展开全部
有个小点的程序,只是统计字的 没有统e68a84e8a2ad3231313335323631343130323136353331333431343064计词的 可以参考下public class WordCount {
public HashMap count(File file) {
HashMap map = new HashMap();
long count = 0;
String regex = "[\\u4e00-\\u9fa5]";
try {
BufferedReader in = new BufferedReader(new FileReader(file));
String line = in.readLine();
while (line != null) {
Pattern p = Pattern.compile(regex);
Matcher m = p.matcher(line);
while (m.find()) {
count++;
String word = m.group();
if (map.containsKey(word)) {
map.put(word, map.get(word) + 1);
} else {
map.put(word, 1);
}
}
line = in.readLine();
}
} catch (Exception e) {
System.out.println("File error");
}
System.out.println("字数: " + count);
return map;
}
public static void main(String[] args) {
File file = new File("D:\\dou.txt");
WordCount wc = new WordCount();
System.out.println("使用汉字数目: " + wc.count(file).size());
}
}
运行结果:
文件内容: