Created
September 8, 2013 05:09
-
-
Save luan-cestari/6482016 to your computer and use it in GitHub Desktop.
Processing the file to extract data using REGEX
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import java.nio.ByteBuffer; | |
import java.nio.charset.Charset; | |
import java.nio.file.Files; | |
import java.nio.file.Paths; | |
import java.util.regex.Matcher; | |
import java.util.regex.Pattern; | |
public class Main { | |
public static void main(String[] args) throws Exception{ | |
// The Regex to extract the data from the input. It is using named captured group from JDK7 but it can be removed (just remove the <name> in capturing group in bellow the pattern and use matcher.group(x) instead of the name of the group) | |
Pattern pattern = | |
Pattern.compile("--MIME_boundary-\\d*\\n(?:Content-Type: text/xml; charset=\"UTF-8\"\\nContent-Transfer-Encoding: 8bit\\nContent-Location: dataHeader\\.xml\\n<\\?xml version=\"1\\.0\" encoding=\"UTF-8\"\\?>\\n<Header>\\n <DataLen>(?<first>.*)</DataLen>|Content-Type: application/octet-stream\\nContent-Location: data\\.bin\\n(?<second>.*)\\n)"); | |
// read the intere file named "input" into a String instance | |
Matcher matcher = pattern.matcher(Charset.defaultCharset().decode(ByteBuffer.wrap(Files.readAllBytes(Paths.get("input")))).toString()); | |
boolean found = false; | |
while (matcher.find()) { | |
System.out.println(matcher.group("first")); //matcher.group(1) | |
System.out.println(matcher.group("second")); //if matcher.group(1) is null, matcher.group(2) | |
System.out.println("!!!!!!!!!!!!"); | |
found = true; | |
} | |
if(!found){ | |
System.out.println("No match found"); | |
} | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment