Exemple #1
0
/*
ComputeImpact return percentage of words in new revision compared to old
revision, using

	count_of_words_in_new
	/
	(count_of_words_in_old + count_of_words_in_new)

if no words are found in old and new revision, return 0.
*/
func ComputeImpact(oldrevid, newrevid string, wordlist []string) float64 {
	oldtext, _ := revision.GetContentClean(oldrevid)
	newtext, _ := revision.GetContentClean(newrevid)

	oldCnt := tekstus.StringCountTokens(oldtext, wordlist, false)
	newCnt := tekstus.StringCountTokens(newtext, wordlist, false)

	total := float64(oldCnt + newCnt)
	if total == 0 {
		return 0
	}

	return float64(newCnt) / total
}
Exemple #2
0
func TestStringCountTokens(t *testing.T) {
	for _, td := range dataStringCountTokens {
		got := tekstus.StringCountTokens(td.line, td.tokens, false)

		assert(t, td.exp, got, true)
	}
}
Exemple #3
0
/*
Compute number of good token in inserted text.
*/
func (ftr *GoodToken) Compute(dataset tabula.DatasetInterface) {
	col := dataset.GetColumnByName("additions")

	for _, rec := range col.Records {
		cnt := tekstus.StringCountTokens(rec.String(), tokens, false)

		ftr.PushBack(tabula.NewRecordInt(int64(cnt)))
	}
}