import java.io.*;
import java.util.*;
class A {
public static void main(String args[]) throws Exception {
Console con = System.console();
String str;
int i=0;
HashMap map = new HashMap();
HashSet set = new HashSet();
System.out.println("Enter File Name : ");
str = con.readLine();
File f = new File(str);
f.createNewFile();
FileInputStream fis = new FileInputStream(str);
StreamTokenizer st = new StreamTokenizer(fis);
while(st.nextToken()!=StreamTokenizer.TT_EOF) {
String s;
switch(st.ttype) {
case StreamTokenizer.TT_NUMBER: s = st.nval+"";
break;
case StreamTokenizer.TT_WORD: s = st.sval;
break;
default: s = ""+((char)st.ttype);
}
map.put(i+"",s);
set.add(s);
i++;
}
Iterator iter = set.iterator();
System.out.println("Frequency Of Words :");
while(iter.hasNext()) {
String word;
int count=0;
word=(String)iter.next();
for(int j=0; j<i ; j++) {
String word2;
word2=(String)map.get(j+"");
if(word.equals(word2))
count++;
}
System.out.println(" WORD : "+ word+" = "+count);
}
System.out.println("Total Words In Files: "+i);
}
}
在此代码中我首先创建了一个包含以下数据的文本文件:
@Hello Hii World#* c ++ java salesforce
这段代码的输出是:
**单词频率:
WORD:#= 1
WORD:@ = 1
WORD:c = 1
WORD:salesforce = 1
WORD:* = 1
WORD:这= 1
WORD:+ = 2
WORD:java = 1
WORD:世界= 1
WORD:你好= 1
文件中的总字数:11 **
在哪里我无法找到为什么这显示c ++作为一个单独的单词。我想将c ++组合为输出中的单个单词
你可以这样做
// Create the file at path specified in the String str
// ...
HashMap<String, Integer> map = new HashMap<>();
InputStream fis = new FileInputStream(str);
Reader bufferedReader = new BufferedReader(new InputStreamReader(fis));
StreamTokenizer st = new StreamTokenizer(bufferedReader);
st.wordChars('+', '+');
while(st.nextToken() != StreamTokenizer.TT_EOF) {
String s;
switch(st.ttype) {
case StreamTokenizer.TT_NUMBER:
s = String.valueOf(st.nval);
break;
case StreamTokenizer.TT_WORD:
s = st.sval;
break;
default:
s = String.valueOf((char)st.ttype);
}
Integer val = map.get(s);
if(val == null)
val = 1;
else
val++;
map.put(s, val);
}
Set<String> keySet = map.keySet();
Iterator<String> iter = keySet.iterator();
System.out.println("Frequency Of Words :");
int sum = 0;
while(iter.hasNext()) {
String word = iter.next();
int count = map.get(word);
sum += count;
System.out.println(" WORD : " + word + " = " + count);
}
System.out.println("Total Words In Files: " + sum);
请注意,我使用Generics而不是HashMap和Iterator的原始版本更新了代码。此外,不推荐使用您用于StreamTokenizer的构造函数。 map和set的使用都没用,因为你可以使用.keySet()方法遍历地图的键集。地图现在从String(单词)到Integer(单词计数)。
无论如何,关于你做的例子,我认为一个简单的拆分方法会更合适。
有关StreamTokenizer的wordChars方法的更多信息,您可以查看#wordChars(int, int)