Add compression to dictionary data

Cargo.lock

@@ -2,6 +2,47 @@
 # It is not intended for manual editing.
 version = 3
 
+[[package]]
+name = "cc"
+version = "1.0.73"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2fff2a6927b3bb87f9595d67196a70493f627687a71d87a0d692242c33f58c11"
+
+[[package]]
+name = "libc"
+version = "0.2.126"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "349d5a591cd28b49e1d1037471617a32ddcda5731b99419008085f72d5a53836"
+
+[[package]]
+name = "lzma-sys"
+version = "0.1.19"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e06754c4acf47d49c727d5665ca9fb828851cda315ed3bd51edd148ef78a8772"
+dependencies = [
+ "cc",
+ "libc",
+ "pkg-config",
+]
+
+[[package]]
+name = "pkg-config"
+version = "0.3.25"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1df8c4ec4b0627e53bdf214615ad287367e482558cf84b109250b37464dc03ae"
+
 [[package]]
 name = "unscrambler"
 version = "0.1.0"
+dependencies = [
+ "xz2",
+]
+
+[[package]]
+name = "xz2"
+version = "0.1.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "388c44dc09d76f1536602ead6d325eb532f5c122f17782bd57fb47baeeb767e2"
+dependencies = [
+ "lzma-sys",
+]

Cargo.toml

@@ -6,3 +6,4 @@ edition = "2021"
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
 
 [dependencies]
+xz2 = "0.1.7"

README.md

@@ -6,4 +6,4 @@ I'm learning Rust, so this is just a rewrite of an simple old project in Rust.
 
 ### Note
 
-The main wordlist was pulled from [words_alpha.txt by dwyl](https://github.com/dwyl/english-words/) and processed using Rust. Processing code was really simple, so didn't put it up here.
+The main `src/wordlist` was pulled from [words_alpha.txt by dwyl](https://github.com/dwyl/english-words/) and processed using Rust. Processing code was really simple, so didn't put it up here. The processing included pre-sorting the each line in `src/wordlist` to create `src/wordlist_sorted` and then compressing both using `xz`.

src/main.rs

@@ -1,9 +1,22 @@
-use std::io::{self, Write};
+use std::io::{self, prelude::*, Write};
+use xz2::read::XzDecoder;
 
 fn main() {
-    // read the dictionary files
-    let wordlist = include_str!("data/wordlist.txt");
-    let wordlist_sorted = include_str!("data/wordlist_sorted.txt");
+    // load the compressed dictionary files (embedded in compile-time)
+    let wordlist_cmp: &[u8] = include_bytes!("dict/wordlist.txt.xz");
+    let wordlist_sorted_cmp: &[u8] = include_bytes!("dict/wordlist_sorted.txt.xz");
+
+    // decompress the dictionary files
+    let mut decompressor = XzDecoder::new(wordlist_cmp);
+    let mut decompressor_sorted = XzDecoder::new(wordlist_sorted_cmp);
+    let mut wordlist = String::new();
+    let mut wordlist_sorted = String::new();
+    decompressor.read_to_string(&mut wordlist).unwrap();
+    decompressor_sorted
+        .read_to_string(&mut wordlist_sorted)
+        .unwrap();
+
+    // some formatting of the dictionary data
     let wordlist = &[" ", &wordlist.replace("\n", " ")[..]].join("")[..];
     let wordlist_sorted = &[" ", &wordlist_sorted.replace("\n", " ")[..]].join("")[..];