail.com>
 either,https://github.com/rayon-rs/either,MIT OR Apache-2.0,bluss
+encode_unicode,https://github.com/tormol/encode_unicode,Apache-2.0 OR MIT,Torbjørn Birch Moltu <t.b.moltu@lyse.net>
 encoding_rs,https://github.com/hsivonen/encoding_rs,(Apache-2.0 OR MIT) AND BSD-3-Clause,Henri Sivonen <hsivonen@hsivonen.fi>
 enum-as-inner,https://github.com/bluejekyll/enum-as-inner,MIT OR Apache-2.0,Benjamin Fry <benjaminfry@me.com>
 equivalent,https://github.com/cuviper/equivalent,Apache-2.0 OR MIT,The equivalent Authors
@@ -282,6 +284,10 @@ parking_lot_core,https://github.com/Amanieu/parking_lot,MIT OR Apache-2.0,Amanie
 paste,https://github.com/dtolnay/paste,MIT OR Apache-2.0,David Tolnay <dtolnay@gmail.com>
 path-tree,https://github.com/viz-rs/path-tree,MIT OR Apache-2.0,Fangdun Tsai <cfddream@gmail.com>
 percent-encoding,https://github.com/servo/rust-url,MIT OR Apache-2.0,The rust-url developers
+pest,https://github.com/pest-parser/pest,MIT OR Apache-2.0,Dragoș Tiselice <dragostiselice@gmail.com>
+pest_derive,https://github.com/pest-parser/pest,MIT OR Apache-2.0,Dragoș Tiselice <dragostiselice@gmail.com>
+pest_generator,https://github.com/pest-parser/pest,MIT OR Apache-2.0,Dragoș Tiselice <dragostiselice@gmail.com>
+pest_meta,https://github.com/pest-parser/pest,MIT OR Apache-2.0,Dragoș Tiselice <dragostiselice@gmail.com>
 petgraph,https://github.com/petgraph/petgraph,MIT OR Apache-2.0,"bluss, mitchmindtree"
 pico-args,https://github.com/RazrFalcon/pico-args,MIT,Yevhenii Reizner <razrfalcon@gmail.com>
 pin-project,https://github.com/taiki-e/pin-project,Apache-2.0 OR MIT,The pin-project Authors
@@ -464,6 +470,7 @@ try-lock,https://github.com/seanmonstar/try-lock,MIT,Sean McArthur <sean@seanmon
 twox-hash,https://github.com/shepmaster/twox-hash,MIT,Jake Goulding <jake.goulding@gmail.com>
 typeid,https://github.com/dtolnay/typeid,MIT OR Apache-2.0,David Tolnay <dtolnay@gmail.com>
 typenum,https://github.com/paholg/typenum,MIT OR Apache-2.0,"Paho Lurie-Gregg <paho@paholg.com>, Andre Bogus <bogusandre@gmail.com>"
+ucd-trie,https://github.com/BurntSushi/ucd-generate,MIT OR Apache-2.0,Andrew Gallant <jamslam@gmail.com>
 unarray,https://github.com/cameron1024/unarray,MIT OR Apache-2.0,The unarray Authors
 unicase,https://github.com/seanmonstar/unicase,MIT OR Apache-2.0,Sean McArthur <sean@seanmonstar.com>
 unicode-ident,https://github.com/dtolnay/unicode-ident,(MIT OR Apache-2.0) AND Unicode-DFS-2016,David Tolnay <dtolnay@gmail.com>

libdd-common/src/regex_engine.rs

@@ -13,7 +13,7 @@
 //! regexes requiring Unicode character class support.
 
 #[cfg(all(feature = "regex-lite", not(feature = "require-regex-full")))]
-pub use regex_lite::{escape, Captures, Regex, RegexBuilder, Replacer};
+pub use regex_lite::{escape, Captures, Error, Regex, RegexBuilder, Replacer};
 
 #[cfg(not(all(feature = "regex-lite", not(feature = "require-regex-full"))))]
-pub use regex::{escape, Captures, Regex, RegexBuilder, Replacer};
+pub use regex::{escape, Captures, Error, Regex, RegexBuilder, Replacer};

libdd-data-pipeline/Cargo.toml

@@ -80,6 +80,7 @@ tokio = { version = "1.23", features = [
     "time",
     "test-util",
 ], default-features = false }
+insta = { version = "1.47.2", features = ["json", "redactions"] }
 
 [features]
 default = ["https", "telemetry"]

libdd-data-pipeline/src/agent_info/schema.rs

@@ -40,20 +40,25 @@ pub struct AgentInfoStruct {
     /// Container tags hash from HTTP response header
     pub container_tags_hash: Option<String>,
     /// Exact-match tag filters applied before stats computation (root span only).
-    pub filter_tags: Option<FilterTagsConfig>,
+    #[serde(default)]
+    pub filter_tags: FilterTagsConfig,
     /// Regex-match tag filters applied before stats computation (root span only).
-    pub filter_tags_regex: Option<FilterTagsConfig>,
+    #[serde(default)]
+    pub filter_tags_regex: FilterTagsConfig,
     /// Regex patterns for root-span resource names; matching traces are excluded from stats.
-    pub ignore_resources: Option<Vec<String>>,
+    #[serde(default)]
+    pub ignore_resources: Vec<String>,
 }
 
 /// Require/reject lists for tag-based trace filters exposed by the agent /info endpoint.
 #[derive(Clone, Serialize, Deserialize, Default, Debug, PartialEq)]
 pub struct FilterTagsConfig {
     /// All listed filters must match at least one root-span tag for the trace to be accepted.
-    pub require: Option<Vec<String>>,
+    #[serde(default)]
+    pub require: Vec<String>,
     /// If any listed filter matches a root-span tag the trace is rejected.
-    pub reject: Option<Vec<String>>,
+    #[serde(default)]
+    pub reject: Vec<String>,
 }
 
 #[allow(missing_docs)]

libdd-data-pipeline/src/trace_exporter/builder.rs

@@ -1,13 +1,15 @@
 // Copyright 2024-Present Datadog, Inc. https://www.datadoghq.com/
 // SPDX-License-Identifier: Apache-2.0
 
+use crate::agent_info::schema::FilterTagsConfig;
 use crate::agent_info::AgentInfoFetcher;
 use crate::otlp::config::{OtlpProtocol, DEFAULT_OTLP_TIMEOUT};
 use crate::otlp::OtlpTraceConfig;
 #[cfg(all(not(target_arch = "wasm32"), feature = "telemetry"))]
 use crate::telemetry::TelemetryClientBuilder;
 use crate::trace_exporter::agent_response::AgentResponsePayloadVersion;
 use crate::trace_exporter::error::BuilderErrorKind;
+use crate::trace_exporter::trace_filter::TraceFilterer;
 #[cfg(all(not(target_arch = "wasm32"), feature = "telemetry"))]
 use crate::trace_exporter::TelemetryConfig;
 #[cfg(not(target_arch = "wasm32"))]
@@ -65,6 +67,9 @@ pub struct TraceExporterBuilder {
     connection_timeout: Option<u64>,
     otlp_endpoint: Option<String>,
     otlp_headers: Vec<(String, String)>,
+    filter_tags: FilterTagsConfig,
+    filter_tags_regex: FilterTagsConfig,
+    ignore_resources: Vec<String>,
 }
 
 impl TraceExporterBuilder {
@@ -286,6 +291,24 @@ impl TraceExporterBuilder {
         self
     }
 
+    // TODO: doc
+    pub fn set_filter_tags(&mut self, filter_tags: FilterTagsConfig) -> &mut Self {
+        self.filter_tags = filter_tags;
+        self
+    }
+
+    // TODO: doc
+    pub fn set_filter_tags_regex(&mut self, filter_tags_regex: FilterTagsConfig) -> &mut Self {
+        self.filter_tags_regex = filter_tags_regex;
+        self
+    }
+
+    // TODO: doc
+    pub fn set_ignore_resources(&mut self, ignore_resources: Vec<String>) -> &mut Self {
+        self.ignore_resources = ignore_resources;
+        self
+    }
+
     #[allow(missing_docs)]
     pub fn build<C: HttpClientCapability + SleepCapability + MaybeSend + Sync + 'static>(
         self,
@@ -496,6 +519,11 @@ impl TraceExporterBuilder {
                 .agent_rates_payload_version_enabled
                 .then(AgentResponsePayloadVersion::new),
             otlp_config,
+            trace_filterer: TraceFilterer::new(
+                &self.filter_tags,
+                &self.filter_tags_regex,
+                &self.ignore_resources,
+            ),
         })
     }