update code to support TA - Tamil language

docs/README.md

@@ -66,3 +66,104 @@ cargo run -- <args>
 ```
 
 where `<args>` are the command-line arguments you would pass the DidYouMean binary. Note that this is an unoptimized build contianing debug information so it runs much, much slower.
+Adding New Language
+===================
+Update the language code in the list at 
+
+
+Update the language wordlist
+============================
+```
+$ cargo run -- --lang ta  --update-langs --wordlist-url https://raw.githubusercontent.com/arcturusannamalai/wordlists/main/
+    Finished dev [unoptimized + debuginfo] target(s) in 0.17s
+     Running `target/debug/dym --lang ta --update-langs --wordlist-url 'https://raw.githubusercontent.com/arcturusannamalai/wordlists/main/'`
+Downloading English word list...
+Accessing URL: https://raw.githubusercontent.com/arcturusannamalai/wordlists/main//en
+[00:00:00] [############################################################################################################################] 4.12MiB/4.12MiB (0s)
+Downloading Tamil word list...
+Accessing URL: https://raw.githubusercontent.com/arcturusannamalai/wordlists/main//ta
+[00:00:00] [############################################################################################################################] 1.73MiB/1.73MiB (0s)
+```
+
+Run did you mean:
+================
+e.g.
+```
+cargo run -- --lang ta  கலஅ 
+   Compiling didyoumean v1.1.4 (/Users/user/devel/rust-in-action/didyoumean)
+    Finished dev [unoptimized + debuginfo] target(s) in 1.18s
+     Running `target/debug/dym --lang ta 'கலஅ'`
+Did you mean?
+1. கலி
+2. கலை
+3. கல்
+4. அ
+5. அகல்
+
+```
+
+
+For more info see the help text and options,
+```
+$ cargo run -- --help
+
+didyoumean user$ cargo run -- --help
+   Compiling didyoumean v1.1.4 (/Users/user/devel/rust-in-action/didyoumean)
+    Finished dev [unoptimized + debuginfo] target(s) in 2.24s
+     Running `target/debug/dym --help`
+didyoumean 1.1.4
+Hisbaan Noorani
+Did You Mean: A cli spelling corrector
+
+USAGE:
+    dym [OPTIONS] [SEARCH_TERM]
+
+ARGS:
+    <SEARCH_TERM>
+
+
+OPTIONS:
+    -c, --clean-output
+            Print a clean version of the output without the title, numbers or colour.
+
+    -h, --help
+            Print help information
+
+    -l, --lang <LANG>
+            Select the desired language using its locale code. For example, English would have the
+            locale code en and French would have the locale code fr. See --print-langs for a list of
+            locale codes and the corresponding languages.
+
+            [default: en]
+
+    -n, --number <NUMBER>
+            Change the number of words the program will print. The default value is five.
+
+            [default: 5]
+
+        --print-langs
+            Display a list of supported languages and their respective locale codes.
+
+        --update-langs
+            Update all language files from the repository specified by CLI @wordlist-url@.
+
+    -v, --verbose
+            Print verbose output including the edit distance of the found word to the queried word.
+
+    -V, --version
+            Print version information
+
+    -w, --wordlist-url <WORDLIST_URL>
+            Wordlist repository URL. The default value is
+            'https://raw.githubusercontent.com/hisbaan/wordlists/main'
+
+            [default: https://raw.githubusercontent.com/hisbaan/wordlists/main]
+
+    -y, --yank
+            Yank (copy) the selected word to the system clipboard. If no word is selected, the
+            clipboard will not be altered.
+
+```
+
+
+

src/cli.rs

@@ -51,7 +51,15 @@ pub struct Cli {
     #[clap(
         long = "update-langs",
         help = "Update all language files",
-        long_help = "Update all language files from the repository https://github.com/hisbaan/wordlists."
+        long_help = "Update all language files from the repository specified by CLI @wordlist-url@."
     )]
     pub update_langs: bool,
+    #[clap(
+        short = 'w',
+        long = "wordlist-url",
+        help = "Wordlist repository URL",
+        long_help = "Wordlist repository URL. The default value is 'https://raw.githubusercontent.com/hisbaan/wordlists/main'",
+        default_value = "https://raw.githubusercontent.com/hisbaan/wordlists/main"
+    )]
+    pub wordlist_url: String,
 }

src/langs.rs

@@ -64,6 +64,7 @@ pub static LOCALES: phf::Map<&'static str, &'static str> = phf_map! {
     "st" => "Sesotho",
     "sv" => "Swedish",
     "sw" => "Swahili",
+    "ta" => "Tamil",
     "tg" => "Tajik",
     "th" => "Thai",
     "tk" => "Turkmen",
@@ -129,6 +130,7 @@ pub static SUPPORTED_LANGS: phf::Map<&'static str, &'static str> = phf_map! {
     "st" => "Sesotho",
     "sv" => "Swedish",
     "sw" => "Swahili",
+    "ta" => "Tamil",
     "tg" => "Tajik",
     "tk" => "Turkmen",
     "tl" => "Tagalog",

src/lib.rs

@@ -17,6 +17,7 @@ pub fn yank(string: &str) {
         "freebsd",
         "netbsd",
         "dragonfly",
+        "mac osx",
         "netbsd",
         "openbsd",
         "solaris",

src/main.rs

@@ -58,7 +58,11 @@ fn run_app() -> std::result::Result<(), Error> {
 
     // Update all downloaded languages.
     if args.update_langs {
-        update_langs();
+        assert!(
+            !args.wordlist_url.ends_with("/"),
+            "URL should end with branch name in github without trailing /"
+        );
+        update_langs(args.wordlist_url);
         std::process::exit(0);
     }
 
@@ -88,7 +92,7 @@ fn run_app() -> std::result::Result<(), Error> {
     }
 
     if SUPPORTED_LANGS.contains_key(args.lang.as_str()) {
-        fetch_word_list(args.lang.to_owned());
+        fetch_word_list(args.lang.to_owned(), args.wordlist_url.to_owned());
     } else {
         // Not supported
         // Initialize new command.
@@ -110,14 +114,13 @@ fn run_app() -> std::result::Result<(), Error> {
         // Exit with error.
         clap::Error::exit(&error);
     }
-
     // Get word list. The program will only get here if/when this is a valid word list.
     let word_list = read_to_string(dirs::data_dir().unwrap().join("didyoumean").join(args.lang))
         .expect("Error reading file");
 
     // Get dictionary of words from words.txt.
     let dictionary = word_list.split('\n');
-
+    //assert!(dictionary.clone().count()>20,"Size of wordlist > 20 words");
     // Create mutable vecs for storing the top n words.
     let mut top_n_words = vec![""; args.number];
     let mut top_n_dists = vec![search_term.len() * 10; args.number];
@@ -224,7 +227,7 @@ fn run_app() -> std::result::Result<(), Error> {
 ///
 /// * `lang` - A locale code string to define the word list file to fetch.
 #[tokio::main]
-async fn fetch_word_list(lang: String) {
+async fn fetch_word_list(lang: String, wordlist_url: String) {
     // Get data directory.
     let data_dir = dirs::data_dir().unwrap().join("didyoumean");
 
@@ -243,11 +246,8 @@ async fn fetch_word_list(lang: String) {
             LOCALES.get(&lang).unwrap().to_string().blue()
         );
 
-        let url = format!(
-            "https://raw.githubusercontent.com/hisbaan/wordlists/main/{}",
-            &lang
-        );
-
+        let url = format!("{}/{}", wordlist_url, &lang);
+        println!("Accessing URL: {}", url);
         // Setup reqwest.
         let response = get(&url).await.expect("Request failed");
         let total_size = response.content_length().unwrap();
@@ -280,7 +280,7 @@ async fn fetch_word_list(lang: String) {
 }
 
 /// Update the word list files by deleting and downloading the files from the repository.
-fn update_langs() {
+fn update_langs(wordlist_url: String) {
     let data = data_dir().unwrap().join("didyoumean");
 
     // Create data directory if it doesn't exist.
@@ -299,7 +299,7 @@ fn update_langs() {
         // Only delete and download if the language is supported.
         if SUPPORTED_LANGS.contains_key(string) {
             remove_file(data.join(&string)).expect("Failed to update file (deletion failed)");
-            fetch_word_list(string.to_string());
+            fetch_word_list(string.to_string(), wordlist_url.to_string());
         }
     }
 }