Vendor the en_US dictionary

It will be a little friendlier for anyone trying out the examples or
benchmarks to make the dictionary lookup infallible. We will eventually
want to use a real dictionary for integration tests and we can drop the
xdg dependency. The file size is around a half of a MB so I don't feel
too badly about pulling this in.

Cargo.toml

@@ -9,6 +9,3 @@ rust-version = "1.60"
 [dependencies]
 # TODO: investigate using smartstring to cut down on allocations since
 # there are plenty of small strings.
-
-[dev-dependencies]
-xdg = "2.5"

bench/Cargo.toml

@@ -8,4 +8,3 @@ rust-version = "1.66"
 [dependencies]
 spellbook = { path = "../" }
 brunch = "0.5"
-xdg = "2.5"

bench/src/main.rs

@@ -3,33 +3,13 @@ use std::hint::black_box;
 use brunch::Bench;
 use spellbook::Dictionary;
 
+const EN_US_DIC: &str = include_str!("../../vendor/en_US/en_US.dic");
+const EN_US_AFF: &str = include_str!("../../vendor/en_US/en_US.aff");
+
 const SAMPLES: u32 = 500_000;
 
 fn main() {
-    let base = xdg::BaseDirectories::new().expect("Could not determine XDG directories");
-    let (dic_path, aff_path) = match base.get_data_dirs().iter().find_map(|dir| {
-        let subdir = dir.join("hunspell");
-        if !subdir.is_dir() {
-            return None;
-        }
-
-        let dic = subdir.join("en_US.dic");
-        let aff = subdir.join("en_US.aff");
-        if dic.is_file() && aff.is_file() {
-            Some((dic, aff))
-        } else {
-            None
-        }
-    }) {
-        Some((dic, aff)) => (dic, aff),
-        None => {
-            eprintln!("Could not find the en_US dictionary");
-            std::process::exit(1);
-        }
-    };
-    let dic_text = std::fs::read_to_string(dic_path).unwrap();
-    let aff_text = std::fs::read_to_string(aff_path).unwrap();
-    let dict = Dictionary::compile(&aff_text, &dic_text).unwrap();
+    let dict = Dictionary::compile(EN_US_AFF, EN_US_DIC).unwrap();
 
     eprintln!("Starting benchmarks...");
     eprintln!();
@@ -39,7 +19,7 @@ fn main() {
 
         // Compilation
         Bench::new("Compile en_US")
-            .run(|| Dictionary::compile(black_box(&aff_text), black_box(&dic_text))),
+            .run(|| Dictionary::compile(black_box(EN_US_AFF), black_box(EN_US_DIC))),
         Bench::spacer(),
 
         // Checking

examples/check.rs

@@ -1,52 +1,23 @@
 use std::time::Instant;
 
 use spellbook::Dictionary;
-use xdg::BaseDirectories;
+
+const EN_US_DIC: &str = include_str!("../vendor/en_US/en_US.dic");
+const EN_US_AFF: &str = include_str!("../vendor/en_US/en_US.aff");
 
 fn main() {
     let mut args = std::env::args().skip(1);
-    let arg1 = match args.next() {
+    let word = match args.next() {
         Some(arg) => arg,
         None => {
-            eprintln!("Usage: check [LANG] WORD");
-            std::process::exit(1);
-        }
-    };
-    let (lang, word) = match args.next() {
-        Some(arg2) => (arg1, arg2),
-        None => ("en_US".to_string(), arg1),
-    };
-
-    let base = BaseDirectories::new().expect("Could not determine XDG directories");
-    let (dic_path, aff_path) = match base.get_data_dirs().iter().find_map(|dir| {
-        let subdir = dir.join("hunspell");
-        if !subdir.is_dir() {
-            return None;
-        }
-
-        let dic = subdir.join(format!("{lang}.dic"));
-        let aff = subdir.join(format!("{lang}.aff"));
-        if dic.is_file() && aff.is_file() {
-            Some((dic, aff))
-        } else {
-            None
-        }
-    }) {
-        Some((dic, aff)) => (dic, aff),
-        None => {
-            eprintln!("Could not find the {lang} dictionary");
+            eprintln!("Usage: check WORD");
             std::process::exit(1);
         }
     };
-    let dic_text = std::fs::read_to_string(dic_path).unwrap();
-    let aff_text = std::fs::read_to_string(aff_path).unwrap();
 
     let now = Instant::now();
-    let dict = Dictionary::compile(&aff_text, &dic_text).unwrap();
-    println!(
-        "Compiled the {lang} dictionary in {}ms",
-        now.elapsed().as_millis()
-    );
+    let dict = Dictionary::compile(EN_US_AFF, EN_US_DIC).unwrap();
+    println!("Compiled the dictionary in {}ms", now.elapsed().as_millis());
 
     let now = Instant::now();
     if dict.check(&word) {

shell.nix

@@ -11,5 +11,4 @@ pkgs.mkShell {
     cargo-flamegraph
   ];
   RUST_BACKTRACE = "1";
-  XDG_DATA_DIRS = with pkgs; lib.makeSearchPath "share" [hunspellDicts.en_US];
 }

vendor/en_US/README.txt

@@ -0,0 +1,6 @@
+US English dictionary.
+
+These files are licensed separately from spellbook. See the '*license.txt'
+files in this directory.
+
+Upstream <https://github.com/JetBrains/hunspell-dictionaries>

vendor/en_US/WordNet_license.txt

@@ -0,0 +1,31 @@
+WordNet Release 2.1
+
+This software and database is being provided to you, the LICENSEE, by  
+Princeton University under the following license.  By obtaining, using  
+and/or copying this software and database, you agree that you have  
+read, understood, and will comply with these terms and conditions.:  
+
+Permission to use, copy, modify and distribute this software and  
+database and its documentation for any purpose and without fee or  
+royalty is hereby granted, provided that you agree to comply with  
+the following copyright notice and statements, including the disclaimer,  
+and that the same appear on ALL copies of the software, database and  
+documentation, including modifications that you make for internal  
+use or for distribution.  
+
+WordNet 2.1 Copyright 2005 by Princeton University.  All rights reserved.  
+
+THIS SOFTWARE AND DATABASE IS PROVIDED "AS IS" AND PRINCETON  
+UNIVERSITY MAKES NO REPRESENTATIONS OR WARRANTIES, EXPRESS OR  
+IMPLIED.  BY WAY OF EXAMPLE, BUT NOT LIMITATION, PRINCETON  
+UNIVERSITY MAKES NO REPRESENTATIONS OR WARRANTIES OF MERCHANT-  
+ABILITY OR FITNESS FOR ANY PARTICULAR PURPOSE OR THAT THE USE  
+OF THE LICENSED SOFTWARE, DATABASE OR DOCUMENTATION WILL NOT  
+INFRINGE ANY THIRD PARTY PATENTS, COPYRIGHTS, TRADEMARKS OR  
+OTHER RIGHTS.  
+
+The name of Princeton University or Princeton may not be used in  
+advertising or publicity pertaining to distribution of the software  
+and/or database.  Title to copyright in this software, database and  
+any associated documentation shall at all times remain with  
+Princeton University and LICENSEE agrees to preserve same.