| 1 | // Copyright (c) 2019-2024 Alexander Medvednikov. All rights reserved. |
| 2 | // Use of this source code is governed by an MIT license |
| 3 | // that can be found in the LICENSE file. |
| 4 | import os |
| 5 | |
| 6 | fn main() { |
| 7 | mut path := 'cinderella.txt' |
| 8 | if os.args.len != 2 { |
| 9 | println('usage: word_counter [text_file]') |
| 10 | println('using ${path}') |
| 11 | } else { |
| 12 | path = os.args[1] |
| 13 | } |
| 14 | contents := os.read_file(path.trim_space()) or { |
| 15 | println('failed to open ${path}') |
| 16 | return |
| 17 | } |
| 18 | mut m := map[string]int{} |
| 19 | for word in extract_words(contents) { |
| 20 | m[word]++ |
| 21 | } |
| 22 | // Sort the keys |
| 23 | mut keys := m.keys() |
| 24 | keys.sort() |
| 25 | // Print the map |
| 26 | for key in keys { |
| 27 | val := m[key] |
| 28 | println('${key} => ${val}') |
| 29 | } |
| 30 | } |
| 31 | |
| 32 | // Creates an array of words from a given string |
| 33 | fn extract_words(contents string) []string { |
| 34 | mut splits := []string{} |
| 35 | for space_split in contents.to_lower().split(' ') { |
| 36 | if space_split.contains('\n') { |
| 37 | splits << space_split.split('\n') |
| 38 | } else { |
| 39 | splits << space_split |
| 40 | } |
| 41 | } |
| 42 | |
| 43 | mut results := []string{} |
| 44 | for s in splits { |
| 45 | result := filter_word(s) |
| 46 | if result == '' { |
| 47 | continue |
| 48 | } |
| 49 | results << result |
| 50 | } |
| 51 | |
| 52 | return results |
| 53 | } |
| 54 | |
| 55 | // Removes punctuation |
| 56 | fn filter_word(word string) string { |
| 57 | if word == '' || word == ' ' { |
| 58 | return '' |
| 59 | } |
| 60 | mut i := 0 |
| 61 | for i < word.len && !word[i].is_letter() { |
| 62 | i++ |
| 63 | } |
| 64 | start := i |
| 65 | for i < word.len && word[i].is_letter() { |
| 66 | i++ |
| 67 | } |
| 68 | end := i |
| 69 | return word[start..end] |
| 70 | } |
| 71 | |