- update code to support TA - Tamil language

- add README to show how to add new language - add option to download wordlist from different repository - add assertions for incorrectly downloaded files etc. - update README
hisbaan · Dec 19, 2023 · 549d6a0 · 549d6a0
1 parent 614d76c
commit 549d6a0
Show file tree

Hide file tree

Showing 5 changed files with 259 additions and 150 deletions.
diff --git a/README.md b/README.md
@@ -0,0 +1,101 @@
+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.
+
+```
+
+
+
diff --git a/src/cli.rs b/src/cli.rs
@@ -4,54 +4,62 @@ use clap::Parser;
 #[derive(Parser)]
 #[clap(author = "Hisbaan Noorani", version = "1.1.4", about = "Did You Mean: A cli spelling corrector", long_about = None)]
 pub struct Cli {
-    pub search_term: Option<String>,
-    #[clap(
-        short = 'n',
-        long = "number",
-        default_value_t = 5,
-        help = "Change the number of matches printed",
-        long_help = "Change the number of words the program will print. The default value is five."
-    )]
-    pub number: usize,
-    #[clap(
-        short = 'c',
-        long = "clean-output",
-        help = "Print clean output",
-        long_help = "Print a clean version of the output without the title, numbers or colour."
-    )]
-    pub clean_output: bool,
-    #[clap(
-        short = 'v',
-        long = "verbose",
-        help = "Print verbose output",
-        long_help = "Print verbose output including the edit distance of the found word to the queried word."
-    )]
-    pub verbose: bool,
-    #[clap(
-        short = 'y',
-        long = "yank",
-        help = "Yank (copy) to the system cliboard",
-        long_help = "Yank (copy) the selected word to the system clipboard. If no word is selected, the clipboard will not be altered."
-    )]
-    pub yank: bool,
-    #[clap(
-        short = 'l',
-        long = "lang",
-        help = "Select the desired language using the locale code (en, fr, sp, etc.)",
-        long_help = "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_value = "en"
-    )]
-    pub lang: String,
-    #[clap(
-        long = "print-langs",
-        help = "Display a list of supported languages",
-        long_help = "Display a list of supported languages and their respective locale codes."
-    )]
-    pub print_langs: bool,
-    #[clap(
-        long = "update-langs",
-        help = "Update all language files",
-        long_help = "Update all language files from the repository https://github.com/hisbaan/wordlists."
-    )]
-    pub update_langs: bool,
+  pub search_term: Option<String>,
+  #[clap(
+    short = 'n',
+    long = "number",
+    default_value_t = 5,
+    help = "Change the number of matches printed",
+    long_help = "Change the number of words the program will print. The default value is five."
+  )]
+  pub number: usize,
+  #[clap(
+    short = 'c',
+    long = "clean-output",
+    help = "Print clean output",
+    long_help = "Print a clean version of the output without the title, numbers or colour."
+  )]
+  pub clean_output: bool,
+  #[clap(
+    short = 'v',
+    long = "verbose",
+    help = "Print verbose output",
+    long_help = "Print verbose output including the edit distance of the found word to the queried word."
+  )]
+  pub verbose: bool,
+  #[clap(
+    short = 'y',
+    long = "yank",
+    help = "Yank (copy) to the system cliboard",
+    long_help = "Yank (copy) the selected word to the system clipboard. If no word is selected, the clipboard will not be altered."
+  )]
+  pub yank: bool,
+  #[clap(
+    short = 'l',
+    long = "lang",
+    help = "Select the desired language using the locale code (en, fr, sp, etc.)",
+    long_help = "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_value = "en"
+  )]
+  pub lang: String,
+  #[clap(
+    long = "print-langs",
+    help = "Display a list of supported languages",
+    long_help = "Display a list of supported languages and their respective locale codes."
+  )]
+  pub print_langs: bool,
+  #[clap(
+    long = "update-langs",
+    help = "Update all language files",
+    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,
 }
diff --git a/src/langs.rs b/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",