Java读取包含7000万行文本的大型文本文件
我有一个包含7000万行文本的大测试文件。 我必须逐行读文件 我使用了两种不同的方法：Java读取包含7000万行文本的大型文本文件,java,io,Java,Io,我有一个包含7000万行文本的大测试文件。 我必须逐行读文件 我使用了两种不同的方法： InputStreamReader isr = new InputStreamReader(new FileInputStream(FilePath),"unicode"); BufferedReader br = new BufferedReader(isr); while((cur=br.readLine()) != null); 及 是否有其他方法可以加快这项任务 致以最诚挚的问候，如果您关注的是性能
InputStreamReader isr = new InputStreamReader(new FileInputStream(FilePath),"unicode");
BufferedReader br = new BufferedReader(isr);
while((cur=br.readLine()) != null);
致以最诚挚的问候，如果您关注的是性能，您可以看看
java.nio.*java.io.*try (BufferedReader br = Files.newBufferedReader(Paths.get("test.txt"), StandardCharsets.UTF_8)) {
for (String line = null; (line = br.readLine()) != null;) {
//
}
}
try (Scanner sc = new Scanner(new File("test.txt"), "UTF-8")) {
while (sc.hasNextLine()) {
String line = sc.nextLine();
}
// note that Scanner suppresses exceptions
if (sc.ioException() != null) {
throw sc.ioException();
}
}
try (SeekableByteChannel ch = Files.newByteChannel(Paths.get("test.txt"))) {
ByteBuffer bb = ByteBuffer.allocateDirect(1000);
for(;;) {
StringBuilder line = new StringBuilder();
int n = ch.read(bb);
// add chars to line
// ...
}
}
ByteBuffer.allocateDirect字节缓冲区字符串，查找下一个…是一个很好的开始方式
此外，您需要创建测试用例，在其中读取前10k（或其他内容，但不应太小）行，并相应地计算读取时间
线程化可能是一种很好的方式，但重要的是我们知道您将如何处理数据
另一个需要考虑的问题是，如何存储该大小的数据。我也有类似的问题，但我只需要文件中的字节。我阅读了各种答案中提供的链接，并最终尝试编写一个类似于叶甫根尼答案中的#5的链接。他们不是在开玩笑，这需要很多代码
基本前提是每行文本的长度未知。我将从一个可查找的字节通道开始，将数据读入字节缓冲区，然后在其上循环查找EOL。当某个内容是循环之间的“结转”时，它会增加一个计数器，然后最终移动seekablebytechnel位置并读取整个缓冲区
这是冗长的。。。但它是有效的。这对于我所需要的东西来说是非常快的，但是我相信还有更多的改进可以做
过程方法被简化为开始读取文件的基础
private long startOffset;
private long endOffset;
private SeekableByteChannel sbc;
private final ByteBuffer buffer = ByteBuffer.allocateDirect(1024);
public void process() throws IOException
{
startOffset = 0;
sbc = Files.newByteChannel(FILE, EnumSet.of(READ));
byte[] message = null;
while((message = readRecord()) != null)
{
// do something
}
}
public byte[] readRecord() throws IOException
{
endOffset = startOffset;
boolean eol = false;
boolean carryOver = false;
byte[] record = null;
while(!eol)
{
byte data;
buffer.clear();
final int bytesRead = sbc.read(buffer);
if(bytesRead == -1)
{
return null;
}
buffer.flip();
for(int i = 0; i < bytesRead && !eol; i++)
{
data = buffer.get();
if(data == '\r' || data == '\n')
{
eol = true;
endOffset += i;
if(carryOver)
{
final int messageSize = (int)(endOffset - startOffset);
sbc.position(startOffset);
final ByteBuffer tempBuffer = ByteBuffer.allocateDirect(messageSize);
sbc.read(tempBuffer);
tempBuffer.flip();
record = new byte[messageSize];
tempBuffer.get(record);
}
else
{
record = new byte[i];
// Need to move the buffer position back since the get moved it forward
buffer.position(0);
buffer.get(record, 0, i);
}
// Skip past the newline characters
if(isWindowsOS())
{
startOffset = (endOffset + 2);
}
else
{
startOffset = (endOffset + 1);
}
// Move the file position back
sbc.position(startOffset);
}
}
if(!eol && sbc.position() == sbc.size())
{
// We have hit the end of the file, just take all the bytes
record = new byte[bytesRead];
eol = true;
buffer.position(0);
buffer.get(record, 0, bytesRead);
}
else if(!eol)
{
// The EOL marker wasn't found, continue the loop
carryOver = true;
endOffset += bytesRead;
}
}
// System.out.println(new String(record));
return record;
}
private long startOffset；
私人长期内补偿；
私人频道sbc；
私有最终ByteBuffer缓冲区=ByteBuffer.allocateDirect（1024）；
public void进程（）引发IOException
{
startOffset=0；
sbc=Files.newByteChannel（FILE，EnumSet.of（READ））；
字节[]消息=null；
而（（message=readRecord（））！=null）
{
//做点什么
}
}
公共字节[]readRecord（）引发IOException
{
endOffset=startOffset；
布尔eol=假；
布尔携带=假；
字节[]记录=null；
而（！eol）
{
字节数据；
buffer.clear（）；
final int bytesRead=sbc.read（缓冲区）；
如果（字节读==-1）
{
返回null；
}
flip（）；
对于（int i=0；i
事实上，我在空闲时间对这一主题进行了数月的研究，并提出了一个基准。下面是一个代码，用于对逐行读取文件的所有不同方式进行基准测试。各个性能可能因基础系统而异。
我在Windows10Java8Intel i5HP笔记本电脑上运行：下面是代码
import java.io.*;
import java.nio.channels.Channels;
import java.nio.channels.FileChannel;
import java.nio.file.Files;
import java.util.ArrayList;
import java.util.List;
import java.util.Scanner;
import java.util.regex.Pattern;
import java.util.stream.Stream;
public class ReadComplexDelimitedFile {
private static long total = 0;
private static final Pattern FIELD_DELIMITER_PATTERN = Pattern.compile("\\^\\|\\^");
@SuppressWarnings("unused")
private void readFileUsingScanner() {
String s;
try (Scanner stdin = new Scanner(new File(this.getClass().getResource("input.txt").getPath()))) {
while (stdin.hasNextLine()) {
s = stdin.nextLine();
String[] fields = FIELD_DELIMITER_PATTERN.split(s, 0);
total = total + fields.length;
}
} catch (Exception e) {
System.err.println("Error");
}
}
//Winner
private void readFileUsingCustomBufferedReader() {
try (CustomBufferedReader stdin = new CustomBufferedReader(new FileReader(new File(this.getClass().getResource("input.txt").getPath())))) {
String s;
while ((s = stdin.readLine()) != null) {
String[] fields = FIELD_DELIMITER_PATTERN.split(s, 0);
total += fields.length;
}
} catch (Exception e) {
System.err.println("Error");
}
}
private void readFileUsingBufferedReader() {
try (BufferedReader stdin = new BufferedReader(new FileReader(new File(this.getClass().getResource("input.txt").getPath())))) {
String s;
while ((s = stdin.readLine()) != null) {
String[] fields = FIELD_DELIMITER_PATTERN.split(s, 0);
total += fields.length;
}
} catch (Exception e) {
System.err.println("Error");
}
}
private void readFileUsingLineReader() {
try (LineNumberReader stdin = new LineNumberReader(new FileReader(new File(this.getClass().getResource("input.txt").getPath())))) {
String s;
while ((s = stdin.readLine()) != null) {
String[] fields = FIELD_DELIMITER_PATTERN.split(s, 0);
total += fields.length;
}
} catch (Exception e) {
System.err.println("Error");
}
}
private void readFileUsingStreams() {
try (Stream<String> stream = Files.lines((new File(this.getClass().getResource("input.txt").getPath())).toPath())) {
total += stream.mapToInt(s -> FIELD_DELIMITER_PATTERN.split(s, 0).length).sum();
} catch (IOException e1) {
e1.printStackTrace();
}
}
private void readFileUsingBufferedReaderFileChannel() {
try (FileInputStream fis = new FileInputStream(this.getClass().getResource("input.txt").getPath())) {
try (FileChannel inputChannel = fis.getChannel()) {
try (CustomBufferedReader stdin = new CustomBufferedReader(Channels.newReader(inputChannel, "UTF-8"))) {
String s;
while ((s = stdin.readLine()) != null) {
String[] fields = FIELD_DELIMITER_PATTERN.split(s, 0);
total = total + fields.length;
}
}
} catch (Exception e) {
System.err.println("Error");
}
} catch (Exception e) {
System.err.println("Error");
}
}
public static void main(String args[]) {
//JVM wamrup
for (int i = 0; i < 100000; i++) {
total += i;
}
// We know scanner is slow-Still warming up
ReadComplexDelimitedFile readComplexDelimitedFile = new ReadComplexDelimitedFile();
List<Long> longList = new ArrayList<>(50);
for (int i = 0; i < 50; i++) {
total = 0;
long startTime = System.nanoTime();
//readComplexDelimitedFile.readFileUsingScanner();
long stopTime = System.nanoTime();
long timeDifference = stopTime - startTime;
longList.add(timeDifference);
}
System.out.println("Time taken for readFileUsingScanner");
longList.forEach(System.out::println);
// Actual performance test starts here
longList = new ArrayList<>(10);
for (int i = 0; i < 10; i++) {
total = 0;
long startTime = System.nanoTime();
readComplexDelimitedFile.readFileUsingBufferedReaderFileChannel();
long stopTime = System.nanoTime();
long timeDifference = stopTime - startTime;
longList.add(timeDifference);
}
System.out.println("Time taken for readFileUsingBufferedReaderFileChannel");
longList.forEach(System.out::println);
longList.clear();
for (int i = 0; i < 10; i++) {
total = 0;
long startTime = System.nanoTime();
readComplexDelimitedFile.readFileUsingBufferedReader();
long stopTime = System.nanoTime();
long timeDifference = stopTime - startTime;
longList.add(timeDifference);
}
System.out.println("Time taken for readFileUsingBufferedReader");
longList.forEach(System.out::println);
longList.clear();
for (int i = 0; i < 10; i++) {
total = 0;
long startTime = System.nanoTime();
readComplexDelimitedFile.readFileUsingStreams();
long stopTime = System.nanoTime();
long timeDifference = stopTime - startTime;
longList.add(timeDifference);
}
System.out.println("Time taken for readFileUsingStreams");
longList.forEach(System.out::println);
longList.clear();
for (int i = 0; i < 10; i++) {
total = 0;
long startTime = System.nanoTime();
readComplexDelimitedFile.readFileUsingCustomBufferedReader();
long stopTime = System.nanoTime();
long timeDifference = stopTime - startTime;
longList.add(timeDifference);
}
System.out.println("Time taken for readFileUsingCustomBufferedReader");
longList.forEach(System.out::println);
longList.clear();
for (int i = 0; i < 10; i++) {
total = 0;
long startTime = System.nanoTime();
readComplexDelimitedFile.readFileUsingLineReader();
long stopTime = System.nanoTime();
long timeDifference = stopTime - startTime;
longList.add(timeDifference);
}
System.out.println("Time taken for readFileUsingLineReader");
longList.forEach(System.out::println);
}
}
现在的结果是：
使用BufferedReaderFileChannel读取文件所用的时间
2902690903
1845190694
1894071377
1815161868
1861056735
1867693540
1857521371
1794176251
1768008762
1853089582
使用BufferedReader读取文件所用的时间
2022837353
1925901163
1802266711
1842689572
1899984555
1843101306
1998642345
1821242301
1820168806
1830375108
使用Streams读取文件所用的时间
1992855461
1930827034
1850876033
1843402533
1800378283
1863581324
1810857226
1798497108
1809531144
1796345853
使用CustomBufferedReader读取文件所用的时间
1759732702
1765987214
1776997357
1772999486
17685
import java.io.*;
import java.nio.channels.Channels;
import java.nio.channels.FileChannel;
import java.nio.file.Files;
import java.util.ArrayList;
import java.util.List;
import java.util.Scanner;
import java.util.regex.Pattern;
import java.util.stream.Stream;
public class ReadComplexDelimitedFile {
private static long total = 0;
private static final Pattern FIELD_DELIMITER_PATTERN = Pattern.compile("\\^\\|\\^");
@SuppressWarnings("unused")
private void readFileUsingScanner() {
String s;
try (Scanner stdin = new Scanner(new File(this.getClass().getResource("input.txt").getPath()))) {
while (stdin.hasNextLine()) {
s = stdin.nextLine();
String[] fields = FIELD_DELIMITER_PATTERN.split(s, 0);
total = total + fields.length;
}
} catch (Exception e) {
System.err.println("Error");
}
}
//Winner
private void readFileUsingCustomBufferedReader() {
try (CustomBufferedReader stdin = new CustomBufferedReader(new FileReader(new File(this.getClass().getResource("input.txt").getPath())))) {
String s;
while ((s = stdin.readLine()) != null) {
String[] fields = FIELD_DELIMITER_PATTERN.split(s, 0);
total += fields.length;
}
} catch (Exception e) {
System.err.println("Error");
}
}
private void readFileUsingBufferedReader() {
try (BufferedReader stdin = new BufferedReader(new FileReader(new File(this.getClass().getResource("input.txt").getPath())))) {
String s;
while ((s = stdin.readLine()) != null) {
String[] fields = FIELD_DELIMITER_PATTERN.split(s, 0);
total += fields.length;
}
} catch (Exception e) {
System.err.println("Error");
}
}
private void readFileUsingLineReader() {
try (LineNumberReader stdin = new LineNumberReader(new FileReader(new File(this.getClass().getResource("input.txt").getPath())))) {
String s;
while ((s = stdin.readLine()) != null) {
String[] fields = FIELD_DELIMITER_PATTERN.split(s, 0);
total += fields.length;
}
} catch (Exception e) {
System.err.println("Error");
}
}
private void readFileUsingStreams() {
try (Stream<String> stream = Files.lines((new File(this.getClass().getResource("input.txt").getPath())).toPath())) {
total += stream.mapToInt(s -> FIELD_DELIMITER_PATTERN.split(s, 0).length).sum();
} catch (IOException e1) {
e1.printStackTrace();
}
}
private void readFileUsingBufferedReaderFileChannel() {
try (FileInputStream fis = new FileInputStream(this.getClass().getResource("input.txt").getPath())) {
try (FileChannel inputChannel = fis.getChannel()) {
try (CustomBufferedReader stdin = new CustomBufferedReader(Channels.newReader(inputChannel, "UTF-8"))) {
String s;
while ((s = stdin.readLine()) != null) {
String[] fields = FIELD_DELIMITER_PATTERN.split(s, 0);
total = total + fields.length;
}
}
} catch (Exception e) {
System.err.println("Error");
}
} catch (Exception e) {
System.err.println("Error");
}
}
public static void main(String args[]) {
//JVM wamrup
for (int i = 0; i < 100000; i++) {
total += i;
}
// We know scanner is slow-Still warming up
ReadComplexDelimitedFile readComplexDelimitedFile = new ReadComplexDelimitedFile();
List<Long> longList = new ArrayList<>(50);
for (int i = 0; i < 50; i++) {
total = 0;
long startTime = System.nanoTime();
//readComplexDelimitedFile.readFileUsingScanner();
long stopTime = System.nanoTime();
long timeDifference = stopTime - startTime;
longList.add(timeDifference);
}
System.out.println("Time taken for readFileUsingScanner");
longList.forEach(System.out::println);
// Actual performance test starts here
longList = new ArrayList<>(10);
for (int i = 0; i < 10; i++) {
total = 0;
long startTime = System.nanoTime();
readComplexDelimitedFile.readFileUsingBufferedReaderFileChannel();
long stopTime = System.nanoTime();
long timeDifference = stopTime - startTime;
longList.add(timeDifference);
}
System.out.println("Time taken for readFileUsingBufferedReaderFileChannel");
longList.forEach(System.out::println);
longList.clear();
for (int i = 0; i < 10; i++) {
total = 0;
long startTime = System.nanoTime();
readComplexDelimitedFile.readFileUsingBufferedReader();
long stopTime = System.nanoTime();
long timeDifference = stopTime - startTime;
longList.add(timeDifference);
}
System.out.println("Time taken for readFileUsingBufferedReader");
longList.forEach(System.out::println);
longList.clear();
for (int i = 0; i < 10; i++) {
total = 0;
long startTime = System.nanoTime();
readComplexDelimitedFile.readFileUsingStreams();
long stopTime = System.nanoTime();
long timeDifference = stopTime - startTime;
longList.add(timeDifference);
}
System.out.println("Time taken for readFileUsingStreams");
longList.forEach(System.out::println);
longList.clear();
for (int i = 0; i < 10; i++) {
total = 0;
long startTime = System.nanoTime();
readComplexDelimitedFile.readFileUsingCustomBufferedReader();
long stopTime = System.nanoTime();
long timeDifference = stopTime - startTime;
longList.add(timeDifference);
}
System.out.println("Time taken for readFileUsingCustomBufferedReader");
longList.forEach(System.out::println);
longList.clear();
for (int i = 0; i < 10; i++) {
total = 0;
long startTime = System.nanoTime();
readComplexDelimitedFile.readFileUsingLineReader();
long stopTime = System.nanoTime();
long timeDifference = stopTime - startTime;
longList.add(timeDifference);
}
System.out.println("Time taken for readFileUsingLineReader");
longList.forEach(System.out::println);
}
}
import com.sun.istack.internal.NotNull;
import java.io.*;
import java.util.Iterator;
import java.util.NoSuchElementException;
import java.util.Spliterator;
import java.util.Spliterators;
import java.util.concurrent.locks.ReadWriteLock;
import java.util.concurrent.locks.ReentrantReadWriteLock;
import java.util.stream.Stream;
import java.util.stream.StreamSupport;
/**
* Reads text from a character-input stream, buffering characters so as to
* provide for the efficient reading of characters, arrays, and lines.
* <p>
* <p> The buffer size may be specified, or the default size may be used. The
* default is large enough for most purposes.
* <p>
* <p> In general, each read request made of a Reader causes a corresponding
* read request to be made of the underlying character or byte stream. It is
* therefore advisable to wrap a CustomBufferedReader around any Reader whose read()
* operations may be costly, such as FileReaders and InputStreamReaders. For
* example,
* <p>
* <pre>
* CustomBufferedReader in
* = new CustomBufferedReader(new FileReader("foo.in"));
* </pre>
* <p>
* will buffer the input from the specified file. Without buffering, each
* invocation of read() or readLine() could cause bytes to be read from the
* file, converted into characters, and then returned, which can be very
* inefficient.
* <p>
* <p> Programs that use DataInputStreams for textual input can be localized by
* replacing each DataInputStream with an appropriate CustomBufferedReader.
*
* @author Mark Reinhold
* @see FileReader
* @see InputStreamReader
* @see java.nio.file.Files#newBufferedReader
* @since JDK1.1
*/
public class CustomBufferedReader extends Reader {
private final Reader in;
private char cb[];
private int nChars, nextChar;
private static final int INVALIDATED = -2;
private static final int UNMARKED = -1;
private int markedChar = UNMARKED;
private int readAheadLimit = 0; /* Valid only when markedChar > 0 */
/**
* If the next character is a line feed, skip it
*/
private boolean skipLF = false;
/**
* The skipLF flag when the mark was set
*/
private boolean markedSkipLF = false;
private static int defaultCharBufferSize = 8192;
private static int defaultExpectedLineLength = 80;
private ReadWriteLock rwlock;
/**
* Creates a buffering character-input stream that uses an input buffer of
* the specified size.
*
* @param in A Reader
* @param sz Input-buffer size
* @throws IllegalArgumentException If {@code sz <= 0}
*/
public CustomBufferedReader(@NotNull final Reader in, int sz) {
super(in);
if (sz <= 0)
throw new IllegalArgumentException("Buffer size <= 0");
this.in = in;
cb = new char[sz];
nextChar = nChars = 0;
rwlock = new ReentrantReadWriteLock();
}
/**
* Creates a buffering character-input stream that uses a default-sized
* input buffer.
*
* @param in A Reader
*/
public CustomBufferedReader(@NotNull final Reader in) {
this(in, defaultCharBufferSize);
}
/**
* Fills the input buffer, taking the mark into account if it is valid.
*/
private void fill() throws IOException {
int dst;
if (markedChar <= UNMARKED) {
/* No mark */
dst = 0;
} else {
/* Marked */
int delta = nextChar - markedChar;
if (delta >= readAheadLimit) {
/* Gone past read-ahead limit: Invalidate mark */
markedChar = INVALIDATED;
readAheadLimit = 0;
dst = 0;
} else {
if (readAheadLimit <= cb.length) {
/* Shuffle in the current buffer */
System.arraycopy(cb, markedChar, cb, 0, delta);
markedChar = 0;
dst = delta;
} else {
/* Reallocate buffer to accommodate read-ahead limit */
char ncb[] = new char[readAheadLimit];
System.arraycopy(cb, markedChar, ncb, 0, delta);
cb = ncb;
markedChar = 0;
dst = delta;
}
nextChar = nChars = delta;
}
}
int n;
do {
n = in.read(cb, dst, cb.length - dst);
} while (n == 0);
if (n > 0) {
nChars = dst + n;
nextChar = dst;
}
}
/**
* Reads a single character.
*
* @return The character read, as an integer in the range
* 0 to 65535 (<tt>0x00-0xffff</tt>), or -1 if the
* end of the stream has been reached
* @throws IOException If an I/O error occurs
*/
public char readChar() throws IOException {
for (; ; ) {
if (nextChar >= nChars) {
fill();
if (nextChar >= nChars)
return (char) -1;
}
return cb[nextChar++];
}
}
/**
* Reads characters into a portion of an array, reading from the underlying
* stream if necessary.
*/
private int read1(char[] cbuf, int off, int len) throws IOException {
if (nextChar >= nChars) {
/* If the requested length is at least as large as the buffer, and
if there is no mark/reset activity, and if line feeds are not
being skipped, do not bother to copy the characters into the
local buffer. In this way buffered streams will cascade
harmlessly. */
if (len >= cb.length && markedChar <= UNMARKED && !skipLF) {
return in.read(cbuf, off, len);
}
fill();
}
if (nextChar >= nChars) return -1;
int n = Math.min(len, nChars - nextChar);
System.arraycopy(cb, nextChar, cbuf, off, n);
nextChar += n;
return n;
}
/**
* Reads characters into a portion of an array.
* <p>
* <p> This method implements the general contract of the corresponding
* <code>{@link Reader#read(char[], int, int) read}</code> method of the
* <code>{@link Reader}</code> class. As an additional convenience, it
* attempts to read as many characters as possible by repeatedly invoking
* the <code>read</code> method of the underlying stream. This iterated
* <code>read</code> continues until one of the following conditions becomes
* true: <ul>
* <p>
* <li> The specified number of characters have been read,
* <p>
* <li> The <code>read</code> method of the underlying stream returns
* <code>-1</code>, indicating end-of-file, or
* <p>
* <li> The <code>ready</code> method of the underlying stream
* returns <code>false</code>, indicating that further input requests
* would block.
* <p>
* </ul> If the first <code>read</code> on the underlying stream returns
* <code>-1</code> to indicate end-of-file then this method returns
* <code>-1</code>. Otherwise this method returns the number of characters
* actually read.
* <p>
* <p> Subclasses of this class are encouraged, but not required, to
* attempt to read as many characters as possible in the same fashion.
* <p>
* <p> Ordinarily this method takes characters from this stream's character
* buffer, filling it from the underlying stream as necessary. If,
* however, the buffer is empty, the mark is not valid, and the requested
* length is at least as large as the buffer, then this method will read
* characters directly from the underlying stream into the given array.
* Thus redundant <code>CustomBufferedReader</code>s will not copy data
* unnecessarily.
*
* @param cbuf Destination buffer
* @param off Offset at which to start storing characters
* @param len Maximum number of characters to read
* @return The number of characters read, or -1 if the end of the
* stream has been reached
* @throws IOException If an I/O error occurs
*/
public int read(char cbuf[], int off, int len) throws IOException {
int n = read1(cbuf, off, len);
if (n <= 0) return n;
while ((n < len) && in.ready()) {
int n1 = read1(cbuf, off + n, len - n);
if (n1 <= 0) break;
n += n1;
}
return n;
}
/**
* Reads a line of text. A line is considered to be terminated by any one
* of a line feed ('\n'), a carriage return ('\r'), or a carriage return
* followed immediately by a linefeed.
*
* @param ignoreLF If true, the next '\n' will be skipped
* @return A String containing the contents of the line, not including
* any line-termination characters, or null if the end of the
* stream has been reached
* @throws IOException If an I/O error occurs
* @see java.io.LineNumberReader#readLine()
*/
String readLine(boolean ignoreLF) throws IOException {
StringBuilder s = null;
int startChar;
bufferLoop:
for (; ; ) {
if (nextChar >= nChars)
fill();
if (nextChar >= nChars) { /* EOF */
if (s != null && s.length() > 0)
return s.toString();
else
return null;
}
boolean eol = false;
char c = 0;
int i;
/* Skip a leftover '\n', if necessary */
charLoop:
for (i = nextChar; i < nChars; i++) {
c = cb[i];
if ((c == '\n')) {
eol = true;
break charLoop;
}
}
startChar = nextChar;
nextChar = i;
if (eol) {
String str;
if (s == null) {
str = new String(cb, startChar, i - startChar);
} else {
s.append(cb, startChar, i - startChar);
str = s.toString();
}
nextChar++;
return str;
}
if (s == null)
s = new StringBuilder(defaultExpectedLineLength);
s.append(cb, startChar, i - startChar);
}
}
/**
* Reads a line of text. A line is considered to be terminated by any one
* of a line feed ('\n'), a carriage return ('\r'), or a carriage return
* followed immediately by a linefeed.
*
* @return A String containing the contents of the line, not including
* any line-termination characters, or null if the end of the
* stream has been reached
* @throws IOException If an I/O error occurs
* @see java.nio.file.Files#readAllLines
*/
public String readLine() throws IOException {
return readLine(false);
}
/**
* Skips characters.
*
* @param n The number of characters to skip
* @return The number of characters actually skipped
* @throws IllegalArgumentException If <code>n</code> is negative.
* @throws IOException If an I/O error occurs
*/
public long skip(long n) throws IOException {
if (n < 0L) {
throw new IllegalArgumentException("skip value is negative");
}
rwlock.readLock().lock();
long r = n;
try{
while (r > 0) {
if (nextChar >= nChars)
fill();
if (nextChar >= nChars) /* EOF */
break;
if (skipLF) {
skipLF = false;
if (cb[nextChar] == '\n') {
nextChar++;
}
}
long d = nChars - nextChar;
if (r <= d) {
nextChar += r;
r = 0;
break;
} else {
r -= d;
nextChar = nChars;
}
}
} finally {
rwlock.readLock().unlock();
}
return n - r;
}
/**
* Tells whether this stream is ready to be read. A buffered character
* stream is ready if the buffer is not empty, or if the underlying
* character stream is ready.
*
* @throws IOException If an I/O error occurs
*/
public boolean ready() throws IOException {
rwlock.readLock().lock();
try {
/*
* If newline needs to be skipped and the next char to be read
* is a newline character, then just skip it right away.
*/
if (skipLF) {
/* Note that in.ready() will return true if and only if the next
* read on the stream will not block.
*/
if (nextChar >= nChars && in.ready()) {
fill();
}
if (nextChar < nChars) {
if (cb[nextChar] == '\n')
nextChar++;
skipLF = false;
}
}
} finally {
rwlock.readLock().unlock();
}
return (nextChar < nChars) || in.ready();
}
/**
* Tells whether this stream supports the mark() operation, which it does.
*/
public boolean markSupported() {
return true;
}
/**
* Marks the present position in the stream. Subsequent calls to reset()
* will attempt to reposition the stream to this point.
*
* @param readAheadLimit Limit on the number of characters that may be
* read while still preserving the mark. An attempt
* to reset the stream after reading characters
* up to this limit or beyond may fail.
* A limit value larger than the size of the input
* buffer will cause a new buffer to be allocated
* whose size is no smaller than limit.
* Therefore large values should be used with care.
* @throws IllegalArgumentException If {@code readAheadLimit < 0}
* @throws IOException If an I/O error occurs
*/
public void mark(int readAheadLimit) throws IOException {
if (readAheadLimit < 0) {
throw new IllegalArgumentException("Read-ahead limit < 0");
}
rwlock.readLock().lock();
try {
this.readAheadLimit = readAheadLimit;
markedChar = nextChar;
markedSkipLF = skipLF;
} finally {
rwlock.readLock().unlock();
}
}
/**
* Resets the stream to the most recent mark.
*
* @throws IOException If the stream has never been marked,
* or if the mark has been invalidated
*/
public void reset() throws IOException {
rwlock.readLock().lock();
try {
if (markedChar < 0)
throw new IOException((markedChar == INVALIDATED)
? "Mark invalid"
: "Stream not marked");
nextChar = markedChar;
skipLF = markedSkipLF;
} finally {
rwlock.readLock().unlock();
}
}
public void close() throws IOException {
rwlock.readLock().lock();
try {
in.close();
} finally {
cb = null;
rwlock.readLock().unlock();
}
}
public Stream<String> lines() {
Iterator<String> iter = new Iterator<String>() {
String nextLine = null;
@Override
public boolean hasNext() {
if (nextLine != null) {
return true;
} else {
try {
nextLine = readLine();
return (nextLine != null);
} catch (IOException e) {
throw new UncheckedIOException(e);
}
}
}
@Override
public String next() {
if (nextLine != null || hasNext()) {
String line = nextLine;
nextLine = null;
return line;
} else {
throw new NoSuchElementException();
}
}
};
return StreamSupport.stream(Spliterators.spliteratorUnknownSize(
iter, Spliterator.ORDERED | Spliterator.NONNULL), false);
}
}
Start Date^|^Start Time^|^End Date^|^End Time^|^Event Title ^|^All Day Event^|^No End Time^|^Event Description^|^Contact ^|^Contact Email^|^Contact Phone^|^Location^|^Category^|^Mandatory^|^Registration^|^Maximum^|^Last Date To Register
9/5/2011^|^3:00:00 PM^|^9/5/2011^|^^|^Social Studies Dept. Meeting^|^N^|^Y^|^Department meeting^|^Chris Gallagher^|^cgallagher@schoolwires.com^|^814-555-5179^|^High School^|^2^|^N^|^N^|^25^|^9/2/2011
@Test
public void testLargeFileIO_Scanner() throws Exception {
long start = new Date().getTime();
String fileName = "/Downloads/SampleTextFile_1000kb.txt"; //this path is on my local
InputStream inputStream = new FileInputStream(fileName);
try (Scanner fileScanner = new Scanner(inputStream, StandardCharsets.UTF_8.name())) {
while (fileScanner.hasNextLine()) {
String line = fileScanner.nextLine();
//System.out.println(line);
}
}
long end = new Date().getTime();
long time = end - start;
System.out.println("Scanner Time Consumed => " + time);
}
@Test
public void testLargeFileIO_BufferedReader() throws Exception {
long start = new Date().getTime();
String fileName = "/Downloads/SampleTextFile_1000kb.txt"; //this path is on my local
try (BufferedReader fileBufferReader = new BufferedReader(new FileReader(fileName))) {
String fileLineContent;
while ((fileLineContent = fileBufferReader.readLine()) != null) {
//System.out.println(fileLineContent);
}
}
long end = new Date().getTime();
long time = (long) (end - start);
System.out.println("BufferedReader Time Consumed => " + time);
}
@Test
public void testLargeFileIO_Stream() throws Exception {
long start = new Date().getTime();
String fileName = "/Downloads/SampleTextFile_1000kb.txt"; //this path is on my local
try (Stream inputStream = Files.lines(Paths.get(fileName), StandardCharsets.UTF_8)) {
//inputStream.forEach(System.out::println);
}
long end = new Date().getTime();
long time = end - start;
System.out.println("Stream Time Consumed => " + time);
}
Stream<String> lines = Files.lines(Paths.get("c:\myfile.txt"));
lines.forEach(l -> {
// Do anything line by line
});