0
public static String entryPattern = "^([\\d.]+) (\\S+) (.+?) \\[([\\w:/]+\\s[+\\-]\\d{4})\\] \"(.+?)\" (\\d{3}) (\\d+) \"([^\"]+)\" \"([^\"]+)\"";
public static void parseTwigLine(String line) {
Pattern p = Pattern.compile(entryPattern);
Pattern p1;
Matcher matcher = p.matcher(line);
System.out.println(matcher.groupCount());
if (!matcher.matches() || NUM_FIELDS != matcher.groupCount()) {
System.err.println("Bad log entry (or problem with RE?):");
System.err.println(line);
return;
}
timeStamp = matcher.group(4);
ipAddress = matcher.group(1);
if (!matcher.group(3).equals("-")) {
userName = matcher.group(3);
}
request = matcher.group(5);
response = matcher.group(6);
bytesSent = matcher.group(7);
browser = matcher.group(9);
if (!matcher.group(8).equals("-"))
url = matcher.group(8);
instanceName = url.split("/")[3];
if(request.contains("?q")) {
queryTerms = request.split("[?|&]")[1];
} else if(url.contains("?q")) {
queryTerms = url.split("[?|&]")[1].split("=")[1];
}
if(request.contains("&f")) {
filters = request.split("&f=")[1];
} else if(url.contains("&f")) {
filters = request.split("&f=")[1];
}
}
对于此行,我的正则表达式没有得到匹配..任何建议为什么会发生这种情况。因为我从上面的代码中总是收到一个错误Bad log entry (or problem with RE?)
。什么毛病我正则表达式在Java中使用正则表达式解析字符串行
10.53.32.1 - - [14/Nov/2011:09:45:56 -0800] "GET /host-ui/themes/client/images/preview/left6_na.gif HTTP/1.1" 304 - "http://search.host.com/search-ui/?q=8960" "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; MS-RTC LM 8; InfoPath.3; BOIE9;ENUS)"
而对于这个下面一行是matched--越来越
10.53.32.1 - - [14/Nov/2011:09:45:56 -0800] "GET /host-ui/themes/client/images/btn_close_include.png HTTP/1.1" 200 1023 "http://search.host.com/search-ui/?q=8960" "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; MS-RTC LM 8; InfoPath.3; BOIE9;ENUS)"
对于已知格式的消息,是一个正则表达式的最佳途径吗?似乎它可能更容易打破它知道数据呈现在一个非常一致的模式,然后如果你需要,分解使用更简单的正则表达式,分裂等各个部分(如表单参数) –
@Dave Newton,哪种方法最好。使用正则表达式或只是通过分割字符串.. – ferhan
不知道;如果速度不是问题,那可能没关系。 –