From 3032e11b784022b17b4f5111ab271c647d989eb7 Mon Sep 17 00:00:00 2001
From: ryan <ryan@distrust.co>
Date: Thu, 17 Aug 2023 23:15:19 -0500
Subject: [PATCH] keyfork-mnemonic-generate: the math ain't mathin

---
 Cargo.lock                            | 42 +++++++++++++++++++++++++++
 keyfork-mnemonic-generate/Cargo.toml  |  1 +
 keyfork-mnemonic-generate/src/main.rs | 41 +++++++++++++++++++++++---
 3 files changed, 80 insertions(+), 4 deletions(-)

diff --git a/Cargo.lock b/Cargo.lock
index 53b71e4..2ec4b6e 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -2,6 +2,23 @@
 # It is not intended for manual editing.
 version = 3
 
+[[package]]
+name = "bip39"
+version = "2.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "93f2635620bf0b9d4576eb7bb9a38a55df78bd1205d26fa994b25911a69f212f"
+dependencies = [
+ "bitcoin_hashes",
+ "serde",
+ "unicode-normalization",
+]
+
+[[package]]
+name = "bitcoin_hashes"
+version = "0.11.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "90064b8dee6815a6470d60bad07bbbaee885c0e12d04177138fa3291a01b7bc4"
+
 [[package]]
 name = "block-buffer"
 version = "0.10.4"
@@ -72,6 +89,7 @@ checksum = "af150ab688ff2122fcef229be89cb50dd66af9e01a4ff320cc137eecc9bacc38"
 name = "keyfork-mnemonic-generate"
 version = "0.1.0"
 dependencies = [
+ "bip39",
  "hex",
  "serde_json",
  "sha2",
@@ -117,12 +135,36 @@ dependencies = [
  "digest",
 ]
 
+[[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 = "typenum"
 version = "1.16.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "497961ef93d974e23eb6f433eb5fe1b7930b659f06d12dec6fc44a8f554c0bba"
 
+[[package]]
+name = "unicode-normalization"
+version = "0.1.22"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5c5713f0fc4b5db668a2ac63cdb7bb4469d8c9fed047b1d0292cc7b0ce2ba921"
+dependencies = [
+ "tinyvec",
+]
+
 [[package]]
 name = "version_check"
 version = "0.9.4"
diff --git a/keyfork-mnemonic-generate/Cargo.toml b/keyfork-mnemonic-generate/Cargo.toml
index 4652cd1..6e78648 100644
--- a/keyfork-mnemonic-generate/Cargo.toml
+++ b/keyfork-mnemonic-generate/Cargo.toml
@@ -9,5 +9,6 @@ edition = "2021"
 sha2 = "0.10.7"
 
 [dev-dependencies]
+bip39 = "2.0.0"
 hex = "0.4.3"
 serde_json = "1.0.105"
diff --git a/keyfork-mnemonic-generate/src/main.rs b/keyfork-mnemonic-generate/src/main.rs
index de974ad..7f3b702 100644
--- a/keyfork-mnemonic-generate/src/main.rs
+++ b/keyfork-mnemonic-generate/src/main.rs
@@ -93,6 +93,8 @@ fn ensure_offline() {
 
 // TODO: Can a Mnemonic be formatted using a wordlist, without allocating or without storing the
 // entire word list?
+//
+// NOTE: Yes, use a Language and pass a reference to this.
 struct Mnemonic {
     pub words: Vec<usize>,
     wordlist: Vec<String>,
@@ -233,19 +235,50 @@ mod tests {
         Ok(())
     }
 
+    #[test]
+    fn matches_bip39_crate() {
+        let mut random_handle = File::open("/dev/random").unwrap();
+        let entropy = &mut [0u8; 256 / 8];
+        random_handle.read_exact(&mut entropy[..]).unwrap();
+        let my_mnemonic = super::Mnemonic::from_entropy(&entropy[..256 / 8]).unwrap();
+        let their_mnemonic = bip39::Mnemonic::from_entropy(&entropy[..256 / 8]).unwrap();
+        /*
+        let my_words = my_mnemonic.words.clone();
+        let their_words = their_mnemonic.word_iter().collect::<Vec<_>>();
+        */
+        assert_eq!(my_mnemonic.to_string(), their_mnemonic.to_string());
+    }
+
     #[test]
     fn count_to_get_duplicate_words() {
         let mut count = 0.;
-        let mut random_handle = File::open("/dev/urandom").unwrap();
+        let mut smallest = 2048;
+        let mut largest = 0;
+        let mut random_handle = File::open("/dev/random").unwrap();
         let entropy = &mut [0u8; 256 / 8];
+        let mut set = std::collections::HashMap::<&str, u32>::new();
         for _ in 0..100_000 {
             random_handle.read_exact(&mut entropy[..]).unwrap();
-            let mut mnemonic = Mnemonic::from_entropy(&entropy[..256 / 8]).unwrap();
+            // let bits = generate_slice_hash(entropy);
+            let mnemonic = bip39::Mnemonic::from_entropy(&entropy[..256 / 8]).unwrap();
+            /*
             mnemonic.words.dedup();
-            if mnemonic.words.len() != 24 {
+            */
+            // NOTE: This pulls everything BUT the last word, just for testing.
+            // Change to ..24 to include the last word.
+            for (word, _) in mnemonic.word_iter().zip(0..23) {
+                *set.entry(word).or_insert(0) += 1;
+            }
+            let mut words = mnemonic.word_iter().collect::<Vec<_>>();
+            words.dedup();
+            if words.len() != 24 {
                 count += 1.;
             }
         }
-        panic!("counts: {count} {}", count / 100_000.)
+        for entry in &set {
+            smallest = std::cmp::min(smallest, *entry.1);
+            largest = std::cmp::max(largest, *entry.1);
+        }
+        panic!("{count} len:{} smallest:{smallest} largest:{largest}", set.len())
     }
 }