package com.sohu.hot.vis.servlet;
import org.apache.commons.lang.StringUtils;
import java.io.BufferedReader;
import java.io.File;
import java.io.FileReader;
import java.util.*;
/**
* 測試一下在文件中找單詞重複次數的，一個面試題
*
* @author liweihan
* @time 2016-12-28 16:48
*/
public class TestHan {
public static void main(String[] args) throws Exception {
display("C:/java.txt");
display2("C:/java.txt");
}
/**
* @author liweihan
* @time 2016/12/28 17:28
* @description 方法1:正則，分割，map
* 缺點：對標點符號沒有辦法區分？！
* @param path
* @throws Exception
*/
public static void display(String path)throws Exception{
File file=new File(path);
BufferedReader br = new BufferedReader(new FileReader(file));
String line = null;
//定義一個map集合保存單詞和單詞出現的個數
TreeMap<String,Integer> tm = new TreeMap<String,Integer>();
//讀取文件
while((line=br.readLine())!=null){
line = line.toLowerCase();
String reg1 = "\\s+";
String reg2 ="\\w+";
//將讀取的文本進行分割
String str[] = line.split(reg1);
for(String s: str){
if(s.matches(reg2)){
//判斷集合中是否已經存在該單詞，如果存在則個數加1，否則將單詞添加到集合中，且個數置爲1
if(!tm.containsKey(s)){
tm.put(s,1);
}else{
tm.put(s,tm.get(s)+1);
}
}
}
}
br.close();
System.out.println(tm);
printResult(tm);
}
/**
* @author liweihan
* @time 2016/12/28 17:30
* @description 方法2
* @param path
* @throws Exception
*/
public static void display2(String path)throws Exception{
File file=new File(path);
BufferedReader br = new BufferedReader(new FileReader(file));
int tmpchar;
StringBuilder exist=new StringBuilder();
Map<String,Integer> map=new TreeMap<String,Integer>();
//讀取文件
while((tmpchar=br.read())!=-1){ //讀取單個字符
if (isCharacter(tmpchar)) { //字母
exist.append((char) tmpchar);
} else {
Addword(exist.toString(),map);
exist = new StringBuilder();
}
}
br.close();
System.out.println(map);
printResult(map);
}
/**
* @author liweihan
* @time 2016/12/28 17:32
* @description 判斷是否爲字母
* @param tmpchar
* @return
*/
public static boolean isCharacter(int tmpchar) {
if(tmpchar >= 65 && tmpchar <= 90) {
return true;
} else if (tmpchar >= 97 && tmpchar <= 122) {
return true;
} else {
return false;
}
}
/**
* @author liweihan
* @time 2016/12/28 17:36
* @description 把字母組合成單詞,並統計單詞的數量
* @param str
* @param map
*/
public static void Addword(String str,Map<String,Integer> map) {
str = str.toLowerCase();
Integer count = map.get(str);
if (count == null) {
map.put(str,1);
} else {
map.put(str,count+1);
}
}
/**
* @author liweihan
* @time 2016/12/28 18:34
* @description 打印map集合的數據，並排序
* @param map
*/
public static void printResult(Map<String,Integer> map) {
List<Map.Entry<String,Integer>> list = new ArrayList<Map.Entry<String,Integer>>(map.entrySet());
Collections.sort(list, new Comparator<Map.Entry<String, Integer>>() {
@Override
public int compare(Map.Entry<String, Integer> o1, Map.Entry<String, Integer> o2) {
return (o2.getValue().compareTo(o1.getValue()) ); //降序排序,當o2小於、等於、大於o1時，返回-1,0,1
/**
*
* public int compareTo(BigInteger val)
*
* 將此 BigInteger 與指定的 BigInteger 進行比較。
* 對於針對六個布爾比較運算符 (<, ==, >, >=, !=, <=) 中的每一個運算符的各個方法，
* 優先提供此方法。執行這些比較的建議語句是：
* (x.compareTo(y) <op> 0)，其中 <op> 是六個比較運算符之一。
*
* 當此 BigInteger 在數值上小於、等於或大於 val 時，返回 -1，0，或 1。
http://hanchaohan.blog.51cto.com/2996417/1734709
*/
}
});
/* int i = 10;
Set<String> keySet = map.keySet();
Iterator<String> iter = keySet.iterator();
while(iter.hasNext() && i > 0) {
String key = iter.next();
System.out.println( (String)key + " : " + map.get(key));
i--;
}*/
for (int i = 0; i < 10; i++) {
Map.Entry<String,Integer> entry = list.get(i);
if (entry == null) {
return;
}
System.out.println(entry.getKey() + " : " + entry.getValue());
}
}
}輸出結果：
{a=4, all=1, along=1, always=2, and=6, appreciate=2, are=2, around=2, bad=1, based=1, be=1, begins=1, best=1, brighten=1, brighter=1, brightest=1, can=1, chance=1, comes=1, crying=1, day=1, do=1, dream=1, dreams=1, ends=1, enough=1, everyone=2, everything=1, failures=1, feel=1, for=2, forgotten=1, from=1, future=1, go=2, happen=1, happiest=1, happiness=1, have=7, hope=1, hug=1, hurts=2, if=1, importance=1, in=4, is=2, it=1, just=3, keep=1, kiss=1, know=1, let=2, lies=1, life=4, lifeuntil=1, make=6, mean=1, message=1, miss=2, moments=1, most=1, much=1, necessarily=1, need=1, of=6, on=3, one=4, only=2, opportunity=1, or=1, other=1, out=1, past=1, people=3, pick=1, probably=1, put=1, really=2, see=1, send=1, side=1, smile=1, smiling=1, so=2, someone=1, something=1, sorrow=1, that=6, the=8, their=3, them=3, there=1, they=1, things=2, this=2, those=8, to=15, touched=2, trials=1, want=6, was=1, way=1, well=1, were=2, what=2, when=4, where=1, who=9, will=3, with=4, you=26, your=4, yourself=1}
you : 26
to : 15
who : 9
the : 8
those : 8
have : 7
and : 6
make : 6
of : 6
that : 6
{need=1, sorrow=1, =37, they=2, person=1, don=3, for=3, everything=2, chance=1, forgotten=1, people=3, of=6, are=2, on=3, only=2, something=1, yourself=1, along=1, happen=1, everyone=2, smile=2, ends=1, others=1, or=1, happiness=2, bad=1, always=2, them=3, will=3, go=4, born=1, put=1, lies=1, most=1, grows=1, life=4, side=1, happy=1, probably=1, best=1, do=2, pick=1, happiest=1, want=6, just=3, failures=1, may=1, let=2, a=4, crying=2, really=2, t=4, s=1, what=2, nothing=1, down=1, based=1, keep=1, heartaches=1, to=19, send=1, dreams=1, hug=1, enough=4, where=1, who=10, necessarily=1, love=1, kiss=1, were=2, please=1, future=1, tear=1, someone=2, when=5, friendship=1, brighten=1, brighter=1, smiling=2, trials=1, live=1, be=3, shoes=1, dream=2, so=2, begins=1, lifeuntil=1, moments=1, comes=1, much=1, and=8, that=6, sweet=1, importance=1, strong=1, lives=1, day=1, this=2, make=6, hope=1, appreciate=2, other=1, can=2, have=7, one=4, way=2, tried=1, well=1, from=1, re=1, was=1, because=1, another=1, real=1, if=2, touched=2, die=1, mean=1, all=1, too=1, hurts=2, feel=1, is=2, those=9, with=4, it=3, your=4, you=32, the=10, past=2, know=1, in=4, cry=1, around=2, human=1, message=2, opportunity=1, hurt=1, see=1, brightest=1, there=1, things=2, their=3, worry=1, searched=1, miss=2, out=1}
: 37
you : 32
to : 19
who : 10
the : 10
those : 9
and : 8
have : 7
of : 6
want : 6