Created
December 18, 2013 12:44
-
-
Save dchekmarev/8021713 to your computer and use it in GitHub Desktop.
allows to seek to any line in the file
This file contains hidden or 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 com.google.common.primitives.Longs; | |
import java.io.BufferedReader; | |
import java.io.ByteArrayInputStream; | |
import java.io.File; | |
import java.io.IOException; | |
import java.io.InputStreamReader; | |
import java.nio.ByteBuffer; | |
import java.nio.channels.SeekableByteChannel; | |
import java.nio.file.Files; | |
import java.util.ArrayList; | |
import java.util.List; | |
public static class LineReader { | |
private final File file; | |
private final long offsets[]; | |
private final static int BUFFER_SIZE = 1024; | |
public LineReader(File file) throws IOException { | |
this.file = file; | |
List<Long> offsetsList = new ArrayList<>(); | |
try (SeekableByteChannel sbc = Files.newByteChannel(file.toPath())) { | |
byte[] buf = new byte[BUFFER_SIZE]; | |
long offset = 0; | |
offsetsList.add(0L); | |
while (sbc.position() < sbc.size()) { | |
ByteBuffer dst = ByteBuffer.wrap(buf); | |
sbc.read(dst); | |
InputStreamReader reader = new InputStreamReader(new ByteArrayInputStream(buf)); | |
int processedOffset = 0; | |
while (reader.ready()) { | |
Character ch = (char) reader.read(); | |
int length = ch.toString().getBytes().length; | |
offset += length; | |
processedOffset += length; | |
if (ch == '\n') { | |
offsetsList.add(offset); | |
} | |
if (processedOffset > BUFFER_SIZE - 10) { | |
sbc.position(offset); | |
break; | |
} | |
} | |
} | |
} | |
offsets = Longs.toArray(offsetsList); | |
} | |
public int getLinesCount() { | |
return offsets.length; | |
} | |
public String getLine(int line) throws IOException { | |
try (SeekableByteChannel sbc = Files.newByteChannel(file.toPath())) { | |
long expectedSize = (line < offsets.length - 1 ? offsets[line + 1] : sbc.size()) - offsets[line]; | |
byte[] buf = new byte[(int) expectedSize]; | |
ByteBuffer dst = ByteBuffer.wrap(buf); | |
sbc.position(offsets[line]); | |
sbc.read(dst); | |
BufferedReader br = new BufferedReader(new InputStreamReader(new ByteArrayInputStream(buf))); | |
return br.readLine(); | |
} | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment