考虑如下的两个字符串:
1. for(int i=0; i < b.size();i++){
2. do something in English(not necessary to be a sentence).
我们很容易就看出来,第一个是java代码,第二个则是英文句子。那么计算机程序有事如何区分这两者的呢?
java code可能不可解析,因为它是一段完整的方法(或声明或表达式),下面提供了这个问题的解决方法。有时,Java代码和英文单词并没有完全划清楚的界限,这中解决方案并不是100%的准确可靠。然而,这样的解决方案你只需要根据你业务需求稍作调整就能满足你的要求,你也可以从GitHub下载相关代码。
这方案的基本思想就是将字符串转成一组标记符号。比如,上面的代码可能会成为:“KEY,SEPARATOR,ID,ASSIGN,NUMBER,SEPARATOT,…”,然后再使用一些简单的规则就能把Java代码从英文中区分出来。
下面提供一个可将字符串转换为一组标记的Tokenizer类。
package lexical;
import java.util.LinkedList;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class Tokenizer {
private class TokenInfo {
public final Pattern regex;
public final int token;
public TokenInfo(Pattern regex, int token) {
super();
this.regex = regex;
this.token = token;
}
}
public class Token {
public final int token;
public final String sequence;
public Token(int token, String sequence) {
super();
this.token = token;
this.sequence = sequence;
}
}
private LinkedList<TokenInfo> tokenInfos;
private LinkedList<Token> tokens;
public Tokenizer() {
tokenInfos = new LinkedList<TokenInfo>();
tokens = new LinkedList<Token>();
}
public void add(String regex, int token) {
tokenInfos
.add(new TokenInfo(Pattern.compile("^(" + regex + ")"), token));
}
public void tokenize(String str) {
String s = str.trim();
tokens.clear();
while (!s.equals("")) {
//System.out.println(s);
boolean match = false;
for (TokenInfo info : tokenInfos) {
Matcher m = info.regex.matcher(s);
if (m.find()) {
match = true;
String tok = m.group().trim();
s = m.replaceFirst("").trim();
tokens.add(new Token(info.token, tok));
break;
}
}
if (!match){
//throw new ParserException("Unexpected character in input: " + s);
tokens.clear();
System.out.println("Unexpected character in input: " + s);
return;
}
}
}
public LinkedList<Token> getTokens() {
return tokens;
}
public String getTokensString() {
StringBuilder sb = new StringBuilder();
for (Tokenizer.Token tok : tokens) {
sb.append(tok.token);
}
return sb.toString();
}
}
我们可以通过Java关键字,运算符,标示符,分隔符,等等。并分配一个映射值的标示符(用于存储Java的关键字),这样以来就很容易区分Java代码和英文了。
package lexical;
import greenblocks.javaapiexamples.DB;
import java.io.IOException;
import java.sql.ResultSet;
import java.sql.SQLException;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import org.apache.commons.lang.StringUtils;
import NLP.POSTagger;
public class EnglishOrCode {
private static Tokenizer tokenizer = null;
public static void initializeTokenizer() {
tokenizer = new Tokenizer();
//key words
String keyString = "abstract assert boolean break byte case catch "
+ "char class const continue default do double else enum"
+ " extends false final finally float for goto if implements "
+ "import instanceof int interface long native new null "
+ "package private protected public return short static "
+ "strictfp super switch synchronized this throw throws true "
+ "transient try void volatile while todo";
String[] keys = keyString.split(" ");
String keyStr = StringUtils.join(keys, "|");
tokenizer.add(keyStr, 1);
tokenizer.add("\\(|\\)|\\{|\\}|\\[|\\]|;|,|\\.|=|>|<|!|~|"
+ "\\?|:|==|<=|>=|!=|&&|\\|\\||\\+\\+|--|"
+ "\\+|-|\\*|/|&|\\||\\^|%|\'|\"|\n|\r|\\$|\\#",
2);//separators, operators, etc
tokenizer.add("[0-9]+", 3); //number
tokenizer.add("[a-zA-Z][a-zA-Z0-9_]*", 4);//identifier
tokenizer.add("@", 4);
}
public static void main(String[] args) throws SQLException, ClassNotFoundException, IOException {
initializeTokenizer();
String s = "do something in English";
if(isEnglish(s)){
System.out.println("English");
}else{
System.out.println("Java Code");
}
s = "for (int i = 0; i < b.size(); i++) {";
if(isEnglish(s)){
System.out.println("English");
}else{
System.out.println("Java Code");
}
}
private static boolean isEnglish(String replaced) {
tokenizer.tokenize(replaced);
String patternString = tokenizer.getTokensString();
if(patternString.matches(".*444.*") || patternString.matches("4+")){
return true;
}else{
return false;
}
}
}
输出结果:
English
Java Code