Adar shaked word frequency ex

src/main.rs

@@ -2,6 +2,7 @@ mod testing_resources;
 
 use clap::Parser;
 use std::fs;
+use std::collections::HashMap;
 
 /// wc impl in rust
 #[derive(Parser, Debug)]
@@ -19,34 +20,56 @@ struct Args {
     #[arg(short = 'w')]
     should_words: bool,
 
+    /// Print the number of words in each input file
+    #[arg(short = 'f')]
+    should_frequency: bool,
+
     /// Paths to input files we want to `wc`. If more than one input file is
     /// specified, a line of cumulative counts for all the files is displayed
     /// on a separate line after the output for the last file.
     paths: Vec<String>,
 }
 
+impl Args {
+    // validate the input arguments
+    fn validate_args(&self) -> Result<(), String> {
+        if self.should_frequency && (self.should_characters || self.should_lines || self.should_words) {
+            return Err("should_frequency is mutually exclusive".to_string());
+        }
+        Ok(())
+    }
+}
+
 fn main() {
     let parsed_args = Args::parse();
     let should_words: bool;
     let should_lines: bool;
     let should_characters: bool;
+    let should_frequency: bool;
     let mut should_exit_with_err: bool = false;
-    if !parsed_args.should_characters && !parsed_args.should_lines && !parsed_args.should_words {
+
+    //validate the input arguments
+    parsed_args.validate_args().unwrap();
+
+    if !parsed_args.should_characters && !parsed_args.should_lines && !parsed_args.should_words && !parsed_args.should_frequency {
         // Compat with wc behavior, no flags passed means all these should be on.
         should_characters = true;
         should_lines = true;
         should_words = true;
+        should_frequency = false;
     } else {
         should_characters = parsed_args.should_characters;
         should_lines = parsed_args.should_lines;
         should_words = parsed_args.should_words;
+        should_frequency = parsed_args.should_frequency;
     }
 
     let mut total_words: usize = 0;
     let mut total_lines: usize = 0;
     let mut total_characters: usize = 0;
+    let mut words_frequency: HashMap<String, u64> = HashMap::new();
     for path in parsed_args.paths.iter() {
-        let file_contents = match fs::read_to_string(path) {
+        let file_contents = match fs::read_to_string(path.clone()) {
             Ok(x) => x,
             Err(e) => {
                 eprint!("wc: {}: {}", path, e.to_string());
@@ -69,8 +92,16 @@ fn main() {
             total_characters += characters_in_this_content;
             print!("{:>8}", characters_in_this_content);
         }
-        println!(" {}", path)
+        if should_frequency {
+            count_and_update_word_frequency_for_content(&mut words_frequency, file_contents);
+        } else {
+            println!(" {}", path)
+        }   
+    }
+    if should_frequency {
+        print_top_frequent_words(&mut words_frequency);
     }
+
     // Now if more than 1 path, print total
     if parsed_args.paths.len() > 1 {
         if should_lines {
@@ -82,13 +113,30 @@ fn main() {
         if should_characters {
             print!("{:>8}", total_characters);
         }
-        println!(" total")
+        if !should_frequency {
+            println!(" total")
+        }
     }
     if should_exit_with_err {
         std::process::exit(0x00000001);
     }
 }
 
+fn print_top_frequent_words(words_frequency: &mut HashMap<String, u64>) {
+    let mut words_frequency_vec: Vec<(&String, &u64)> = words_frequency.iter().collect();
+    words_frequency_vec.sort_by(|word_tuple_a, word_tuple_b| word_tuple_b.1.cmp(word_tuple_a.1));
+    for (word, count) in words_frequency_vec.iter().take(10) {
+        println!("{:>8} {}", count, word);
+    }
+}
+
+fn count_and_update_word_frequency_for_content(words_frequency: &mut HashMap<String, u64>, file_contents: String) {
+    for word in file_contents.split_whitespace() {
+        let count = words_frequency.entry(word.to_string()).or_insert(0);
+        *count += 1;
+    }
+}
+
 fn count_lines_in_content(content: &str) -> usize {
     // My initial implementation
     // content.split('\n').fold(0, |lines: u64, _x| lines + 1)
@@ -108,6 +156,7 @@ fn count_words_in_content(content: &str) -> usize {
 
 #[cfg(test)]
 mod tests {
+    use std::path::Path;
     use crate::testing_resources::EXAMPLE_CONTENT_EMPTY;
     use crate::testing_resources::EXAMPLE_CONTENT_FIVE_WORDS;
     use crate::testing_resources::EXAMPLE_CONTENT_TEN_CHARS;
@@ -132,4 +181,23 @@ mod tests {
         assert_eq!(10, count_characters_in_content(EXAMPLE_CONTENT_TEN_CHARS));
         assert_eq!(0, count_characters_in_content(EXAMPLE_CONTENT_EMPTY));
     }
+
+    #[test]
+    fn test_word_frequency_licence_file() {
+        let mut words_frequency: HashMap<String, u64> = HashMap::new();
+
+        let licence_path = Path::new("LICENSE");
+        let file_contents = fs::read_to_string(licence_path).unwrap();
+        count_and_update_word_frequency_for_content(&mut words_frequency, file_contents.to_string());
+        assert_eq!(309, *words_frequency.get("the").unwrap());
+        assert_eq!(208, *words_frequency.get("of").unwrap());
+        assert_eq!(174, *words_frequency.get("to").unwrap());
+        assert_eq!(165, *words_frequency.get("a").unwrap());
+        assert_eq!(131, *words_frequency.get("or").unwrap());
+        assert_eq!(102, *words_frequency.get("you").unwrap());
+        assert_eq!(89, *words_frequency.get("that").unwrap());
+        assert_eq!(86, *words_frequency.get("and").unwrap());
+        assert_eq!(72, *words_frequency.get("this").unwrap());
+        assert_eq!(70, *words_frequency.get("in").unwrap());
+    }
 }