python 英语分词_Porter：一个好用的英文分词算法

The Porter Stemming Algorithm 已有多种语言实现

porterstemmer 示例

from porterstemmer import Stemmer

stemmer = Stemmer()

print stemmer("foo")

print stemmer(u"foo")

print stemmer("er")

print stemmer(u"er")

print stemmer("")

print stemmer(u'')

try:

stemmer()

except:

print "exception raised."

try:

stemmer(None)

except:

print "exception raised."

package main

import (

"bufio"

"github.com/agonopol/go-stem"

"os"

)

func main() {

in := bufio.NewReader(os.Stdin)

out := bufio.NewWriter(os.Stdout)

defer out.Flush()

for word, err := in.ReadSlice('\n'); err == nil; word, err = in.ReadSlice('\n') {

out.Write(stemmer.Stem(word))

out.WriteString("\n")

}

}