mnemonic-hash-checker: move from postgres to bloom filter

mnemonic-hash-checker/Cargo.lock

@@ -130,10 +130,10 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9e1b586273c5702936fe7b7d6896644d8be71e6314cfe09d3167c95f712589e8"
 
 [[package]]
-name = "base64"
+name = "bit-vec"
-version = "0.21.2"
+version = "0.6.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "604178f6c5c21f02dc555784810edfb88d34ac2c73b2eae109655649ee73ce3d"
+checksum = "349f9b6a179ed607305526ca489b34ad0a41aed5f7980fa90eb03160b69598fb"
 
 [[package]]
 name = "bitflags"
@@ -157,10 +157,15 @@ dependencies = [
 ]
 
 [[package]]
-name = "byteorder"
+name = "bloomfilter"
-version = "1.4.3"
+version = "1.0.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "14c189c53d098945499cdfa7ecc63567cf3886b3332b312a5b4585d8d3a6a610"
+checksum = "8129c0ab340c1b0caf6dbc587e814d04ba811e336dcf8fc268c04e047428ebb0"
+dependencies = [
+ "bit-vec",
+ "getrandom",
+ "siphasher",
+]
 
 [[package]]
 name = "bytes"
@@ -266,40 +271,6 @@ dependencies = [
  "typenum",
 ]
 
-[[package]]
-name = "deadpool"
-version = "0.9.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "421fe0f90f2ab22016f32a9881be5134fdd71c65298917084b0c7477cbc3856e"
-dependencies = [
- "async-trait",
- "deadpool-runtime",
- "num_cpus",
- "retain_mut",
- "tokio",
-]
-
-[[package]]
-name = "deadpool-postgres"
-version = "0.10.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "836a24a9d49deefe610b8b60c767a7412e9a931d79a89415cd2d2d71630ca8d7"
-dependencies = [
- "deadpool",
- "log",
- "tokio",
- "tokio-postgres",
-]
-
-[[package]]
-name = "deadpool-runtime"
-version = "0.1.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "eaa37046cc0f6c3cc6090fbdbf73ef0b8ef4cfcc37f6befc0020f63e8cf121e1"
-dependencies = [
- "tokio",
-]
-
 [[package]]
 name = "digest"
 version = "0.10.7"
@@ -308,7 +279,6 @@ checksum = "9ed9a281f7bc9b7576e61468ba615a66a5c8cfdff42420a70aa82701a3b1e292"
 dependencies = [
  "block-buffer",
  "crypto-common",
- "subtle",
 ]
 
 [[package]]
@@ -342,12 +312,6 @@ dependencies = [
  "once_cell",
 ]
 
-[[package]]
-name = "fallible-iterator"
-version = "0.2.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4443176a9f2c162692bd3d352d745ef9413eec5782a80d8fd6f8a1ac692a07f7"
-
 [[package]]
 name = "fnv"
 version = "1.0.7"
@@ -370,7 +334,6 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "955518d47e09b25bbebc7a18df10b81f0c766eaf4c4f1cccef2fca5f2a4fb5f2"
 dependencies = [
  "futures-core",
- "futures-sink",
 ]
 
 [[package]]
@@ -379,23 +342,6 @@ version = "0.3.28"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "4bca583b7e26f571124fe5b7561d49cb2868d79116cfa0eefce955557c6fee8c"
 
-[[package]]
-name = "futures-macro"
-version = "0.3.28"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "89ca545a94061b6365f2c7355b4b32bd20df3ff95f02da9329b34ccc3bd6ee72"
-dependencies = [
- "proc-macro2",
- "quote",
- "syn 2.0.28",
-]
-
-[[package]]
-name = "futures-sink"
-version = "0.3.28"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f43be4fe21a13b9781a69afa4985b0f6ee0e1afab2c6f454a8cf30e2b2237b6e"
-
 [[package]]
 name = "futures-task"
 version = "0.3.28"
@@ -409,8 +355,6 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "26b01e40b772d54cf6c6d721c1d1abd0647a0106a12ecaa1c186273392a69533"
 dependencies = [
  "futures-core",
- "futures-macro",
- "futures-sink",
  "futures-task",
  "pin-project-lite",
  "pin-utils",
@@ -450,7 +394,7 @@ version = "0.3.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f3e372db8e5c0d213e0cd0b9be18be2aca3d44cf2fe30a9d46a65581cd454584"
 dependencies = [
- "base64 0.13.1",
+ "base64",
  "bitflags 1.3.2",
  "bytes",
  "headers-core",
@@ -481,15 +425,6 @@ version = "0.3.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "443144c8cdadd93ebf52ddb4056d257f5b52c04d3c804e657d19eb73fc33668b"
 
-[[package]]
-name = "hmac"
-version = "0.12.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6c49c37c09c17a53d937dfbb742eb3a961d65a994e6bcdcf37e7399d0cc8ab5e"
-dependencies = [
- "digest",
-]
-
 [[package]]
 name = "http"
 version = "0.2.9"
@@ -546,7 +481,7 @@ dependencies = [
  "httpdate",
  "itoa",
  "pin-project-lite",
- "socket2 0.4.9",
+ "socket2",
  "tokio",
  "tower-service",
  "tracing",
@@ -625,15 +560,6 @@ version = "0.7.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ed1202b2a6f884ae56f04cff409ab315c5ce26b5e58d7412e484f01fd52f52ef"
 
-[[package]]
-name = "md-5"
-version = "0.10.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6365506850d44bff6e2fbcb5176cf63650e48bd45ef2fe2665ae1570e0f4b9ca"
-dependencies = [
- "digest",
-]
-
 [[package]]
 name = "memchr"
 version = "2.5.0"
@@ -671,12 +597,11 @@ name = "mnemonic-hash-checker"
 version = "0.1.0"
 dependencies = [
  "axum",
+ "bloomfilter",
  "clap",
  "color-eyre",
- "deadpool-postgres",
  "serde",
  "tokio",
- "tokio-postgres",
  "tower-http",
  "tracing",
  "tracing-error",
@@ -765,24 +690,6 @@ version = "2.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9b2a4787296e9989611394c33f193f676704af1686e70b8f8033ab5ba9a35a94"
 
-[[package]]
-name = "phf"
-version = "0.11.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ade2d8b8f33c7333b51bcf0428d37e217e9f32192ae4772156f65063b8ce03dc"
-dependencies = [
- "phf_shared",
-]
-
-[[package]]
-name = "phf_shared"
-version = "0.11.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "90fcb95eef784c2ac79119d1dd819e162b5da872ce6f3c3abe1e8ca1c082f72b"
-dependencies = [
- "siphasher",
-]
-
 [[package]]
 name = "pin-project"
 version = "1.1.3"
@@ -815,41 +722,6 @@ version = "0.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "8b870d8c151b6f2fb93e84a13146138f05d02ed11c7e7c54f8826aaaf7c9f184"
 
-[[package]]
-name = "postgres-protocol"
-version = "0.6.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "78b7fa9f396f51dffd61546fd8573ee20592287996568e6175ceb0f8699ad75d"
-dependencies = [
- "base64 0.21.2",
- "byteorder",
- "bytes",
- "fallible-iterator",
- "hmac",
- "md-5",
- "memchr",
- "rand",
- "sha2",
- "stringprep",
-]
-
-[[package]]
-name = "postgres-types"
-version = "0.2.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f028f05971fe20f512bcc679e2c10227e57809a3af86a7606304435bc8896cd6"
-dependencies = [
- "bytes",
- "fallible-iterator",
- "postgres-protocol",
-]
-
-[[package]]
-name = "ppv-lite86"
-version = "0.2.17"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5b40af805b3121feab8a3c29f04d8ad262fa8e0561883e7653e024ae4479e6de"
-
 [[package]]
 name = "proc-macro-error"
 version = "1.0.4"
@@ -892,36 +764,6 @@ dependencies = [
  "proc-macro2",
 ]
 
-[[package]]
-name = "rand"
-version = "0.8.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "34af8d1a0e25924bc5b7c43c079c942339d8f0a8b57c39049bef581b46327404"
-dependencies = [
- "libc",
- "rand_chacha",
- "rand_core",
-]
-
-[[package]]
-name = "rand_chacha"
-version = "0.3.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e6c10a63a0fa32252be49d21e7709d4d4baf8d231c2dbce1eaa8141b9b127d88"
-dependencies = [
- "ppv-lite86",
- "rand_core",
-]
-
-[[package]]
-name = "rand_core"
-version = "0.6.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ec0be4795e2f6a28069bec0b5ff3e2ac9bafc99e6a9a7dc3547996c5c816922c"
-dependencies = [
- "getrandom",
-]
-
 [[package]]
 name = "redox_syscall"
 version = "0.3.5"
@@ -975,12 +817,6 @@ version = "0.7.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e5ea92a5b6195c6ef2a0295ea818b312502c6fc94dde986c5553242e18fd4ce2"
 
-[[package]]
-name = "retain_mut"
-version = "0.1.9"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4389f1d5789befaf6029ebd9f7dac4af7f7e3d61b69d4f30e2ac02b57e7712b0"
-
 [[package]]
 name = "rustc-demangle"
 version = "0.1.23"
@@ -1082,17 +918,6 @@ dependencies = [
  "digest",
 ]
 
-[[package]]
-name = "sha2"
-version = "0.10.7"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "479fb9d862239e610720565ca91403019f2f00410f1864c5aa7479b950a76ed8"
-dependencies = [
- "cfg-if",
- "cpufeatures",
- "digest",
-]
-
 [[package]]
 name = "sharded-slab"
 version = "0.1.4"
@@ -1142,38 +967,12 @@ dependencies = [
  "winapi",
 ]
 
-[[package]]
-name = "socket2"
-version = "0.5.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2538b18701741680e0322a2302176d3253a35388e2e62f172f64f4f16605f877"
-dependencies = [
- "libc",
- "windows-sys",
-]
-
-[[package]]
-name = "stringprep"
-version = "0.1.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "db3737bde7edce97102e0e2b15365bf7a20bfdb5f60f4f9e8d7004258a51a8da"
-dependencies = [
- "unicode-bidi",
- "unicode-normalization",
-]
-
 [[package]]
 name = "strsim"
 version = "0.10.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "73473c0e59e6d5812c5dfe2a064a6444949f089e20eec9a2e5506596494e4623"
 
-[[package]]
-name = "subtle"
-version = "2.5.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "81cdd64d312baedb58e21336b31bc043b77e01cc99033ce76ef539f78e965ebc"
-
 [[package]]
 name = "syn"
 version = "1.0.109"
@@ -1221,21 +1020,6 @@ dependencies = [
  "once_cell",
 ]
 
-[[package]]
-name = "tinyvec"
-version = "1.6.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "87cc5ceb3875bb20c2890005a4e226a4651264a5c75edb2421b52861a0a0cb50"
-dependencies = [
- "tinyvec_macros",
-]
-
-[[package]]
-name = "tinyvec_macros"
-version = "0.1.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1f3ccbac311fea05f86f61904b462b55fb3df8837a366dfc601a0161d0532f20"
-
 [[package]]
 name = "tokio"
 version = "1.29.1"
@@ -1251,7 +1035,7 @@ dependencies = [
  "parking_lot",
  "pin-project-lite",
  "signal-hook-registry",
- "socket2 0.4.9",
+ "socket2",
  "tokio-macros",
  "tracing",
  "windows-sys",
@@ -1268,44 +1052,6 @@ dependencies = [
  "syn 2.0.28",
 ]
 
-[[package]]
-name = "tokio-postgres"
-version = "0.7.8"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6e89f6234aa8fd43779746012fcf53603cdb91fdd8399aa0de868c2d56b6dde1"
-dependencies = [
- "async-trait",
- "byteorder",
- "bytes",
- "fallible-iterator",
- "futures-channel",
- "futures-util",
- "log",
- "parking_lot",
- "percent-encoding",
- "phf",
- "pin-project-lite",
- "postgres-protocol",
- "postgres-types",
- "socket2 0.5.3",
- "tokio",
- "tokio-util",
-]
-
-[[package]]
-name = "tokio-util"
-version = "0.7.8"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "806fe8c2c87eccc8b3267cbae29ed3ab2d0bd37fca70ab622e46aaa9375ddb7d"
-dependencies = [
- "bytes",
- "futures-core",
- "futures-sink",
- "pin-project-lite",
- "tokio",
- "tracing",
-]
-
 [[package]]
 name = "tower"
 version = "0.4.13"
@@ -1451,27 +1197,12 @@ version = "1.16.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "497961ef93d974e23eb6f433eb5fe1b7930b659f06d12dec6fc44a8f554c0bba"
 
-[[package]]
-name = "unicode-bidi"
-version = "0.3.13"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "92888ba5573ff080736b3648696b70cafad7d250551175acbaa4e0385b3e1460"
-
 [[package]]
 name = "unicode-ident"
 version = "1.0.11"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "301abaae475aa91687eb82514b328ab47a211a533026cb25fc3e519b86adfc3c"
 
-[[package]]
-name = "unicode-normalization"
-version = "0.1.22"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5c5713f0fc4b5db668a2ac63cdb7bb4469d8c9fed047b1d0292cc7b0ce2ba921"
-dependencies = [
- "tinyvec",
-]
-
 [[package]]
 name = "valuable"
 version = "0.1.0"

mnemonic-hash-checker/Cargo.toml

@@ -7,12 +7,11 @@ edition = "2021"
 
 [dependencies]
 axum = { version = "0.6.20", features = ["headers", "macros", "tracing"] }
+bloomfilter = "1.0.9"
 clap = { version = "=4.0.32", features = ["derive", "env"] }
 color-eyre = "0.6.2"
-deadpool-postgres = "0.10.5"
 serde = { version = "1.0.181", features = ["serde_derive"] }
 tokio = { version = "1.29.1", features = ["full", "fs", "tracing"] }
-tokio-postgres = "0.7.8"
 tower-http = { version = "0.4.3", features = ["trace", "catch-panic"] }
 tracing = "0.1.37"
 tracing-error = "0.2.0"

mnemonic-hash-checker/src/bloom.rs

@@ -0,0 +1,43 @@
+use std::{fs::File, io::{BufReader, Read}, path::Path};
+
+use color_eyre::eyre::Result;
+use bloomfilter::Bloom;
+
+pub fn load(file: &Path) -> Result<Bloom<String>> {
+    let file = File::open(file)?;
+    let length = file.metadata().unwrap().len();
+
+    let mut buf = BufReader::new(file);
+
+    let mut num_bits: [u8; 8] = [0; 8];
+    buf.read_exact(&mut num_bits)?;
+
+    let mut num_hash_fun: [u8; 4] = [0; 4];
+    buf.read_exact(&mut num_hash_fun)?;
+
+    let mut sk00: [u8; 8] = [0; 8];
+    buf.read_exact(&mut sk00)?;
+    let mut sk01: [u8; 8] = [0; 8];
+    buf.read_exact(&mut sk01)?;
+    let mut sk10: [u8; 8] = [0; 8];
+    buf.read_exact(&mut sk10)?;
+    let mut sk11: [u8; 8] = [0; 8];
+    buf.read_exact(&mut sk11)?;
+
+    let number_of_bits: u64 = u64::from_be_bytes(num_bits);
+    let number_of_hash_functions: u32 = u32::from_be_bytes(num_hash_fun);
+    let sip_keys: [(u64, u64); 2] = [
+        (u64::from_be_bytes(sk00), (u64::from_be_bytes(sk01))),
+        (u64::from_be_bytes(sk10), (u64::from_be_bytes(sk11))),
+    ];
+
+    let mut bitmap = vec![0; (length - 8 - 4 - 32) as usize];
+    buf.read_exact(&mut bitmap)?;
+
+    Ok(Bloom::from_existing(
+        &bitmap,
+        number_of_bits,
+        number_of_hash_functions,
+        sip_keys,
+    ))
+}

mnemonic-hash-checker/src/main.rs

@@ -1,4 +1,5 @@
 use std::net::SocketAddr;
+use std::path::PathBuf;
 use std::sync::Arc;
 
 use axum::{
@@ -9,13 +10,12 @@ use axum::{
     Json, Router,
 };
 
+use bloomfilter::Bloom;
+
 use color_eyre::eyre::Result;
 
 use clap::Parser;
 
-use deadpool_postgres::{Config, ManagerConfig, Pool, RecyclingMethod, Runtime};
-use tokio_postgres::NoTls;
-
 use serde::Deserialize;
 
 use tower_http::catch_panic::CatchPanicLayer;
@@ -25,39 +25,21 @@ use tracing_subscriber::filter::{EnvFilter, LevelFilter};
 use tracing_subscriber::fmt::format::FmtSpan;
 use tracing_subscriber::prelude::*;
 
-use tracing::{debug, info};
+use tracing::info;
+
+mod bloom;
 
 #[derive(Parser)]
 struct CliConfig {
     #[clap(long, env)]
-    bind_address: Option<SocketAddr>,
+    bloom_filter_path: PathBuf,
-
-    #[clap(long, env, default_value = "postgres")]
-    postgres_dbname: String,
-
-    #[clap(long, env, default_value = "localhost")]
-    postgres_host: String,
 
     #[clap(long, env)]
-    postgres_password: String,
+    bind_address: Option<SocketAddr>,
-
-    #[clap(long, env, default_value = "5432")]
-    postgres_port: u16,
-
-    #[clap(long, env, default_value = "postgres")]
-    postgres_user: String,
-
-    #[clap(long, env, default_value = "mnemonics")]
-    database_table: String,
-
-    #[clap(long, env, default_value = "hash")]
-    database_column: String,
 }
 
 struct AppState {
-    pool: Pool,
+    bloom_filter: Bloom<String>
-    database_table: String,
-    database_column: String,
 }
 
 fn setup_registry() {
@@ -79,19 +61,9 @@ async fn index() -> impl IntoResponse {
 }
 
 #[tracing::instrument(skip(state))]
-async fn check_hash(hash: &str, state: &AppState) -> Result<bool> {
+async fn check_hash(hash: &str, state: &AppState) -> bool {
-    let client = state.pool.get().await?;
+    let bloom_filter = &state.bloom_filter;
-    let column = &state.database_column;
+    bloom_filter.check(&hash.to_string())
-    let table = &state.database_table;
-    let formatted_query = format!("SELECT {column} FROM {table} WHERE hash = $1");
-    let query = client.prepare_cached(formatted_query.as_str()).await?;
-    let rows = client.query(&query, &[&hash]).await?;
-    if let Some(row) = rows.get(0) {
-        let retrieved_hash: String = row.try_get(0)?;
-        Ok(hash == retrieved_hash)
-    } else {
-        Ok(false)
-    }
 }
 
 #[derive(Deserialize)]
@@ -104,17 +76,13 @@ struct CheckQuery {
 async fn check_hash_slug(
     query: Query<CheckQuery>,
     State(state): State<Arc<AppState>>,
-) -> (StatusCode, Json<Option<bool>>) {
+) -> (StatusCode, Json<bool>) {
     let result = check_hash(&query.sha256, &state).await;
-    let status_code = match result.as_ref() {
+    let status_code = match state.bloom_filter.check(&query.sha256.to_string()) {
-        Ok(true) => StatusCode::OK,
+        true => StatusCode::OK,
-        Ok(false) => StatusCode::NOT_FOUND,
+        false => StatusCode::NOT_FOUND,
-        Err(e) => {
-            debug!(%e, "Error while performing lookup");
-            StatusCode::INTERNAL_SERVER_ERROR
-        }
     };
-    (status_code, Json(result.ok()))
+    (status_code, Json(result))
 }
 
 #[tokio::main]
@@ -123,28 +91,20 @@ async fn main() -> Result<()> {
     color_eyre::install()?;
 
     let cli_config = CliConfig::parse();
-    let mut config = Config::new();
-    config.dbname = Some(cli_config.postgres_dbname);
-    config.host = Some(cli_config.postgres_host);
-    config.password = Some(cli_config.postgres_password);
-    config.port = Some(cli_config.postgres_port);
-    config.user = Some(cli_config.postgres_user);
-    config.manager = Some(ManagerConfig {
-        recycling_method: RecyclingMethod::Fast,
-    });
-    let pool = config.create_pool(Some(Runtime::Tokio1), NoTls)?;
     let addr = cli_config
         .bind_address
         .unwrap_or_else(|| (std::net::Ipv4Addr::new(127, 0, 0, 1), 8000).into());
 
+    info!("loading bloom filter");
+
+    let state = AppState {
+        bloom_filter: bloom::load(cli_config.bloom_filter_path.as_ref())?
+    };
+
     let app = Router::new()
         .route("/", get(index))
         .route("/check", get(check_hash_slug))
-        .with_state(Arc::new(AppState {
+        .with_state(Arc::new(state))
-            pool,
-            database_table: cli_config.database_table,
-            database_column: cli_config.database_column,
-        }))
         .layer(CatchPanicLayer::new())
         .layer(TraceLayer::new_for_http());