// sample-wordcount.go: counts words in text, including non-ASCII text.
// Free sample from 99helpers.com/file-types/go
//
// Its tests are in sample-wordcount_test.go. Keep both in the same folder:
//
//	go run sample-wordcount.go
//	go test -v sample-wordcount.go sample-wordcount_test.go
package main

import (
	"cmp"
	"fmt"
	"slices"
	"strings"
	"unicode"
	"unicode/utf8"
)

// WordCount is one word and how often it appears.
type WordCount struct {
	Word  string
	Count int
}

// CountWords splits text into words (runs of letters and digits), folds
// them to lower case and counts each one. Go strings are UTF-8, and
// unicode.IsLetter works for every script, so "Café" and "東京" are words.
func CountWords(text string) map[string]int {
	counts := make(map[string]int)
	words := strings.FieldsFunc(text, func(r rune) bool {
		return !unicode.IsLetter(r) && !unicode.IsDigit(r)
	})
	for _, w := range words {
		counts[strings.ToLower(w)]++
	}
	return counts
}

// TopWords returns the n most frequent words, most frequent first, with
// ties in alphabetical order so the result is always the same.
func TopWords(counts map[string]int, n int) []WordCount {
	list := make([]WordCount, 0, len(counts))
	for w, c := range counts {
		list = append(list, WordCount{w, c})
	}
	slices.SortFunc(list, func(a, b WordCount) int {
		if c := cmp.Compare(b.Count, a.Count); c != 0 {
			return c
		}
		return strings.Compare(a.Word, b.Word)
	})
	return list[:min(n, len(list))]
}

func main() {
	text := "The café opens at nine. The CAFÉ closes at six; café au lait costs €3. " +
		"Der Bäcker backt, der Bäcker verkauft. 東京 東京 大阪"

	for _, wc := range TopWords(CountWords(text), 5) {
		// len counts bytes; utf8.RuneCountInString counts characters.
		fmt.Printf("%-8s %d  (%d bytes, %d runes)\n", wc.Word, wc.Count,
			len(wc.Word), utf8.RuneCountInString(wc.Word))
	}
}