我的代码有问题。我需要做几个操作的日志文件上有这样的结构:Java文件I/O帮助
190.12.1.100 2011-03-02 12:12 test.html
190.12.1.100 2011-03-03 13:18 data.html
128.33.100.1 2011-03-03 15:25 test.html
128.33.100.1 2011-03-04 18:30 info.html
我需要每月访问,每页和基于IP唯一身份访问者人数访问次数的数量。这不是问题,我设法让所有三个操作都起作用。问题是,只有第一个选项正确运行,而其他选择只是返回0后的值,就好像该文件是空的,所以我猜我犯了一个错误的I/O的地方。这里的代码:
import java.io.*;
import java.util.*;
public class WebServerAnalyzer {
private Map<String, Integer> hm1;
private Map<String, Integer> hm2;
private int[] months;
private Scanner input;
public WebServerAnalyzer() throws IOException {
hm1 = new HashMap<String, Integer>();
hm2 = new HashMap<String, Integer>();
months = new int[12];
for (int i = 0; i < 12; i++) {
months[i] = 0;
}
File file = new File("webserver.log");
try {
input = new Scanner(file);
} catch (FileNotFoundException fne) {
input = null;
}
}
public String nextLine() {
String line = null;
if (input != null && input.hasNextLine()) {
line = input.nextLine();
}
return line;
}
public int getMonth(String line) {
StringTokenizer tok = new StringTokenizer(line);
if (tok.countTokens() == 4) {
String ip = tok.nextToken();
String date = tok.nextToken();
String hour = tok.nextToken();
String page = tok.nextToken();
StringTokenizer dtok = new StringTokenizer(date, "-");
if (dtok.countTokens() == 3) {
String year = dtok.nextToken();
String month = dtok.nextToken();
String day = dtok.nextToken();
int m = Integer.parseInt(month);
return m;
}
}
return -1;
}
public String getIP(String line) {
StringTokenizer tok = new StringTokenizer(line);
if (tok.countTokens() == 4) {
String ip = tok.nextToken();
String date = tok.nextToken();
String hour = tok.nextToken();
String page = tok.nextToken();
StringTokenizer dtok = new StringTokenizer(date, "-");
return ip;
}
return null;
}
public String getPage(String line) {
StringTokenizer tok = new StringTokenizer(line);
if (tok.countTokens() == 4) {
String ip = tok.nextToken();
String date = tok.nextToken();
String hour = tok.nextToken();
String page = tok.nextToken();
StringTokenizer dtok = new StringTokenizer(date, "-");
return page;
}
return null;
}
public void visitsPerMonth() {
String line = null;
do {
line = nextLine();
if (line != null) {
int m = getMonth(line);
if (m != -1) {
months[m - 1]++;
}
}
} while (line != null);
// Print the result
String[] monthName = {"JAN ", "FEB ", "MAR ",
"APR ", "MAY ", "JUN ", "JUL ", "AUG ", "SEP ",
"OCT ", "NOV ", "DEC "};
for (int i = 0; i < 12; i++) {
System.out.println(monthName[i] + months[i]);
}
}
public int count() throws IOException {
InputStream is = new BufferedInputStream(new FileInputStream("webserver.log"));
try {
byte[] c = new byte[1024];
int count = 0;
int readChars = 0;
while ((readChars = is.read(c)) != -1) {
for (int i = 0; i < readChars; ++i) {
if (c[i] == '\n')
++count;
}
}
return count;
} finally {
is.close();
}
}
public void UniqueIP() throws IOException{
String line = null;
for (int x = 0; x <count(); x++){
line = nextLine();
if (line != null) {
if(hm1.containsKey(getIP(line)) == false) {
hm1.put(getIP(line), 1);
} else {
hm1.put(getIP(line), hm1.get(getIP(line)) +1);
}
}
}
Set set = hm1.entrySet();
Iterator i = set.iterator();
System.out.println("\nNumber of unique visitors: " + hm1.size());
while(i.hasNext()) {
Map.Entry me = (Map.Entry)i.next();
System.out.print(me.getKey() + " - ");
System.out.println(me.getValue() + " visits");
}
}
public void pageVisits() throws IOException{
String line = null;
for (int x = 0; x <count(); x++){
line = nextLine();
if (line != null) {
if(hm2.containsKey(getPage(line)) == false)
hm2.put(getPage(line), 1);
else
hm2.put(getPage(line), hm2.get(getPage(line)) +1);
}
}
Set set = hm2.entrySet();
Iterator i = set.iterator();
System.out.println("\nNumber of pages visited: " + hm2.size());
while(i.hasNext()) {
Map.Entry me = (Map.Entry)i.next();
System.out.print(me.getKey() + " - ");
System.out.println(me.getValue() + " visits");
}
}
任何帮助搞清楚这个问题将不胜感激,因为我很卡住。
您应该使用字符串类的Split方法而不是StringTokenizer – Clayton 2011-05-01 09:32:25
它会导致除了被混乱之外的任何问题吗?在所有其他工作完成后,我很可能会这样做。 – Terezi 2011-05-01 09:36:58
不,StringTokenizer仍然适用于你想要完成的工作,它只是被弃用了。所以除非标记器因为某种原因没有正确地断开字符串,在功能上它基本上是相同的。 – Clayton 2011-05-01 09:40:25