@Override public final void writeMatrixToHDFS( MatrixBlock src, String fname, long rlen, long clen, int brlen, int bclen, long nnz) throws IOException, DMLRuntimeException { // validity check matrix dimensions if (src.getNumRows() != rlen || src.getNumColumns() != clen) { throw new IOException( "Matrix dimensions mismatch with metadata: " + src.getNumRows() + "x" + src.getNumColumns() + " vs " + rlen + "x" + clen + "."); } // prepare file access JobConf job = new JobConf(ConfigurationManager.getCachedJobConf()); FileSystem fs = FileSystem.get(job); Path path = new Path(fname); // if the file already exists on HDFS, remove it. MapReduceTool.deleteFileIfExistOnHDFS(fname); // core write (sequential/parallel) writeCSVMatrixToHDFS(path, job, fs, src, _props); IOUtilFunctions.deleteCrcFilesFromLocalFileSystem(fs, path); }
/** * @param path * @param job * @param fs * @param dest * @param rlen * @param clen * @param brlen * @param bclen * @throws IOException * @throws IllegalAccessException * @throws InstantiationException */ @SuppressWarnings("deprecation") private void readBinaryBlockMatrixBlocksFromHDFS( Path path, JobConf job, FileSystem fs, Collection<IndexedMatrixValue> dest, long rlen, long clen, int brlen, int bclen) throws IOException { MatrixIndexes key = new MatrixIndexes(); MatrixBlock value = new MatrixBlock(); // set up preferred custom serialization framework for binary block format if (MRJobConfiguration.USE_BINARYBLOCK_SERIALIZATION) MRJobConfiguration.addBinaryBlockSerializationFramework(job); for (Path lpath : getSequenceFilePaths(fs, path)) // 1..N files { // directly read from sequence files (individual partfiles) SequenceFile.Reader reader = new SequenceFile.Reader(fs, lpath, job); try { while (reader.next(key, value)) { int row_offset = (int) (key.getRowIndex() - 1) * brlen; int col_offset = (int) (key.getColumnIndex() - 1) * bclen; int rows = value.getNumRows(); int cols = value.getNumColumns(); // bound check per block if (row_offset + rows < 0 || row_offset + rows > rlen || col_offset + cols < 0 || col_offset + cols > clen) { throw new IOException( "Matrix block [" + (row_offset + 1) + ":" + (row_offset + rows) + "," + (col_offset + 1) + ":" + (col_offset + cols) + "] " + "out of overall matrix range [1:" + rlen + ",1:" + clen + "]."); } // copy block to result dest.add(new IndexedMatrixValue(new MatrixIndexes(key), new MatrixBlock(value))); } } finally { IOUtilFunctions.closeSilently(reader); } } }
@Override public final void writeEmptyMatrixToHDFS(String fname, long rlen, long clen, int brlen, int bclen) throws IOException, DMLRuntimeException { JobConf job = new JobConf(ConfigurationManager.getCachedJobConf()); FileSystem fs = FileSystem.get(job); Path path = new Path(fname); MatrixBlock src = new MatrixBlock((int) rlen, 1, true); writeCSVMatrixToHDFS(path, job, fs, src, _props); IOUtilFunctions.deleteCrcFilesFromLocalFileSystem(fs, path); }
/** * @param srcFileName * @param destFileName * @param csvprop * @param rlen * @param clen * @throws IOException */ @SuppressWarnings("unchecked") public final void addHeaderToCSV(String srcFileName, String destFileName, long rlen, long clen) throws IOException { Configuration conf = new Configuration(ConfigurationManager.getCachedJobConf()); Path srcFilePath = new Path(srcFileName); Path destFilePath = new Path(destFileName); FileSystem hdfs = FileSystem.get(conf); if (!_props.hasHeader()) { // simply move srcFile to destFile /* * TODO: Remove this roundabout way! * For example: destFilePath = /user/biadmin/csv/temp/out/file.csv * & the only path that exists already on HDFS is /user/biadmin/csv/. * In this case: the directory structure /user/biadmin/csv/temp/out must be created. * Simple hdfs.rename() does not seem to create this directory structure. */ // delete the destination file, if exists already // boolean ret1 = hdfs.delete(destFilePath, true); // Create /user/biadmin/csv/temp/out/file.csv so that ..../temp/out/ is created. // boolean ret2 = hdfs.createNewFile(destFilePath); // delete the file "file.csv" but preserve the directory structure /user/biadmin/csv/temp/out/ // boolean ret3 = hdfs.delete(destFilePath, true); // finally, move the data to destFilePath = /user/biadmin/csv/temp/out/file.csv // boolean ret4 = hdfs.rename(srcFilePath, destFilePath); // System.out.println("Return values = del:" + ret1 + ", createNew:" + ret2 + ", del:" + ret3 // + ", rename:" + ret4); return; } // construct the header line StringBuilder sb = new StringBuilder(); for (int i = 0; i < clen; i++) { sb.append("C" + (i + 1)); if (i < clen - 1) sb.append(_props.getDelim()); } sb.append('\n'); if (hdfs.isDirectory(srcFilePath)) { // compute sorted order among part files ArrayList<Path> files = new ArrayList<Path>(); for (FileStatus stat : hdfs.listStatus(srcFilePath, CSVReblockMR.hiddenFileFilter)) files.add(stat.getPath()); Collections.sort(files); // first part file path Path firstpart = files.get(0); // create a temp file, and add header and contents of first part Path tmp = new Path(firstpart.toString() + ".tmp"); OutputStream out = hdfs.create(tmp, true); out.write(sb.toString().getBytes()); sb.setLength(0); // copy rest of the data from firstpart InputStream in = null; try { in = hdfs.open(firstpart); IOUtils.copyBytes(in, out, conf, true); } finally { IOUtilFunctions.closeSilently(in); IOUtilFunctions.closeSilently(out); } // rename tmp to firstpart hdfs.delete(firstpart, true); hdfs.rename(tmp, firstpart); // rename srcfile to destFile hdfs.delete(destFilePath, true); hdfs.createNewFile(destFilePath); // force the creation of directory structure hdfs.delete(destFilePath, true); // delete the file, but preserve the directory structure hdfs.rename(srcFilePath, destFilePath); // move the data } else if (hdfs.isFile(srcFilePath)) { // create destination file OutputStream out = hdfs.create(destFilePath, true); // write header out.write(sb.toString().getBytes()); sb.setLength(0); // copy the data from srcFile InputStream in = null; try { in = hdfs.open(srcFilePath); IOUtils.copyBytes(in, out, conf, true); } finally { IOUtilFunctions.closeSilently(in); IOUtilFunctions.closeSilently(out); } } else { throw new IOException(srcFilePath.toString() + ": No such file or directory"); } }
/** * Method to merge multiple CSV part files on HDFS into a single CSV file on HDFS. The part files * are created by CSV_WRITE MR job. * * <p>This method is invoked from CP-write instruction. * * @param srcFileName * @param destFileName * @param csvprop * @param rlen * @param clen * @throws IOException */ public final void mergeCSVPartFiles( String srcFileName, String destFileName, CSVFileFormatProperties csvprop, long rlen, long clen) throws IOException { Configuration conf = new Configuration(ConfigurationManager.getCachedJobConf()); Path srcFilePath = new Path(srcFileName); Path mergedFilePath = new Path(destFileName); FileSystem hdfs = FileSystem.get(conf); if (hdfs.exists(mergedFilePath)) { hdfs.delete(mergedFilePath, true); } OutputStream out = hdfs.create(mergedFilePath, true); // write out the header, if needed if (csvprop.hasHeader()) { StringBuilder sb = new StringBuilder(); for (int i = 0; i < clen; i++) { sb.append("C" + (i + 1)); if (i < clen - 1) sb.append(csvprop.getDelim()); } sb.append('\n'); out.write(sb.toString().getBytes()); sb.setLength(0); } // if the source is a directory if (hdfs.isDirectory(srcFilePath)) { try { FileStatus[] contents = hdfs.listStatus(srcFilePath); Path[] partPaths = new Path[contents.length]; int numPartFiles = 0; for (int i = 0; i < contents.length; i++) { if (!contents[i].isDirectory()) { partPaths[i] = contents[i].getPath(); numPartFiles++; } } Arrays.sort(partPaths); for (int i = 0; i < numPartFiles; i++) { InputStream in = hdfs.open(partPaths[i]); try { IOUtils.copyBytes(in, out, conf, false); if (i < numPartFiles - 1) out.write('\n'); } finally { IOUtilFunctions.closeSilently(in); } } } finally { IOUtilFunctions.closeSilently(out); } } else if (hdfs.isFile(srcFilePath)) { InputStream in = null; try { in = hdfs.open(srcFilePath); IOUtils.copyBytes(in, out, conf, true); } finally { IOUtilFunctions.closeSilently(in); IOUtilFunctions.closeSilently(out); } } else { throw new IOException(srcFilePath.toString() + ": No such file or directory"); } }
/** * @param fileName * @param src * @param rlen * @param clen * @param nnz * @throws IOException */ protected final void writeCSVMatrixToFile( Path path, JobConf job, FileSystem fs, MatrixBlock src, int rl, int ru, CSVFileFormatProperties props) throws IOException { boolean sparse = src.isInSparseFormat(); int clen = src.getNumColumns(); // create buffered writer BufferedWriter br = new BufferedWriter(new OutputStreamWriter(fs.create(path, true))); try { // for obj reuse and preventing repeated buffer re-allocations StringBuilder sb = new StringBuilder(); props = (props == null) ? new CSVFileFormatProperties() : props; String delim = props.getDelim(); boolean csvsparse = props.isSparse(); // Write header line, if needed if (props.hasHeader() && rl == 0) { // write row chunk-wise to prevent OOM on large number of columns for (int bj = 0; bj < clen; bj += BLOCKSIZE_J) { for (int j = bj; j < Math.min(clen, bj + BLOCKSIZE_J); j++) { sb.append("C" + (j + 1)); if (j < clen - 1) sb.append(delim); } br.write(sb.toString()); sb.setLength(0); } sb.append('\n'); br.write(sb.toString()); sb.setLength(0); } // Write data lines if (sparse) // SPARSE { SparseBlock sblock = src.getSparseBlock(); for (int i = rl; i < ru; i++) { // write row chunk-wise to prevent OOM on large number of columns int prev_jix = -1; if (sblock != null && i < sblock.numRows() && !sblock.isEmpty(i)) { int pos = sblock.pos(i); int alen = sblock.size(i); int[] aix = sblock.indexes(i); double[] avals = sblock.values(i); for (int j = pos; j < pos + alen; j++) { int jix = aix[j]; // output empty fields, if needed for (int j2 = prev_jix; j2 < jix - 1; j2++) { if (!csvsparse) sb.append('0'); sb.append(delim); // flush buffered string if (j2 % BLOCKSIZE_J == 0) { br.write(sb.toString()); sb.setLength(0); } } // output the value (non-zero) sb.append(avals[j]); if (jix < clen - 1) sb.append(delim); br.write(sb.toString()); sb.setLength(0); // flush buffered string if (jix % BLOCKSIZE_J == 0) { br.write(sb.toString()); sb.setLength(0); } prev_jix = jix; } } // Output empty fields at the end of the row. // In case of an empty row, output (clen-1) empty fields for (int bj = prev_jix + 1; bj < clen; bj += BLOCKSIZE_J) { for (int j = bj; j < Math.min(clen, bj + BLOCKSIZE_J); j++) { if (!csvsparse) sb.append('0'); if (j < clen - 1) sb.append(delim); } br.write(sb.toString()); sb.setLength(0); } sb.append('\n'); br.write(sb.toString()); sb.setLength(0); } } else // DENSE { for (int i = rl; i < ru; i++) { // write row chunk-wise to prevent OOM on large number of columns for (int bj = 0; bj < clen; bj += BLOCKSIZE_J) { for (int j = bj; j < Math.min(clen, bj + BLOCKSIZE_J); j++) { double lvalue = src.getValueDenseUnsafe(i, j); if (lvalue != 0) // for nnz sb.append(lvalue); else if (!csvsparse) sb.append('0'); if (j != clen - 1) sb.append(delim); } br.write(sb.toString()); sb.setLength(0); } sb.append('\n'); br.write(sb.toString()); // same as append sb.setLength(0); } } } finally { IOUtilFunctions.closeSilently(br); } }
/** * @param path * @param job * @param fs * @param dest * @param rlen * @param clen * @param brlen * @param bclen * @throws IOException */ @SuppressWarnings("deprecation") private void readBinaryCellMatrixFromHDFS( Path path, JobConf job, FileSystem fs, MatrixBlock dest, long rlen, long clen, int brlen, int bclen) throws IOException { boolean sparse = dest.isInSparseFormat(); MatrixIndexes key = new MatrixIndexes(); MatrixCell value = new MatrixCell(); int row = -1; int col = -1; try { for (Path lpath : getSequenceFilePaths(fs, path)) // 1..N files { // directly read from sequence files (individual partfiles) SequenceFile.Reader reader = new SequenceFile.Reader(fs, lpath, job); try { if (sparse) { while (reader.next(key, value)) { row = (int) key.getRowIndex() - 1; col = (int) key.getColumnIndex() - 1; double lvalue = value.getValue(); dest.appendValue(row, col, lvalue); } } else { while (reader.next(key, value)) { row = (int) key.getRowIndex() - 1; col = (int) key.getColumnIndex() - 1; double lvalue = value.getValue(); dest.appendValue(row, col, lvalue); } } } finally { IOUtilFunctions.closeSilently(reader); } } if (sparse) dest.sortSparseRows(); } catch (Exception ex) { // post-mortem error handling and bounds checking if (row < 0 || row + 1 > rlen || col < 0 || col + 1 > clen) { throw new IOException( "Matrix cell [" + (row + 1) + "," + (col + 1) + "] " + "out of overall matrix range [1:" + rlen + ",1:" + clen + "]."); } else { throw new IOException("Unable to read matrix in binary cell format.", ex); } } }
/** * Note: For efficiency, we directly use SequenceFile.Reader instead of SequenceFileInputFormat- * InputSplits-RecordReader (SequenceFileRecordReader). First, this has no drawbacks since the * SequenceFileRecordReader internally uses SequenceFile.Reader as well. Second, it is * advantageous if the actual sequence files are larger than the file splits created by * informat.getSplits (which is usually aligned to the HDFS block size) because then there is * overhead for finding the actual split between our 1k-1k blocks. This case happens if the read * matrix was create by CP or when jobs directly write to large output files (e.g., parfor matrix * partitioning). * * @param path * @param job * @param fs * @param dest * @param rlen * @param clen * @param brlen * @param bclen * @throws IOException * @throws IllegalAccessException * @throws InstantiationException * @throws DMLRuntimeException */ @SuppressWarnings("deprecation") private static void readBinaryBlockMatrixFromHDFS( Path path, JobConf job, FileSystem fs, MatrixBlock dest, long rlen, long clen, int brlen, int bclen) throws IOException, DMLRuntimeException { boolean sparse = dest.isInSparseFormat(); MatrixIndexes key = new MatrixIndexes(); MatrixBlock value = new MatrixBlock(); // set up preferred custom serialization framework for binary block format if (MRJobConfiguration.USE_BINARYBLOCK_SERIALIZATION) MRJobConfiguration.addBinaryBlockSerializationFramework(job); for (Path lpath : getSequenceFilePaths(fs, path)) // 1..N files { // directly read from sequence files (individual partfiles) SequenceFile.Reader reader = new SequenceFile.Reader(fs, lpath, job); try { // note: next(key, value) does not yet exploit the given serialization classes, record // reader does but is generally slower. while (reader.next(key, value)) { // empty block filter (skip entire block) if (value.isEmptyBlock(false)) continue; int row_offset = (int) (key.getRowIndex() - 1) * brlen; int col_offset = (int) (key.getColumnIndex() - 1) * bclen; int rows = value.getNumRows(); int cols = value.getNumColumns(); // bound check per block if (row_offset + rows < 0 || row_offset + rows > rlen || col_offset + cols < 0 || col_offset + cols > clen) { throw new IOException( "Matrix block [" + (row_offset + 1) + ":" + (row_offset + rows) + "," + (col_offset + 1) + ":" + (col_offset + cols) + "] " + "out of overall matrix range [1:" + rlen + ",1:" + clen + "]."); } // copy block to result if (sparse) { dest.appendToSparse(value, row_offset, col_offset); // note: append requires final sort } else { dest.copy( row_offset, row_offset + rows - 1, col_offset, col_offset + cols - 1, value, false); } } } finally { IOUtilFunctions.closeSilently(reader); } } if (sparse && clen > bclen) { // no need to sort if 1 column block since always sorted dest.sortSparseRows(); } }
/** * @param path * @param job * @param src * @param rlen * @param clen * @param brlen * @param bclen * @throws IOException */ protected void writeTextCellMatrixToHDFS( Path path, JobConf job, MatrixBlock src, long rlen, long clen) throws IOException { boolean sparse = src.isInSparseFormat(); boolean entriesWritten = false; FileSystem fs = FileSystem.get(job); BufferedWriter br = new BufferedWriter(new OutputStreamWriter(fs.create(path, true))); int rows = src.getNumRows(); int cols = src.getNumColumns(); // bound check per block if (rows > rlen || cols > clen) { throw new IOException( "Matrix block [1:" + rows + ",1:" + cols + "] " + "out of overall matrix range [1:" + rlen + ",1:" + clen + "]."); } try { // for obj reuse and preventing repeated buffer re-allocations StringBuilder sb = new StringBuilder(); if (sparse) // SPARSE { SparseRowsIterator iter = src.getSparseRowsIterator(); while (iter.hasNext()) { IJV cell = iter.next(); sb.append(cell.i + 1); sb.append(' '); sb.append(cell.j + 1); sb.append(' '); sb.append(cell.v); sb.append('\n'); br.write(sb.toString()); // same as append sb.setLength(0); entriesWritten = true; } } else // DENSE { for (int i = 0; i < rows; i++) { String rowIndex = Integer.toString(i + 1); for (int j = 0; j < cols; j++) { double lvalue = src.getValueDenseUnsafe(i, j); if (lvalue != 0) // for nnz { sb.append(rowIndex); sb.append(' '); sb.append(j + 1); sb.append(' '); sb.append(lvalue); sb.append('\n'); br.write(sb.toString()); // same as append sb.setLength(0); entriesWritten = true; } } } } // handle empty result if (!entriesWritten) { br.write("1 1 0\n"); } } finally { IOUtilFunctions.closeSilently(br); } }