内容简介:DFA:确定有穷自动机。具体功能:
DFA:确定有穷自动机。
具体功能:
- 将敏感词汇保存在map中。
- 对敏感词汇进行过滤,将敏感词变为“*”。
- 对无意义符号进行忽略处理。
敏感词数据结构:
{ 王:{
isEnd: false
八:{
isEnd:false
蛋:{
isEnd:true
}
}
}
}
无意义符号数据结构:
{
"@":Null (空结构体)
}
package main
import (
"fmt"
"strings"
)
type Null struct {}
var sensitiveWord = make(map[string]interface{})
var Set = make(map[string]Null)
const InvalidWords = " ,~,!,@,#,$,%,^,&,*,(,),_,-,+,=,?,<,>,.,—,,,。,/,\\,|,《,》,?,;,:,:,',‘,;,“,"
var InvalidWord = make(map[string]Null) //无效词汇,不参与敏感词汇判断直接忽略
//生成违禁词集合
func AddSensitiveToMap(set map[string]Null){
for key := range set {
str := []rune(key)
nowMap := sensitiveWord
for i := 0; i < len(str); i++ {
if _,ok := nowMap[string(str[i])]; !ok {//如果该key不存在,
thisMap := make(map[string]interface{})
thisMap["isEnd"] = false
nowMap[string(str[i])] = thisMap
nowMap = thisMap
}else {
nowMap = nowMap[string(str[i])].(map[string]interface{})
}
if i == len(str)-1 {
nowMap["isEnd"] = true
}
}
}
}
//敏感词汇转换为*
func ChangeSensitiveWords(txt string,sensitive map[string]interface{}) (word string){
str := []rune(txt)
nowMap := sensitive
start := -1
tag := -1
for i := 0; i < len(str); i++ {
if _, ok:= InvalidWord[(string(str[i]))]; ok || string(str[i]) == "," {
continue
}
if thisMap, ok :=nowMap[string(str[i])].(map[string]interface{}); ok {
tag++
if tag == 0 {
start = i
}
isEnd, _ := thisMap["isEnd"].(bool)
if isEnd {
for y := start; y < i+1; y++ {
str[y] = 42
}
nowMap = sensitive
start = -1
tag = -1
}else{
nowMap = nowMap[string(str[i])].(map[string]interface{})
}
}else{
if start != -1 {
i = start + 1
}
nowMap = sensitive
start = -1
tag = -1
}
}
return string(str)
}
func main() {
words := strings.Split(InvalidWords,",")
for _, v := range words {
InvalidWord[v] = Null{}
}
Set["你妈逼的"] = Null{}
Set["你妈"] = Null{}
Set["日"] = Null{}
AddSensitiveToMap(Set)
text := "文明用语你&* 妈,逼的你这个狗日的,怎么这么傻啊。我也是服了,我日,这些话我都说不出口"
fmt.Println(ChangeSensitiveWords(text,sensitiveWord))
}
以上就是本文的全部内容,希望对大家的学习有所帮助,也希望大家多多支持 码农网
猜你喜欢:- NLTK学习笔记(五):分类和标注词汇
- 请收好这份NLP热门词汇解读
- 分享一次专业领域词汇的无监督挖掘
- Python TfidfVectorizer throw:空词汇;也许文件只包含停用词“
- 某口腔app发现了不友善词汇(f*ckMobile)
- 程序员写简历时必须注意的技术词汇拼写(持续更新...)
本站部分资源来源于网络,本站转载出于传递更多信息之目的,版权归原作者或者来源机构所有,如转载稿涉及版权问题,请联系我们。
Traction: A Startup Guide to Getting Customers
Gabriel Weinberg、Justin Mares / S-curves Publishing / 2014-8-25 / USD 14.99
Most startups end in failure. Almost every failed startup has a product. What failed startups don't have is traction -- real customer growth. This book introduces startup founders and employees to......一起来看看 《Traction: A Startup Guide to Getting Customers》 这本书的介绍吧!