feat: optimize and simplify python download script

Cargo.lock

@@ -3,131 +3,14 @@
 version = 4
 
 [[package]]
-name = "cfg-if"
+name = "fastrand"
-version = "1.0.0"
+version = "2.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd"
+checksum = "37909eebbb50d72f9059c3b6d82c0463f2ff062c9e95845c43a6c9c0355411be"
-
-[[package]]
-name = "getrandom"
-version = "0.2.15"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c4567c8db10ae91089c99af84c68c38da3ec2f087c3f82960bcdbf3656b6f4d7"
-dependencies = [
- "cfg-if",
- "libc",
- "wasi",
-]
-
-[[package]]
-name = "libc"
-version = "0.2.171"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c19937216e9d3aa9956d9bb8dfc0b0c8beb6058fc4f7a4dc4d850edf86a237d6"
-
-[[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 = "rand"
-version = "0.8.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "34af8d1a0e25924bc5b7c43c079c942339d8f0a8b57c39049bef581b46327404"
-dependencies = [
- "libc",
- "rand_chacha",
- "rand_core",
-]
-
-[[package]]
-name = "rand_chacha"
-version = "0.3.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e6c10a63a0fa32252be49d21e7709d4d4baf8d231c2dbce1eaa8141b9b127d88"
-dependencies = [
- "ppv-lite86",
- "rand_core",
-]
-
-[[package]]
-name = "rand_core"
-version = "0.6.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ec0be4795e2f6a28069bec0b5ff3e2ac9bafc99e6a9a7dc3547996c5c816922c"
-dependencies = [
- "getrandom",
-]
 
 [[package]]
 name = "rpg"
 version = "1.0.0"
 dependencies = [
- "rand",
+ "fastrand",
-]
-
-[[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 = "wasi"
-version = "0.11.0+wasi-snapshot-preview1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9c8d87e72b64a3b4db28d11ce29237c246188f4f51057d65a7eab63b7987e423"
-
-[[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",
 ]

Cargo.toml

@@ -4,4 +4,4 @@ version = "1.0.0"
 edition = "2021"
 
 [dependencies]
-rand = "0.8"
+fastrand = "2.3.0"

download_data.py

@@ -1,33 +1,29 @@
 import nltk
 import os
 
+
 def main():
-    # Load the corpora
+    nltk.download("wordnet")
-    nltk.download('wordnet')
-    nltk.download('averaged_perceptron_tagger')
-    nltk.download('universal_tagset')
 
-    # Get all the adjectives and nouns
+    adjectives = {
-    adjectives = set()
+        lemma.name().capitalize()
-    nouns = set()
+        for synset in nltk.corpus.wordnet.all_synsets(pos="a")
-    for synset in nltk.corpus.wordnet.all_synsets():
+        for lemma in synset.lemmas()
-        for lemma in synset.lemmas():
+        if lemma.name().isalpha()
-            if lemma.name().isalpha():
+    }
-                if synset.pos() == 'a':
+    nouns = {
-                    adjectives.add(lemma.name())
+        lemma.name().capitalize()
-                elif synset.pos() == 'n':
+        for synset in nltk.corpus.wordnet.all_synsets(pos="n")
-                    nouns.add(lemma.name())
+        for lemma in synset.lemmas()
-    
+        if lemma.name().isalpha()
-    # Create the output directory if it doesn't exist
+    }
-    os.makedirs('data', exist_ok=True)
 
-    with open('data/adjectives.txt', 'w+') as file:
+    os.makedirs("data", exist_ok=True)
-        for adjective in adjectives:
+    with open("data/adjectives.txt", "w") as adj_file:
-            file.write(str(adjective).capitalize() + '\n')
+        adj_file.write("\n".join(sorted(adjectives)))
-    
+    with open("data/nouns.txt", "w") as noun_file:
-    with open('data/nouns.txt', 'w+') as file:
+        noun_file.write("\n".join(sorted(nouns)))
-        for noun in nouns:
-            file.write(str(noun).capitalize() + '\n')
 
-if __name__ == '__main__':
+
-    main()
+if __name__ == "__main__":
+    main()

src/main.rs

@@ -1,49 +1,20 @@
-use rand::seq::SliceRandom;
-use rand::Rng;
 use std::env;
-use std::io::{BufRead, BufReader};
 
 fn main() {
-    let num_pseudonyms: usize = {
+    let num_pseudonyms = env::args()
-        let args: Vec<String> = env::args().collect();
+        .nth(1)
-        if args.len() > 1 {
+        .and_then(|arg| arg.parse().ok())
-            match args[1].parse::<usize>() {
+        .unwrap_or(10);
-                Ok(num) => num,
-                Err(_) => {
-                    eprintln!("Le nombre de pseudonymes doit être un entier positif.");
-                    std::process::exit(1);
-                }
-            }
-        } else {
-            100
-        }
-    };
 
-    let adjectives: Vec<String> = {
+    let adjectives = include_str!("../data/adjectives.txt").lines().collect::<Vec<_>>();
-        BufReader::new(include_str!("../data/adjectives.txt").as_bytes())
+    let nouns = include_str!("../data/nouns.txt").lines().collect::<Vec<_>>();
-            .lines()
-            .filter_map(Result::ok)
-            .collect()
-    };
 
-    let nouns: Vec<String> = {
+    (0..num_pseudonyms).for_each(|_| {
-        BufReader::new(include_str!("../data/nouns.txt").as_bytes())
+        println!(
-            .lines()
+            "{}-{}-{}",
-            .filter_map(Result::ok)
+            adjectives[fastrand::usize(0..adjectives.len())],
-            .collect()
+            nouns[fastrand::usize(0..nouns.len())],
-    };
+            fastrand::u32(0..1000)
-
+        );
-    let mut rng = rand::thread_rng();
+    });
-    for _ in 0..num_pseudonyms {
+}
-        let Some(adjective) = adjectives.choose(&mut rng) else {
-            eprintln!("Impossible de choisir un adjectif.");
-            std::process::exit(1);
-        };
-        let Some(noun) = nouns.choose(&mut rng) else {
-            eprintln!("Impossible de choisir un nom.");
-            std::process::exit(1);
-        };
-        let number: u32 = rng.gen_range(1..=999);
-        println!("{}", format!("{}-{}-{}", adjective, noun, number));
-    }
-}