Add source for ngram

Author: dem4ron

bin/generator-utils/ngram

@@ -52,10 +52,10 @@ function check_exercise_existence() {
         message "info" "These are the unimplemented practice exercises:
 ${unimplemented_exercises}"
 
-        # this is a compiled, tiny Rust program
-        # this fn uses the ngram algorithm to find the closest match to an exercise
-        # I'm using the ngrammatic crate to achieve this
-        bin/generator-utils/ngram "${unimplemented_exercises}" "$slug"
+        # Find closest match to typed-in not-found slug
+        # see util/ngram for source
+        echo "${YELLOW}$(bin/generator-utils/ngram "${unimplemented_exercises}" "$slug")${RESET}"
+
         exit 1
     fi
 }

bin/generator-utils/utils.sh

@@ -0,0 +1,9 @@
+[package]
+name = "ngram"
+version = "0.1.0"
+edition = "2021"
+
+# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
+
+[dependencies]
+ngrammatic = "0.4.0"

util/ngram/Cargo.lock

@@ -0,0 +1,2 @@
+#!/usr/bin/env bash
+cargo build --release && cp ./target/release/ngram ../../bin/generator-utils && rm -rf ./target

util/ngram/Cargo.toml

@@ -0,0 +1,30 @@
+use ngrammatic::{CorpusBuilder, Pad};
+
+fn main() {
+    let mut args = std::env::args();
+    let exercises = args.nth(1).expect("Missing exercises argument");
+    let slug = args.nth(0).expect("Missing slug argument");
+    let exercises: Vec<&str> = exercises
+        .split(|c: char| c.is_whitespace() || c == '\n')
+        .collect();
+    let mut corpus = CorpusBuilder::new().arity(2).pad_full(Pad::Auto).finish();
+
+    for exercise in exercises.iter() {
+        corpus.add_text(exercise);
+    }
+
+    if let Some(top_result) = corpus.search(&slug, 0.25).first() {
+        if top_result.similarity > 0.99 {
+            println!("{}", top_result.text);
+        } else {
+            println!(
+                "{} - There is an exercise with a similar name: '{}' [{:.0}% match]",
+                slug,
+                top_result.text,
+                top_result.similarity * 100.0
+            );
+        }
+    } else {
+        println!("{}", slug);
+    }
+}