List of usage examples for org.apache.hadoop.io Text clear
public void clear()
From source file:mapred.io.CustomRecordReader.java
License:Apache License
private int skipUtfByteOrderMark() throws IOException { Text value = new Text(); // Strip BOM(Byte Order Mark) // Text only support UTF-8, we only need to check UTF-8 BOM // (0xEF,0xBB,0xBF) at the start of the text stream. int newMaxLineLength = (int) Math.min(3L + (long) maxLineLength, Integer.MAX_VALUE); int newSize = in.readLine(value, newMaxLineLength, maxBytesToConsume(pos)); // Even we read 3 extra bytes for the first line, // we won't alter existing behavior (no backwards incompat issue). // Because the newSize is less than maxLineLength and // the number of bytes copied to Text is always no more than newSize. // If the return size from readLine is not less than maxLineLength, // we will discard the current line and read the next line. pos += newSize;/*from w w w . j a v a 2s . co m*/ int textLength = value.getLength(); byte[] textBytes = value.getBytes(); if ((textLength >= 3) && (textBytes[0] == (byte) 0xEF) && (textBytes[1] == (byte) 0xBB) && (textBytes[2] == (byte) 0xBF)) { // find UTF-8 BOM, strip it. LOG.info("Found UTF-8 BOM and skipped it"); textLength -= 3; newSize -= 3; if (textLength > 0) { // It may work to use the same buffer and not do the copyBytes textBytes = value.copyBytes(); value.set(textBytes, 3, textLength); } else { value.clear(); } } return newSize; }
From source file:mr.MyFileRecordReader2.java
License:Apache License
private int skipUtfByteOrderMark(Text value) throws IOException { // Strip BOM(Byte Order Mark) // Text only support UTF-8, we only need to check UTF-8 BOM // (0xEF,0xBB,0xBF) at the start of the text stream. int newMaxLineLength = (int) Math.min(3L + (long) maxLineLength, Integer.MAX_VALUE); int newSize = in.readLine(value, newMaxLineLength, maxBytesToConsume(pos)); // Even we read 3 extra bytes for the first line, // we won't alter existing behavior (no backwards incompat issue). // Because the newSize is less than maxLineLength and // the number of bytes copied to Text is always no more than newSize. // If the return size from readLine is not less than maxLineLength, // we will discard the current line and read the next line. pos += newSize;//from ww w . ja v a 2s.c o m int textLength = value.getLength(); byte[] textBytes = value.getBytes(); if ((textLength >= 3) && (textBytes[0] == (byte) 0xEF) && (textBytes[1] == (byte) 0xBB) && (textBytes[2] == (byte) 0xBF)) { // find UTF-8 BOM, strip it. LOG.info("Found UTF-8 BOM and skipped it"); textLength -= 3; newSize -= 3; if (textLength > 0) { // It may work to use the same buffer and not do the copyBytes textBytes = value.copyBytes(); value.set(textBytes, 3, textLength); } else { value.clear(); } } return newSize; }
From source file:mr.MyLineReader.java
License:Apache License
private int myReadLine(Text str, int maxLineLength, int maxBytesToConsume) throws IOException { System.out.println("Enter myReadLine!!!"); str.clear(); int txtLength = 0; // tracks str.getLength(), as an optimization long bytesConsumed = 0; int delPosn = 0; do {//from w ww .ja v a2 s . co m int startPosn = bufferPosn; // starting from where we left off the last time bufferPosn = buffer.length; int n = -1; int readLength = 0; while ((n = in.read(buffer)) > 0) { readLength += n; } bytesConsumed += readLength; int appendLength = readLength - delPosn; if (appendLength > maxLineLength - txtLength) { appendLength = maxLineLength - txtLength; } if (appendLength > 0) { str.append(buffer, startPosn, appendLength); txtLength += appendLength; } } while (delPosn < recordDelimiterBytes.length && bytesConsumed < maxBytesToConsume); if (bytesConsumed > (long) Integer.MAX_VALUE) throw new IOException("Too many bytes before delimiter: " + bytesConsumed); return (int) bytesConsumed; }
From source file:mr.MyLineReader.java
License:Apache License
/** * Read a line terminated by a custom delimiter. *///from w w w .j av a2 s . c o m private int readCustomLine(Text str, int maxLineLength, int maxBytesToConsume) throws IOException { System.out.println("Enter readCustomLine!!!"); str.clear(); int txtLength = 0; // tracks str.getLength(), as an optimization long bytesConsumed = 0; int delPosn = 0; do { int startPosn = bufferPosn; // starting from where we left off the // last // time if (bufferPosn >= bufferLength) { startPosn = bufferPosn = 0; bufferLength = in.read(buffer); if (bufferLength <= 0) break; // EOF } for (; bufferPosn < bufferLength; ++bufferPosn) { if (buffer[bufferPosn] == recordDelimiterBytes[delPosn]) { delPosn++; if (delPosn >= recordDelimiterBytes.length) { bufferPosn++; break; } } else { delPosn = 0; } } int readLength = bufferPosn - startPosn; bytesConsumed += readLength; int appendLength = readLength - delPosn; if (appendLength > maxLineLength - txtLength) { appendLength = maxLineLength - txtLength; } if (appendLength > 0) { str.append(buffer, startPosn, appendLength); txtLength += appendLength; } } while (delPosn < recordDelimiterBytes.length && bytesConsumed < maxBytesToConsume); if (bytesConsumed > (long) Integer.MAX_VALUE) throw new IOException("Too many bytes before delimiter: " + bytesConsumed); return (int) bytesConsumed; }
From source file:oracle.kv.hadoop.hive.table.TableHiveRecordReader.java
License:Open Source License
@Override public boolean next(Text key, Text value) { LOG.trace("next [key = " + key + ", value = " + value + "]"); if (key == null || value == null) { return false; }//from w ww.j a va 2 s. c om boolean ret = false; try { key.clear(); value.clear(); ret = v2RecordReader.nextKeyValue(); if (ret) { final Row curRow = v2RecordReader.getCurrentValue(); assert curRow != null; key.set(curRow.createPrimaryKey().toString()); value.set(curRow.toString()); } } catch (Exception e) { LOG.error("TableHiveRecordReader " + this + " caught: " + e, e); } return ret; }
From source file:org.apache.accumulo.examples.wikisearch.reader.LfLineReader.java
License:Apache License
/** * Read one line from the InputStream into the given Text. A line can be terminated by '\n' (LF). * EOF also terminates an otherwise unterminated line. * * @param str/*from w ww . jav a 2s . c om*/ * the object to store the given line (without newline) * @param maxLineLength * the maximum number of bytes to store into str; the rest of the line is silently * discarded. * @param maxBytesToConsume * the maximum number of bytes to consume in this call. This is only a hint, because if * the line cross this threshold, we allow it to happen. It can overshoot potentially by * as much as one buffer length. * * @return the number of bytes read including the (longest) newline found. * * @throws IOException * if the underlying stream throws */ public int readLine(Text str, int maxLineLength, int maxBytesToConsume) throws IOException { /* * We're reading data from in, but the head of the stream may be already buffered in buffer, so * we have several cases: 1. No newline characters are in the buffer, so we need to copy * everything and read another buffer from the stream. 2. An unambiguously terminated line is in * buffer, so we just copy to str. */ str.clear(); int txtLength = 0; // tracks str.getLength(), as an optimization int newlineLength = 0; // length of terminating newline long bytesConsumed = 0; do { int startPosn = bufferPosn; // starting from where we left off the last time if (bufferPosn >= bufferLength) { startPosn = bufferPosn = 0; bufferLength = in.read(buffer); if (bufferLength <= 0) { break; // EOF } } for (; bufferPosn < bufferLength; ++bufferPosn) { // search for newline if (buffer[bufferPosn] == LF) { newlineLength = 1; ++bufferPosn; // at next invocation proceed from following byte break; } } int readLength = bufferPosn - startPosn; bytesConsumed += readLength; int appendLength = readLength - newlineLength; if (appendLength > maxLineLength - txtLength) { appendLength = maxLineLength - txtLength; } if (appendLength > 0) { str.append(buffer, startPosn, appendLength); txtLength += appendLength; } } while (newlineLength == 0 && bytesConsumed < maxBytesToConsume); if (bytesConsumed > Integer.MAX_VALUE) { throw new IOException("Too many bytes before newline: " + bytesConsumed); } return (int) bytesConsumed; }
From source file:org.apache.asterix.external.indexing.input.HDFSSeekableLineReader.java
License:Apache License
/** * Read one line from the InputStream into the given Text. A line * can be terminated by one of the following: '\n' (LF) , '\r' (CR), * or '\r\n' (CR+LF). EOF also terminates an otherwise unterminated * line./* ww w. j a va2s .co m*/ * * @param str * the object to store the given line (without newline) * @param maxLineLength * the maximum number of bytes to store into str; * the rest of the line is silently discarded. * @param maxBytesToConsume * the maximum number of bytes to consume * in this call. This is only a hint, because if the line cross * this threshold, we allow it to happen. It can overshoot * potentially by as much as one buffer length. * @return the number of bytes read including the (longest) newline * found. * @throws IOException * if the underlying stream throws */ public int readLine(Text str, int maxLineLength, int maxBytesToConsume) throws IOException { /* We're reading data from in, but the head of the stream may be * already buffered in buffer, so we have several cases: * 1. No newline characters are in the buffer, so we need to copy * everything and read another buffer from the stream. * 2. An unambiguously terminated line is in buffer, so we just * copy to str. * 3. Ambiguously terminated line is in buffer, i.e. buffer ends * in CR. In this case we copy everything up to CR to str, but * we also need to see what follows CR: if it's LF, then we * need consume LF as well, so next call to readLine will read * from after that. * We use a flag prevCharCR to signal if previous character was CR * and, if it happens to be at the end of the buffer, delay * consuming it until we have a chance to look at the char that * follows. */ str.clear(); int txtLength = 0; //tracks str.getLength(), as an optimization int newlineLength = 0; //length of terminating newline boolean prevCharCR = false; //true of prev char was CR long bytesConsumed = 0; do { int startPosn = bufferPosn; //starting from where we left off the last time if (bufferPosn >= bufferLength) { startPosn = bufferPosn = 0; if (prevCharCR) ++bytesConsumed; //account for CR from previous read bufferLength = reader.read(buffer); if (bufferLength <= 0) break; // EOF } for (; bufferPosn < bufferLength; ++bufferPosn) { //search for newline if (buffer[bufferPosn] == LF) { newlineLength = (prevCharCR) ? 2 : 1; ++bufferPosn; // at next invocation proceed from following byte break; } if (prevCharCR) { //CR + notLF, we are at notLF newlineLength = 1; break; } prevCharCR = (buffer[bufferPosn] == CR); } int readLength = bufferPosn - startPosn; if (prevCharCR && newlineLength == 0) --readLength; //CR at the end of the buffer bytesConsumed += readLength; int appendLength = readLength - newlineLength; if (appendLength > maxLineLength - txtLength) { appendLength = maxLineLength - txtLength; } if (appendLength > 0) { str.append(buffer, startPosn, appendLength); txtLength += appendLength; } } while (newlineLength == 0 && bytesConsumed < maxBytesToConsume); if (bytesConsumed > (long) Integer.MAX_VALUE) throw new IOException("Too many bytes before newline: " + bytesConsumed); currentFilePos = reader.getPos() - bufferLength + bufferPosn; return (int) bytesConsumed; }
From source file:org.apache.asterix.external.input.record.reader.hdfs.HDFSTextLineReader.java
License:Apache License
/** * Read one line from the InputStream into the given Text. A line * can be terminated by one of the following: '\n' (LF) , '\r' (CR), * or '\r\n' (CR+LF). EOF also terminates an otherwise unterminated * line./*w w w . j ava 2 s . c o m*/ * * @param str * the object to store the given line (without newline) * @param maxLineLength * the maximum number of bytes to store into str; * the rest of the line is silently discarded. * @param maxBytesToConsume * the maximum number of bytes to consume * in this call. This is only a hint, because if the line cross * this threshold, we allow it to happen. It can overshoot * potentially by as much as one buffer length. * @return the number of bytes read including the (longest) newline * found. * @throws IOException * if the underlying stream throws */ public int readLine(Text str, int maxLineLength, int maxBytesToConsume) throws IOException { /* We're reading data from in, but the head of the stream may be * already buffered in buffer, so we have several cases: * 1. No newline characters are in the buffer, so we need to copy * everything and read another buffer from the stream. * 2. An unambiguously terminated line is in buffer, so we just * copy to str. * 3. Ambiguously terminated line is in buffer, i.e. buffer ends * in CR. In this case we copy everything up to CR to str, but * we also need to see what follows CR: if it's LF, then we * need consume LF as well, so next call to readLine will read * from after that. * We use a flag prevCharCR to signal if previous character was CR * and, if it happens to be at the end of the buffer, delay * consuming it until we have a chance to look at the char that * follows. */ str.clear(); int txtLength = 0; //tracks str.getLength(), as an optimization int newlineLength = 0; //length of terminating newline boolean prevCharCR = false; //true of prev char was CR long bytesConsumed = 0; do { int startPosn = bufferPosn; //starting from where we left off the last time if (bufferPosn >= bufferLength) { startPosn = bufferPosn = 0; if (prevCharCR) ++bytesConsumed; //account for CR from previous read bufferLength = reader.read(buffer); if (bufferLength <= 0) break; // EOF } for (; bufferPosn < bufferLength; ++bufferPosn) { //search for newline if (buffer[bufferPosn] == LF) { newlineLength = (prevCharCR) ? 2 : 1; ++bufferPosn; // at next invocation proceed from following byte break; } if (prevCharCR) { //CR + notLF, we are at notLF newlineLength = 1; break; } prevCharCR = (buffer[bufferPosn] == CR); } int readLength = bufferPosn - startPosn; if (prevCharCR && newlineLength == 0) --readLength; //CR at the end of the buffer bytesConsumed += readLength; int appendLength = readLength - newlineLength; if (appendLength > maxLineLength - txtLength) { appendLength = maxLineLength - txtLength; } if (appendLength > 0) { str.append(buffer, startPosn, appendLength); txtLength += appendLength; } } while (newlineLength == 0 && bytesConsumed < maxBytesToConsume); if (bytesConsumed > Integer.MAX_VALUE) throw new IOException("Too many bytes before newline: " + bytesConsumed); currentFilePos = reader.getPos() - bufferLength + bufferPosn; return (int) bytesConsumed; }
From source file:org.apache.ben.QuotationLineReader.java
License:Apache License
/** * Read a line terminated by one of CR, LF, or CRLF. *///from w w w . j a va2 s . com private int readDefaultLine(Text str, int maxLineLength, int maxBytesToConsume) throws IOException { /* We're reading data from in, but the head of the stream may be * already buffered in buffer, so we have several cases: * 1. No newline characters are in the buffer, so we need to copy * everything and read another buffer from the stream. * 2. An unambiguously terminated line is in buffer, so we just * copy to str. * 3. Ambiguously terminated line is in buffer, i.e. buffer ends * in CR. In this case we copy everything up to CR to str, but * we also need to see what follows CR: if it's LF, then we * need consume LF as well, so next call to readLine will read * from after that. * We use a flag prevCharCR to signal if previous character was CR * and, if it happens to be at the end of the buffer, delay * consuming it until we have a chance to look at the char that * follows. */ str.clear(); int txtLength = 0; //tracks str.getLength(), as an optimization int newlineLength = 0; //length of terminating newline boolean prevCharCR = false; //true of prev char was CR int quoteBefore = 0; boolean previousCharEsc = false; long bytesConsumed = 0; do { int startPosn = bufferPosn; //starting from where we left off the last time if (bufferPosn >= bufferLength) { startPosn = bufferPosn = 0; if (prevCharCR) { ++bytesConsumed; //account for CR from previous read } bufferLength = in.read(buffer); if (bufferLength <= 0) { break; // EOF } } for (; bufferPosn < bufferLength; ++bufferPosn) { //search for newline if (buffer[bufferPosn] == QUOTE) { if (!previousCharEsc) { quoteBefore = (quoteBefore == 0) ? 1 : 0; } } if (buffer[bufferPosn] == LF && (quoteBefore == 0)) { newlineLength = (prevCharCR) ? 2 : 1; ++bufferPosn; // at next invocation proceed from following byte break; } if (prevCharCR) { //CR + notLF, we are at notLF newlineLength = 1; break; } prevCharCR = (buffer[bufferPosn] == CR); previousCharEsc = (buffer[bufferPosn] == ESCAPE); } int readLength = bufferPosn - startPosn; if (prevCharCR && newlineLength == 0) { --readLength; //CR at the end of the buffer } bytesConsumed += readLength; int appendLength = readLength - newlineLength; if (appendLength > maxLineLength - txtLength) { appendLength = maxLineLength - txtLength; } if (appendLength > 0) { str.append(buffer, startPosn, appendLength); txtLength += appendLength; } } while (newlineLength == 0 && bytesConsumed < maxBytesToConsume); if (bytesConsumed > (long) Integer.MAX_VALUE) { throw new IOException("Too many bytes before newline: " + bytesConsumed); } return (int) bytesConsumed; }
From source file:org.apache.ben.QuotationLineReader.java
License:Apache License
/** * Read a line terminated by a custom delimiter. */// ww w . j av a 2 s . c om private int readCustomLine(Text str, int maxLineLength, int maxBytesToConsume) throws IOException { /* We're reading data from inputStream, but the head of the stream may be * already captured in the previous buffer, so we have several cases: * * 1. The buffer tail does not contain any character sequence which * matches with the head of delimiter. We count it as a * ambiguous byte count = 0 * * 2. The buffer tail contains a X number of characters, * that forms a sequence, which matches with the * head of delimiter. We count ambiguous byte count = X * * // *** eg: A segment of input file is as follows * * " record 1792: I found this bug very interesting and * I have completely read about it. record 1793: This bug * can be solved easily record 1794: This ." * * delimiter = "record"; * * supposing:- String at the end of buffer = * "I found this bug very interesting and I have completely re" * There for next buffer = "ad about it. record 179 ...." * * The matching characters in the input * buffer tail and delimiter head = "re" * Therefore, ambiguous byte count = 2 **** // * * 2.1 If the following bytes are the remaining characters of * the delimiter, then we have to capture only up to the starting * position of delimiter. That means, we need not include the * ambiguous characters in str. * * 2.2 If the following bytes are not the remaining characters of * the delimiter ( as mentioned in the example ), * then we have to include the ambiguous characters in str. */ str.clear(); int txtLength = 0; // tracks str.getLength(), as an optimization long bytesConsumed = 0; int delPosn = 0; int ambiguousByteCount = 0; // To capture the ambiguous characters count do { int startPosn = bufferPosn; // Start from previous end position if (bufferPosn >= bufferLength) { startPosn = bufferPosn = 0; bufferLength = in.read(buffer); if (bufferLength <= 0) { str.append(recordDelimiterBytes, 0, ambiguousByteCount); break; // EOF } } for (; bufferPosn < bufferLength; ++bufferPosn) { if (buffer[bufferPosn] == recordDelimiterBytes[delPosn]) { delPosn++; if (delPosn >= recordDelimiterBytes.length) { bufferPosn++; break; } } else if (delPosn != 0) { bufferPosn--; delPosn = 0; } } int readLength = bufferPosn - startPosn; bytesConsumed += readLength; int appendLength = readLength - delPosn; if (appendLength > maxLineLength - txtLength) { appendLength = maxLineLength - txtLength; } if (appendLength > 0) { if (ambiguousByteCount > 0) { str.append(recordDelimiterBytes, 0, ambiguousByteCount); //appending the ambiguous characters (refer case 2.2) bytesConsumed += ambiguousByteCount; ambiguousByteCount = 0; } str.append(buffer, startPosn, appendLength); txtLength += appendLength; } if (bufferPosn >= bufferLength) { if (delPosn > 0 && delPosn < recordDelimiterBytes.length) { ambiguousByteCount = delPosn; bytesConsumed -= ambiguousByteCount; //to be consumed in next } } } while (delPosn < recordDelimiterBytes.length && bytesConsumed < maxBytesToConsume); if (bytesConsumed > (long) Integer.MAX_VALUE) { throw new IOException("Too many bytes before delimiter: " + bytesConsumed); } return (int) bytesConsumed; }