/**
* Add files in the input path recursively into the results.
*
* @param result The List to store all files.
* @param fs The FileSystem.
* @param path The input path.
* @param inputFilter The input filter that can be used to filter files/dirs.
* @throws IOException
*/
protected void addInputPathRecursively(
List<FileStatus> result, FileSystem fs, Path path, PathFilter inputFilter)
throws IOException {
RemoteIterator<LocatedFileStatus> iter = fs.listLocatedStatus(path);
while (iter.hasNext()) {
LocatedFileStatus stat = iter.next();
if (inputFilter.accept(stat.getPath())) {
if (stat.isDirectory()) {
addInputPathRecursively(result, fs, stat.getPath(), inputFilter);
} else {
result.add(stat);
}
}
}
}
private List<FileStatus> singleThreadedListStatus(
JobContext job, Path[] dirs, PathFilter inputFilter, boolean recursive) throws IOException {
List<FileStatus> result = new ArrayList<FileStatus>();
List<IOException> errors = new ArrayList<IOException>();
for (int i = 0; i < dirs.length; ++i) {
Path p = dirs[i];
FileSystem fs = p.getFileSystem(job.getConfiguration());
FileStatus[] matches = fs.globStatus(p, inputFilter);
if (matches == null) {
errors.add(new IOException("Input path does not exist: " + p));
} else if (matches.length == 0) {
errors.add(new IOException("Input Pattern " + p + " matches 0 files"));
} else {
for (FileStatus globStat : matches) {
if (globStat.isDirectory()) {
RemoteIterator<LocatedFileStatus> iter = fs.listLocatedStatus(globStat.getPath());
while (iter.hasNext()) {
LocatedFileStatus stat = iter.next();
if (inputFilter.accept(stat.getPath())) {
if (recursive && stat.isDirectory()) {
addInputPathRecursively(result, fs, stat.getPath(), inputFilter);
} else {
result.add(stat);
}
}
}
} else {
result.add(globStat);
}
}
}
}
if (!errors.isEmpty()) {
throw new InvalidInputException(errors);
}
return result;
}