问题一:
我正在尝试计算关键字的频率,我的代码有效,只是它还计算了那些也包含关键字的单词(例如,如果我搜索“count”,那么“account”之类的单词也会被计算在内。)有人知道如何解决这个问题吗?
问题2:
我还想计算文本中唯一单词的数量(这意味着我只计算重复单词一次)。我也不知道如何实现这一点。我的代码只给了我总字数。
这是我的代码:
import java.util.Scanner;
public class Text_minining {
/**
* @param args
*/
public static void main(String[] args) {
//Prompt the user for the search word
System.out.print("enter a search word: ");
//Get the user's search word input
Scanner keywordScanner = new Scanner(System.in);
String keyword = keywordScanner.nextLine();
keyword = keyword.toLowerCase();
//Prompt the user for the text
System.out.println("Enter a string of words (words separated by single spaces or tabs): ");
//Get the user's string input
Scanner userInputScanner = new Scanner(System.in);
String userInput = userInputScanner.nextLine();
userInput = userInput.toLowerCase();
int keywordCount = 0, wordCount = 0;
int lastIndex = 0;
while(lastIndex != -1){
lastIndex = userInput.indexOf(keyword,lastIndex);
if(lastIndex != -1){
keywordCount ++;
lastIndex = keyword.length() + lastIndex;
}
}
boolean wasSpace=true;
for (int i = 0; i < userInput.length(); i++)
{
if (userInput.charAt(i) == ' ') {
wasSpace=true;
}
else{
if(wasSpace == true) wordCount++;
wasSpace = false;
}
}
//Print the results to the screen
System.out.println("-------");
System.out.println("Good, \"" + keyword + "\"appears in the text and the word count is " + keywordCount);
System.out.println("The total number of unique words in the text is " + wordCount);
System.exit(0);
}
}