docs: Added CHANGELOG

CHANGELOG.md

@@ -0,0 +1,5 @@
+# Changelog
+
+## v1.0.0
+
+- Initial release

README.md

@@ -12,7 +12,7 @@ gleam add lancaster_stemmer@1
 import lancaster_stemmer
 
 pub fn main() -> Nil {
-  // TODO: An example of the project in use
+  lancaster_stemmer.stem("breathe", lancaster_stemmer.default_rules())
 }
 ```
 

src/lancaster_stemmer.gleam

@@ -237,18 +237,26 @@ const default_rules_list = [
   ),
 ]
 
-pub fn main() {
+/// Constructs the default ruleset
-  io.println("Hello from paicehusk!")
-  let assert Ok(rules) = load_rules("paice-husk-rules.txt")
-  stem("abominable", rules)
-  |> echo
-}
-
 pub fn default_rules() -> Rules {
   dict.from_list(default_rules_list)
 }
 
+/// Lancaster (Paice-Husk) stemming algorithm
+///
+/// ## Example
+///
+/// ```gleam
+/// lancaster_stemmer.stem("Gleam", lancaster_stemmer.stem.default_rules())
+/// // -> gleam
+/// ```
+///
+/// ```gleam
+/// lancaster_stemmer.stem("fancy", lancaster_stemmer.stem.default_rules())
+/// // -> fant
+/// ```
 pub fn stem(word: String, rules: Rules) -> String {
+  let word = string.lowercase(word)
   case is_valid(word) {
     True -> {
       do_stem(word, rules, True)
@@ -333,6 +341,21 @@ fn is_valid_internal(word: String, length: Int) -> Bool {
   }
 }
 
+/// Constructs a ruleset from the specified file
+///
+/// Format of the file is as follows:
+/// Each line contains a specific rule (order matters)
+/// The rule consists of a string made up of the following parts
+/// | Rule part | Description |
+/// | ------ | ------ |
+/// |suffix|the reverse of the required suffix, e.g. the suffix for winning, ing would be specified gni|
+/// |* (optional)|if the rule is only to be used if a previous rule has not been applied then add an asterisk. For example ht*2. only applies if th is the final suffix, so the stem of breath would be brea but the stem of breathe would be breath because the suffix e has already been removed|
+/// |number of chars to remove|this is the number of characters to remove after the suffix has been matched. For example psychoanalytic has the suffix ytic of which 3 characters should be removed to retain psychoanaly, this would be 'city3'. This can be 0|
+/// |append string (optional)|this is the characters that are appended after the match and removal of characters|
+/// |> or .|If > then you can continue stemming process after this one, if . then stemming stops|
+///
+/// So for example with the `psychoanalytic` stem of `psychoanalys` the rule would be `ytic3s.`
+///
 pub fn load_rules(filename: String) -> Result(Rules, Nil) {
   case simplifile.read(filename) {
     Error(_) -> Error(Nil)

test/lancaster_stemmer_test.gleam

@@ -1,4 +1,7 @@
 import gleeunit
+import lancaster_stemmer
+import simplifile
+import splitter
 
 pub fn main() -> Nil {
   gleeunit.main()
@@ -6,8 +9,29 @@ pub fn main() -> Nil {
 
 // gleeunit test functions end in `_test`
 pub fn hello_world_test() {
-  let name = "Joe"
+  let line_split = splitter.new(["\n", "\r\n"])
-  let greeting = "Hello, " <> name <> "!"
+  let row_split = splitter.new([" ", "\t"])
-
+  let rules = lancaster_stemmer.default_rules()
-  assert greeting == "Hello, Joe!"
+  let assert Ok(tests) = simplifile.read("./test/wordlist.txt")
+  run_test(tests, line_split, row_split, rules)
+}
+
+fn run_test(
+  tests: String,
+  line_split: splitter.Splitter,
+  row_split: splitter.Splitter,
+  rules: lancaster_stemmer.Rules,
+) -> Nil {
+  case splitter.split(line_split, tests) {
+    #("", "", "") -> Nil
+    #(line, _, rest) -> {
+      case splitter.split(row_split, line) |> echo {
+        #("", "", "") -> Nil
+        #(word, _, stem) -> {
+          assert lancaster_stemmer.stem(word, rules) == stem
+        }
+      }
+      run_test(rest, line_split, row_split, rules)
+    }
+  }
 }