implements an option to preserve order of original list, rather than …

…sort alphabetically

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "tidy"
-version = "0.2.22"
+version = "0.2.30"
 authors = ["sts10 <sschlinkert@gmail.com>"]
 edition = "2021"
 
@@ -9,3 +9,4 @@ clap = { version = "3.0.14", features = ["derive"] }
 memchr = "2.4"
 radix_fmt = "1.0.0"
 rand = "0.8.4"
+itertools = "0.10.3"

readme.markdown

@@ -21,7 +21,7 @@ Given a text file with a word list, this tool will create a new word list in whi
 -   duplicate lines (words) are removed
 -   empty lines have been removed
 -   whitespace from beginning and end of words is deleted
--   words are sorted alphabetically
+-   words are sorted alphabetically (though this can be optionally prevented -- see below)
 
 and print that new word list to the terminal or to a new text file.
 
@@ -43,6 +43,8 @@ Optionally, the tool can...
 -   print corresponding dice rolls before words, separated by a tab. Dice can have 2 to 36 sides. (`-D`)
 -   print information about the new list, such as entropy per word, to the terminal (`-A`)
 
+If you do NOT want Tidy to sort list alphabetically, you can use the `--no-alpha` option.
+
 ## Usage
 
 ```txt
@@ -122,6 +124,10 @@ OPTIONS:
             Path for outputted list file. If none given, generated word list will be printed to
             terminal
 
+    -O, --no-alpha
+            Do NOT sort outputted list alphabetically. Preserves original list order. Note that
+            duplicates lines and blank lines will still be removed
+
     -P, --remove-prefix
             Remove prefix words from new list
 
@@ -182,6 +188,8 @@ OPTIONS:
 
 -   `tidy -lPi -o new_list.txt inputted_word_list.txt` Same as above, but the added `-i` flag deletes any integers in words. Words with integers in them are not removed, only the integers within them. For example, "11326 agency" becomes "agency".
 
+-   `tidy -lPiO -o new_list.txt inputted_word_list.txt` Same as above, but the added `-O` flag preserves the original order of the list, rather than sort it alphabetically. Note that duplicates and blank lines are still removed.
+
 -   `tidy -I -o new_list.txt inputted_word_list.txt` Using the `-I` flag removes any words with integers from the list. For example, "hello1" would be removed from the list.
 
 -   `tidy -AA -I -o new_list.txt inputted_word_list.txt` Adding `-AA` prints some information about the created list to the terminal.

src/lib.rs

@@ -15,6 +15,7 @@ pub struct TidyRequest {
     pub list: Vec<String>,
     pub take_first: Option<usize>,
     pub take_rand: Option<usize>,
+    pub sort_alphabetically: bool,
     pub to_lowercase: bool,
     pub should_straighten_quotes: bool,
     pub should_remove_prefix_words: bool,
@@ -232,13 +233,13 @@ pub fn tidy_list(req: TidyRequest) -> Vec<String> {
         None => tidied_list,
     };
     tidied_list = if req.should_remove_suffix_words {
-        remove_suffix_words(sort_and_dedup(&mut tidied_list))
+        remove_suffix_words(dedup_without_sorting(&mut tidied_list))
     } else {
         tidied_list
     };
 
     tidied_list = if req.should_remove_prefix_words {
-        remove_prefix_words(sort_and_dedup(&mut tidied_list))
+        remove_prefix_words(dedup_without_sorting(&mut tidied_list))
     } else {
         tidied_list
     };
@@ -250,7 +251,12 @@ pub fn tidy_list(req: TidyRequest) -> Vec<String> {
     };
 
     // Sort and dedup here
-    tidied_list = sort_and_dedup(&mut tidied_list);
+    // tidied_list = sort_and_dedup(&mut tidied_list);
+
+    if req.sort_alphabetically {
+        tidied_list.sort();
+    }
+    tidied_list = dedup_without_sorting(&mut tidied_list);
 
     // User can cut words from nearly finished list.
     // Does so randomly.
@@ -264,7 +270,11 @@ pub fn tidy_list(req: TidyRequest) -> Vec<String> {
         None => tidied_list,
     };
     // Finally, sort and dedup list (for final time)
-    tidied_list = sort_and_dedup(&mut tidied_list);
+    // tidied_list = sort_and_dedup(&mut tidied_list);
+    if req.sort_alphabetically {
+        tidied_list.sort();
+    }
+    tidied_list = dedup_without_sorting(&mut tidied_list);
     tidied_list
 }
 
@@ -433,15 +443,11 @@ fn straighten_quotes(input: &str) -> String {
     result
 }
 
-/// Alphabetizes and de-duplicates a Vector of `String`s.
-///
-/// For Rust's [`dedup()`](https://doc.rust-lang.org/std/vec/struct.Vec.html#method.dedup)
-/// function to remove all duplicates, the Vector needs to be
-/// [`sort()`](https://doc.rust-lang.org/std/vec/struct.Vec.html#method.sort)ed first.
-fn sort_and_dedup(list: &mut Vec<String>) -> Vec<String> {
-    list.sort();
-    list.dedup();
-    list.to_vec()
+use itertools::Itertools;
+/// De-duplicates a Vector of `String`s while maintaining list order.
+fn dedup_without_sorting(list: &mut [String]) -> Vec<String> {
+    let dedup: Vec<String> = list.iter().unique().map(|s| s.to_string()).collect();
+    dedup.to_vec()
 }
 
 /// Remove prefix words from the given Vector of `String`s.

src/main.rs

@@ -61,6 +61,11 @@ struct Args {
     #[clap(long = "samples")]
     samples: bool,
 
+    /// Do NOT sort outputted list alphabetically. Preserves original list order.
+    /// Note that duplicates lines and blank lines will still be removed.
+    #[clap(short = 'O', long = "no-alpha")]
+    no_alpha: bool,
+
     /// Lowercase all words on new list
     #[clap(short = 'l', long = "lowercase")]
     to_lowercase: bool,
@@ -218,6 +223,7 @@ fn main() {
         list: make_vec_from_filenames(&opt.inputted_word_list),
         take_first: opt.take_first,
         take_rand: opt.take_rand,
+        sort_alphabetically: !opt.no_alpha,
         to_lowercase: opt.to_lowercase,
         should_straighten_quotes: opt.straighten_quotes,
         should_remove_prefix_words: opt.remove_prefix_words,

tests/list_manipulation_tests.rs

@@ -65,6 +65,7 @@ mod list_manipulation_tests {
     fn can_sort_words_alphabetically() {
         let this_tidy_request = TidyRequest {
             list: make_lists().0,
+            sort_alphabetically: true,
             ..Default::default()
         };
         let new_list = tidy_list(this_tidy_request);
@@ -73,6 +74,19 @@ mod list_manipulation_tests {
         assert!(new_list[new_list.len() - 1] == "zookeeper".to_string());
     }
 
+    #[test]
+    fn respect_option_to_not_sort_alphabetically() {
+        let this_tidy_request = TidyRequest {
+            list: make_lists().0,
+            sort_alphabetically: false,
+            ..Default::default()
+        };
+        let new_list = tidy_list(this_tidy_request);
+        assert!(new_list[0] == "zookeeper".to_string());
+        assert!(new_list.contains(&"apple".to_string()));
+        assert!(new_list[new_list.len() - 1] == "station".to_string());
+    }
+
     #[test]
     fn removes_blank_lines() {
         let this_tidy_request = TidyRequest {