package readImgUrl;
import java.io.BufferedInputStream;
import java.io.BufferedReader;
import java.io.BufferedWriter;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.FileReader;
import java.io.FileWriter;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.io.OutputStreamWriter;
import java.net.URL;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.Collections;
import java.util.Comparator;
import java.util.List;
public class ClassifyUrl {
private static int HASHLEN = 100;
private static String file_dir = "D:\\学习\\实验室项目\\ImageNet图片爬取\\classify_url\\";
private static String src_file = "D:\\学习\\实验室项目\\ImageNet图片爬取\\fall11_urls.txt";
public static void main(String[] args) throws Exception {
// TODO Auto-generated method stub
classify_url("D:\\学习\\实验室项目\\ImageNet图片爬取\\fall11_urls.txt");
// rank_filedata("2");
// String s = judgeFileCode(src_file);
// String s = codeString(src_file);
// System.out.println(s);
}
/**
* 对一个文件进行排序
*/
public static void rank_filedata(String filename){
String path1 = file_dir+filename+".txt";
String path2 = file_dir+filename+"_"+".txt";
List<String> list = reader_list(path1);
System.out.println(list.size());
// 排序,通过泛型和匿名类来实现
Collections.sort(list, new Comparator<String>() {
public int compare(String s1, String s2) {
String h1 = s1.split(" ")[1];
String h2 = s2.split(" ")[1];
return h1.compareTo(h2);
}
});
writer_list(list, path2);
}
/**
* 读取文件，返回list
* @param path
* @return
*/
public static List reader_list(String path){
List<String> lineList = new ArrayList();
try {
BufferedReader reader = new BufferedReader(new FileReader(path));
String line = reader.readLine();
while(null != line){
lineList.add(line);
line = reader.readLine();
}
reader.close();
return lineList;
} catch (Exception e) {
// TODO: handle exception
e.printStackTrace();
}
return null;
}
/**
* 将List写入文件
* @param line
*/
public static void writer_list(List list, String path){
try {
BufferedWriter writer = new BufferedWriter(new FileWriter(path));
for(int i=0; i<list.size(); i++){
String line = (String)list.get(i);
writer.write(line+"\r\n");
}
writer.close();
} catch (Exception e) {
// TODO: handle exception
e.printStackTrace();
}
}
/**
* 从文件中逐行读取数据，分类写入0-99个文件
*/
public static void classify_url(String path){
try {
BufferedReader reader ;
String filecode = judgeFileCode(path);
reader = new BufferedReader(new InputStreamReader(new FileInputStream(path),filecode));
// BufferedReader reader = new BufferedReader(new FileReader(path));
String line = reader.readLine();
int line_num = 0;
// while(line_num<4101000){
// reader.readLine();
// line_num++;
// }
while(null != line){
try {
String host = new URL(line.split(" ")[1]).getHost();
int type = hash(host.toCharArray());
// writer(type+"", line);
} catch (Exception e) {
// TODO: handle exception
e.printStackTrace();
}
line = reader.readLine();
line_num++;
if(line_num%100==0){
// System.out.println(line_num);
char [] cc = line.toCharArray();
for(char c: cc){
if(isCnorEn(c)){
System.out.println(line);
break;
}
}
// break;
}
}
reader.close();
} catch (Exception e) {
// TODO: handle exception
e.printStackTrace();
}
}
/**
* 判断是中文还是英文字符
*/
static boolean isCnorEn(char c) {
if ((c >= 0x0391 && c <= 0xFFE5) // 中文字符
|| (c >= 0x0000 && c <= 0x00FF)) // 英文字符
return true;
return false;
// if ((c >= 0x0391 && c <= 0xFFE5) // 英文字符
// ) //
// return true;
// return false;
}
/**
* 给定一个字符串，返回hash后的int值
* @param word
* @return
*/
public static int hash(char[] word) {
int index = 0;
int i=0;
while(i<word.length) {
index += index * 31 + word[i];
i++;
}
return Math.abs(index % HASHLEN);
}
/**
* 将line写入filename中（文件不存在则先建立）
* @param filename
* @param line
*/
public static void writer(String filename, String line){
String path = file_dir+filename+".txt";
try {
File file = new File(path);
if(!file.isFile()){
file.createNewFile();
}
String filecode = judgeFileCode(src_file);
OutputStreamWriter writer = new OutputStreamWriter(new FileOutputStream(path, true), "GBK");
// BufferedWriter writer = new BufferedWriter(new FileWriter(path, true));
if(null != line){
writer.write(line+"\r\n");
}
writer.close();
} catch (Exception e) {
// TODO: handle exception
e.printStackTrace();
}
}
public static String judgeFileCode(String path){
try {
File file = new File(path);
InputStream in= new java.io.FileInputStream(file);
byte[] b = new byte[3];
in.read(b);
in.close();
if (b[0] == -17 && b[1] == -69 && b[2] == -65) {
// System.out.println(file.getName() + "：编码为UTF-8");
return "UTF-8";
}
else{
// System.out.println(file.getName() + "：可能是GBK，也可能是其他编码");
return "GBK";
}
} catch (Exception e) {
// TODO: handle exception
}
return null;
}
/**
* 判断文件的编码格式
* @param fileName :file
* @return 文件编码格式
* @throws Exception
*/
public static String codeString(String fileName) throws Exception{
BufferedInputStream bin = new BufferedInputStream(new FileInputStream(fileName));
int p = (bin.read() << 8) + bin.read();
String code = null;
//其中的 0xefbb、0xfffe、0xfeff、0x5c75这些都是这个文件的前面两个字节的16进制数
switch (p) {
case 0xefbb:
code = "UTF-8";
break;
case 0xfffe:
code = "Unicode";
break;
case 0xfeff:
code = "UTF-16BE";
break;
case 0x5c75:
code = "ANSI|ASCII" ;
break ;
default:
code = "GBK";
}
return code;
}
}
