Simpler Transaction Filtering

rust/Cargo.toml

@@ -1,7 +1,7 @@
 [workspace]
 resolver = "2"
 
-members = ["indexer-metrics", "moving-average", "processor", "server-framework"]
+members = ["indexer-metrics", "moving-average", "processor", "server-framework", "transaction-filter"]
 
 [workspace.package]
 authors = ["Aptos Labs <[email protected]>"]
@@ -67,6 +67,8 @@ jemallocator = { version = "0.5.0", features = [
 ] }
 kanal = { version = "0.1.0-pre8", features = ["async"] }
 once_cell = "1.10.0"
+# SIMD for string search
+memchr = "2.7.2"
 num_cpus = "1.16.0"
 pbjson = "0.5.1"
 prometheus = { version = "0.13.0", default-features = false }
@@ -86,6 +88,7 @@ sha2 = "0.9.3"
 sha3 = "0.9.1"
 strum = { version = "0.24.1", features = ["derive"] }
 tempfile = "3.3.0"
+thiserror = "1.0.61"
 toml = "0.7.4"
 tracing-subscriber = { version = "0.3.17", features = ["json", "env-filter"] }
 tokio = { version = "1.35.1", features = ["full"] }

rust/processor/src/utils/util.rs

@@ -53,8 +53,11 @@ pub struct MultisigPayloadClean {
 }
 
 /// Standardizes all addresses and table handles to be length 66 (0x-64 length hash)
+#[inline]
 pub fn standardize_address(handle: &str) -> String {
-    if let Some(handle) = handle.strip_prefix("0x") {
+    if handle.len() == 66 {
+        handle.to_string()
+    } else if let Some(handle) = handle.strip_prefix("0x") {
         format!("0x{:0>64}", handle)
     } else {
         format!("0x{:0>64}", handle)

rust/transaction-filter/Cargo.toml

@@ -0,0 +1,32 @@
+[package]
+name = "transaction-filter"
+version = "0.1.0"
+
+# Workspace inherited keys
+authors = { workspace = true }
+edition = { workspace = true }
+homepage = { workspace = true }
+license = { workspace = true }
+publish = { workspace = true }
+repository = { workspace = true }
+rust-version = { workspace = true }
+# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
+
+[dependencies]
+anyhow = { workspace = true }
+aptos-protos = { workspace = true }
+
+# SIMD for string search. TODO: benchmark this on various real inputs to see if it's worth it
+memchr = { workspace = true }
+
+prost = { workspace = true }
+
+serde = { workspace = true }
+serde_json = { workspace = true }
+
+thiserror = { workspace = true }
+
+[dev-dependencies]
+# we only decompress the fixture protos in tests
+lz4 = "1.24.0"
+