func getWords(filePath string, tokenizer *goseg.Tokenizer) ([]string, error) {
bytes, err := ioutil.ReadFile(filePath)
if err != nil {
return nil, err
}
words := tokenizer.Cut([]rune(string(bytes)))
return analyzer.Normalize(words, cutset), nil
}
func main() {
classifier := bayesian.NewClassifier(Good, Bad)
tokenizer, err := goseg.NewTokenizerFromFile(dictDataFilePath)
if err != nil {
log.Fatal(err)
}
for _, item := range trainingData {
log.Printf("Traning %s", item.folder)
totalNum := 0
var totalSize int64
startTime := time.Now()
fis, err := ioutil.ReadDir(item.folder)
if err != nil {
log.Fatal(err)
}
for _, fi := range fis {
if fi.IsDir() {
continue
}
totalSize += fi.Size()
filePath := filepath.Join(item.folder, fi.Name())
mail := mailfile.NewPOP3Mail(filePath)
if err = mail.Parse(); err != nil {
log.Fatal(err)
}
post, err := mailpost.Parse(mail)
mail.Close()
if err != nil {
log.Fatalf("Err: %v, Mail:%s", err, mail.Path())
}
words := analyzer.Normalize(tokenizer.Cut([]rune(post.Subject+" "+post.Content)), cutset)
classifier.Learn(words, item.class)
totalNum += 1
}
elapsed := time.Now().Sub(startTime)
fmt.Printf("TotalNum: %d\n", totalNum)
fmt.Printf("Elapsed: %s, TPS(Mail): %f, TPS(FileSize): %s\n",
time.Now().Sub(startTime),
float64(totalNum)/(float64(elapsed)/float64(time.Second)),
fileutil.Humanize(uint64(float64(totalSize)/(float64(elapsed)/float64(time.Second)))))
}
classifier.WriteToFile(output)
}