From 6db40138d1302db0d6306ba3201edce555a69e3a Mon Sep 17 00:00:00 2001
From: mehbark <terezi@pyrope.net>
Date: Sat, 22 Mar 2025 20:55:59 -0400
Subject: [PATCH] mvp
---
Cargo.lock | 418 ++++++++++++++++++++++++++++++++++++++++++++++++++++
Cargo.toml | 10 ++
src/main.rs | 62 ++++++++
3 files changed, 490 insertions(+)
create mode 100644 Cargo.lock
create mode 100644 Cargo.toml
create mode 100644 src/main.rs
diff --git a/Cargo.lock b/Cargo.lock
new file mode 100644
index 0000000..19a838c
--- /dev/null
+++ b/Cargo.lock
@@ -0,0 +1,418 @@
+# This file is automatically @generated by Cargo.
+# It is not intended for manual editing.
+version = 4
+
+[[package]]
+name = "anstream"
+version = "0.6.18"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8acc5369981196006228e28809f761875c0327210a891e941f4c683b3a99529b"
+dependencies = [
+ "anstyle",
+ "anstyle-parse",
+ "anstyle-query",
+ "anstyle-wincon",
+ "colorchoice",
+ "is_terminal_polyfill",
+ "utf8parse",
+]
+
+[[package]]
+name = "anstyle"
+version = "1.0.10"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "55cc3b69f167a1ef2e161439aa98aed94e6028e5f9a59be9a6ffb47aef1651f9"
+
+[[package]]
+name = "anstyle-parse"
+version = "0.2.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3b2d16507662817a6a20a9ea92df6652ee4f94f914589377d69f3b21bc5798a9"
+dependencies = [
+ "utf8parse",
+]
+
+[[package]]
+name = "anstyle-query"
+version = "1.1.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "79947af37f4177cfead1110013d678905c37501914fba0efea834c3fe9a8d60c"
+dependencies = [
+ "windows-sys",
+]
+
+[[package]]
+name = "anstyle-wincon"
+version = "3.0.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ca3534e77181a9cc07539ad51f2141fe32f6c3ffd4df76db8ad92346b003ae4e"
+dependencies = [
+ "anstyle",
+ "once_cell",
+ "windows-sys",
+]
+
+[[package]]
+name = "bitflags"
+version = "2.9.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5c8214115b7bf84099f1309324e63141d4c5d7cc26862f97a0a857dbefe165bd"
+
+[[package]]
+name = "bstr"
+version = "1.11.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "531a9155a481e2ee699d4f98f43c0ca4ff8ee1bfd55c31e9e98fb29d2b176fe0"
+dependencies = [
+ "memchr",
+ "regex-automata",
+ "serde",
+]
+
+[[package]]
+name = "cfg-if"
+version = "1.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd"
+
+[[package]]
+name = "clap"
+version = "4.5.32"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6088f3ae8c3608d19260cd7445411865a485688711b78b5be70d78cd96136f83"
+dependencies = [
+ "clap_builder",
+ "clap_derive",
+]
+
+[[package]]
+name = "clap_builder"
+version = "4.5.32"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "22a7ef7f676155edfb82daa97f99441f3ebf4a58d5e32f295a56259f1b6facc8"
+dependencies = [
+ "anstream",
+ "anstyle",
+ "clap_lex",
+ "strsim",
+]
+
+[[package]]
+name = "clap_derive"
+version = "4.5.32"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "09176aae279615badda0765c0c0b3f6ed53f4709118af73cf4655d85d1530cd7"
+dependencies = [
+ "heck",
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "clap_lex"
+version = "0.7.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f46ad14479a25103f283c0f10005961cf086d8dc42205bb44c46ac563475dca6"
+
+[[package]]
+name = "colorchoice"
+version = "1.0.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5b63caa9aa9397e2d9480a9b13673856c78d8ac123288526c37d7839f2a86990"
+
+[[package]]
+name = "either"
+version = "1.15.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "48c757948c5ede0e46177b7add2e67155f70e33c07fea8284df6576da70b3719"
+
+[[package]]
+name = "fast-markov-chain"
+version = "0.1.0"
+dependencies = [
+ "bstr",
+ "clap",
+ "itertools",
+ "rand",
+]
+
+[[package]]
+name = "getrandom"
+version = "0.3.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "73fea8450eea4bac3940448fb7ae50d91f034f941199fcd9d909a5a07aa455f0"
+dependencies = [
+ "cfg-if",
+ "libc",
+ "r-efi",
+ "wasi",
+]
+
+[[package]]
+name = "heck"
+version = "0.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2304e00983f87ffb38b55b444b5e3b60a884b5d30c0fca7d82fe33449bbe55ea"
+
+[[package]]
+name = "is_terminal_polyfill"
+version = "1.70.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7943c866cc5cd64cbc25b2e01621d07fa8eb2a1a23160ee81ce38704e97b8ecf"
+
+[[package]]
+name = "itertools"
+version = "0.14.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2b192c782037fadd9cfa75548310488aabdbf3d2da73885b31bd0abd03351285"
+dependencies = [
+ "either",
+]
+
+[[package]]
+name = "libc"
+version = "0.2.171"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c19937216e9d3aa9956d9bb8dfc0b0c8beb6058fc4f7a4dc4d850edf86a237d6"
+
+[[package]]
+name = "memchr"
+version = "2.7.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "78ca9ab1a0babb1e7d5695e3530886289c18cf2f87ec19a575a0abdce112e3a3"
+
+[[package]]
+name = "once_cell"
+version = "1.21.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d75b0bedcc4fe52caa0e03d9f1151a323e4aa5e2d78ba3580400cd3c9e2bc4bc"
+
+[[package]]
+name = "ppv-lite86"
+version = "0.2.21"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "85eae3c4ed2f50dcfe72643da4befc30deadb458a9b590d720cde2f2b1e97da9"
+dependencies = [
+ "zerocopy",
+]
+
+[[package]]
+name = "proc-macro2"
+version = "1.0.94"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a31971752e70b8b2686d7e46ec17fb38dad4051d94024c88df49b667caea9c84"
+dependencies = [
+ "unicode-ident",
+]
+
+[[package]]
+name = "quote"
+version = "1.0.40"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1885c039570dc00dcb4ff087a89e185fd56bae234ddc7f056a945bf36467248d"
+dependencies = [
+ "proc-macro2",
+]
+
+[[package]]
+name = "r-efi"
+version = "5.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "74765f6d916ee2faa39bc8e68e4f3ed8949b48cccdac59983d287a7cb71ce9c5"
+
+[[package]]
+name = "rand"
+version = "0.9.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3779b94aeb87e8bd4e834cee3650289ee9e0d5677f976ecdb6d219e5f4f6cd94"
+dependencies = [
+ "rand_chacha",
+ "rand_core",
+ "zerocopy",
+]
+
+[[package]]
+name = "rand_chacha"
+version = "0.9.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d3022b5f1df60f26e1ffddd6c66e8aa15de382ae63b3a0c1bfc0e4d3e3f325cb"
+dependencies = [
+ "ppv-lite86",
+ "rand_core",
+]
+
+[[package]]
+name = "rand_core"
+version = "0.9.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "99d9a13982dcf210057a8a78572b2217b667c3beacbf3a0d8b454f6f82837d38"
+dependencies = [
+ "getrandom",
+]
+
+[[package]]
+name = "regex-automata"
+version = "0.4.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "809e8dc61f6de73b46c85f4c96486310fe304c434cfa43669d7b40f711150908"
+
+[[package]]
+name = "serde"
+version = "1.0.219"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5f0e2c6ed6606019b4e29e69dbaba95b11854410e5347d525002456dbbb786b6"
+dependencies = [
+ "serde_derive",
+]
+
+[[package]]
+name = "serde_derive"
+version = "1.0.219"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5b0276cf7f2c73365f7157c8123c21cd9a50fbbd844757af28ca1f5925fc2a00"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "strsim"
+version = "0.11.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7da8b5736845d9f2fcb837ea5d9e2628564b3b043a70948a3f0b778838c5fb4f"
+
+[[package]]
+name = "syn"
+version = "2.0.100"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b09a44accad81e1ba1cd74a32461ba89dee89095ba17b32f5d03683b1b1fc2a0"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "unicode-ident",
+]
+
+[[package]]
+name = "unicode-ident"
+version = "1.0.18"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5a5f39404a5da50712a4c1eecf25e90dd62b613502b7e925fd4e4d19b5c96512"
+
+[[package]]
+name = "utf8parse"
+version = "0.2.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "06abde3611657adf66d383f00b093d7faecc7fa57071cce2578660c9f1010821"
+
+[[package]]
+name = "wasi"
+version = "0.14.2+wasi-0.2.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9683f9a5a998d873c0d21fcbe3c083009670149a8fab228644b8bd36b2c48cb3"
+dependencies = [
+ "wit-bindgen-rt",
+]
+
+[[package]]
+name = "windows-sys"
+version = "0.59.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1e38bc4d79ed67fd075bcc251a1c39b32a1776bbe92e5bef1f0bf1f8c531853b"
+dependencies = [
+ "windows-targets",
+]
+
+[[package]]
+name = "windows-targets"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9b724f72796e036ab90c1021d4780d4d3d648aca59e491e6b98e725b84e99973"
+dependencies = [
+ "windows_aarch64_gnullvm",
+ "windows_aarch64_msvc",
+ "windows_i686_gnu",
+ "windows_i686_gnullvm",
+ "windows_i686_msvc",
+ "windows_x86_64_gnu",
+ "windows_x86_64_gnullvm",
+ "windows_x86_64_msvc",
+]
+
+[[package]]
+name = "windows_aarch64_gnullvm"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "32a4622180e7a0ec044bb555404c800bc9fd9ec262ec147edd5989ccd0c02cd3"
+
+[[package]]
+name = "windows_aarch64_msvc"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "09ec2a7bb152e2252b53fa7803150007879548bc709c039df7627cabbd05d469"
+
+[[package]]
+name = "windows_i686_gnu"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8e9b5ad5ab802e97eb8e295ac6720e509ee4c243f69d781394014ebfe8bbfa0b"
+
+[[package]]
+name = "windows_i686_gnullvm"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0eee52d38c090b3caa76c563b86c3a4bd71ef1a819287c19d586d7334ae8ed66"
+
+[[package]]
+name = "windows_i686_msvc"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "240948bc05c5e7c6dabba28bf89d89ffce3e303022809e73deaefe4f6ec56c66"
+
+[[package]]
+name = "windows_x86_64_gnu"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "147a5c80aabfbf0c7d901cb5895d1de30ef2907eb21fbbab29ca94c5b08b1a78"
+
+[[package]]
+name = "windows_x86_64_gnullvm"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "24d5b23dc417412679681396f2b49f3de8c1473deb516bd34410872eff51ed0d"
+
+[[package]]
+name = "windows_x86_64_msvc"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "589f6da84c646204747d1270a2a5661ea66ed1cced2631d546fdfb155959f9ec"
+
+[[package]]
+name = "wit-bindgen-rt"
+version = "0.39.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6f42320e61fe2cfd34354ecb597f86f413484a798ba44a8ca1165c58d42da6c1"
+dependencies = [
+ "bitflags",
+]
+
+[[package]]
+name = "zerocopy"
+version = "0.8.24"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2586fea28e186957ef732a5f8b3be2da217d65c5969d4b1e17f973ebbe876879"
+dependencies = [
+ "zerocopy-derive",
+]
+
+[[package]]
+name = "zerocopy-derive"
+version = "0.8.24"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a996a8f63c5c4448cd959ac1bab0aaa3306ccfd060472f85943ee0750f0169be"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
diff --git a/Cargo.toml b/Cargo.toml
new file mode 100644
index 0000000..6a00187
--- /dev/null
+++ b/Cargo.toml
@@ -0,0 +1,10 @@
+[package]
+name = "fast-markov-chain"
+version = "0.1.0"
+edition = "2024"
+
+[dependencies]
+bstr = "1.11.3"
+clap = { version = "4.5.32", features = ["derive"] }
+itertools = "0.14.0"
+rand = "0.9.0"
diff --git a/src/main.rs b/src/main.rs
new file mode 100644
index 0000000..23dcddb
--- /dev/null
+++ b/src/main.rs
@@ -0,0 +1,62 @@
+use std::{
+ collections::HashMap,
+ error::Error,
+ io::{self, Read},
+};
+
+use bstr::ByteSlice;
+use clap::Parser;
+use itertools::Itertools;
+use rand::seq::IndexedRandom;
+
+#[derive(clap::Parser)]
+struct Args {
+ first_word: String,
+ #[arg(short, long)]
+ count: usize,
+ // TODO: higher-order chains
+}
+
+// use bstr because we don't give a cr*p about utf-8!
+fn main() -> Result<(), Box<dyn Error>> {
+ let Args {
+ first_word,
+ mut count,
+ } = Args::parse();
+
+ // printing the first word immediately gives an intuitive idea of how long freq construction takes
+ print!("{first_word} ");
+
+ let mut buf = Vec::with_capacity(1 << 16);
+ io::stdin().read_to_end(&mut buf)?;
+ let buf = buf.to_lowercase();
+
+ let mut freq: HashMap<&str, HashMap<&str, usize>> = HashMap::new();
+ for (word, next) in buf.words().tuple_windows() {
+ *freq.entry(word).or_default().entry(next).or_default() += 1;
+ }
+
+ let mut rng = rand::rng();
+ let mut current_word = first_word.as_str();
+ while let Some(nexts) = freq.get(current_word) {
+ if count == 0 {
+ break;
+ }
+
+ current_word = nexts
+ .iter()
+ .collect::<Vec<_>>()
+ .choose_weighted(&mut rng, |(_, count)| **count)
+ .expect("freq maps must be nonempty")
+ .0;
+
+ print!("{current_word}");
+ if count > 1 {
+ print!(" ");
+ }
+ count -= 1;
+ }
+ println!();
+
+ Ok(())
+}