java - 只输出中文, 包含中文标点符号
在 Java 中直接使用Unicode 转码时会按照UTF-16LE 的方式拆分,并加上 BOM。 如果采用 UTF-16 拆分,在 Java 中默认采用带有 BOM 的 UTF-16BE 拆分。
String a ="12dss显示,‘;()中文只"; StringBuffer b = new StringBuffer(); for(int i = 0;i<a.length();i++) { char t = a.charAt(i); String str = String.valueOf(t); if(str.getBytes().length ==2) { b.append(str); } } System.out.println(b);
结果: 显示‘;()中文只
java:获取字符串中第一个汉字和第一个汉字汉字标点符号的位置?
package tool; public class CopyCat { public static void main ( String[] args ) { String string = "adf你.?的说法sdf"; String reg = "[\u4e00-\u9fa5]"; int index = -1; if (string.matches (".*" + reg + ".*")) { index = string.split (reg)[0].length (); } System.out.println (index); String regex = "[。,!?()《》……、:——【】;’”‘“]"; int ind = -1; if (string.matches (".*" + regex + ".*")) { ind = string.split (regex)[0].length (); } System.out.println (ind); } }
常用汉字 的unicode 码范围是:\u4e00-\u9fa5,下面一个例子是把中英文文档中的汉字提取出来的简单例子:
public class DrawEnglish
{
private static String draw(String content)
{
StringBuffer english = new StringBuffer();
String regex = "[\u4e00-\u9fa5。,?”“《》:!——-、]";
Pattern pattern = Pattern.compile(regex);
Matcher matcher = pattern.matcher(content);
while(matcher.find())
{
String temp = matcher.group();
english.append(temp);
}
return english.toString();
}
public static void drawEnglish(String path)
{
FileInputStream fr;
BufferedReader br;
FileWriter fw;
BufferedWriter bw = null ;
try
{
fr = new FileInputStream(path);
br = new BufferedReader(new InputStreamReader(fr,"gb2312"));
fw = new FileWriter("new1.txt");
bw = new BufferedWriter(fw);
String str = null;
StringBuffer sb = new StringBuffer();
while((str = br.readLine()) != null)
{
sb.append(str + "\n");
}
String temp = draw(sb.toString());
bw.write(temp);
} catch (FileNotFoundException e)
{
e.printStackTrace();
} catch (IOException e)
{
e.printStackTrace();
}
finally
{
try
{
if(bw != null) bw.close();
} catch (IOException e)
{
e.printStackTrace();
}
}
}
public static void main(String[] args)
{
drawEnglish("draw1.txt");
}
}