@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);
}
@Override
public MatrixBlock readMatrixFromHDFS(
String fname, long rlen, long clen, int brlen, int bclen, long estnnz)
throws IOException, DMLRuntimeException {
// allocate output matrix block
MatrixBlock ret =
createOutputMatrixBlock(rlen, clen, (int) rlen, (int) clen, estnnz, true, false);
// prepare file access
JobConf job = new JobConf(ConfigurationManager.getCachedJobConf());
FileSystem fs = FileSystem.get(job);
Path path = new Path(fname);
// check existence and non-empty file
checkValidInputFile(fs, path);
// core read
readBinaryCellMatrixFromHDFS(path, job, fs, ret, rlen, clen, brlen, bclen);
// finally check if change of sparse/dense block representation required
// (nnz maintained via append during read for both dense/sparse)
ret.examSparsity();
return ret;
}
@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);
}
private static void writeCleanupTasksToFile(Path path, int numTasks)
throws DMLRuntimeException, IOException {
BufferedWriter br = null;
try {
FileSystem fs = FileSystem.get(ConfigurationManager.getCachedJobConf());
br = new BufferedWriter(new OutputStreamWriter(fs.create(path, true)));
for (int i = 1; i <= numTasks; i++) br.write(String.valueOf("CLEANUP TASK " + i) + "\n");
} catch (Exception ex) {
throw new DMLRuntimeException(
"Error writing cleanup tasks to taskfile " + path.toString(), ex);
} finally {
if (br != null) br.close();
}
}
/**
* @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");
}
}
