def mr_map_parallel(
processor,
fd=STDIN,
workers=NCPUS,
chunk_size=1000,
out=STDOUT,
):
"""Map in parallel.
`processor` must be an instance of Mapper and promise that it is
safe to execute in a fork()d process. Also note that we f**k
up the result ordering, but relying on result ordering breaks
the mapreduce contract anyway. Note also that like many of the
mr_tools functions, we break on newlines in the emitted output
:param processor: an multiprocessing-safe instance of :py:class:`Mapper`
:param int workers: Number of concurrent workers.
:param int chunk_size: job size per worker
:param file fd: Input data stream (default is stdin)
:param file out: Output data stream (default is stdout)
:type processor: :py:class:`Mapper`
"""
if workers == 1:
return mr_map(processor, fd=fd, out=out)
pool = multiprocessing.Pool(workers)
for res in pool.imap_unordered(processor, fd, chunk_size):
for subres in res:
emit(subres, out=out)
def mr_map_parallel(
processor,
fd=STDIN,
workers=NCPUS,
chunk_size=1000,
out=STDOUT,
):
"""Map in parallel.
`processor` must be an instance of Mapper and promise that it is
safe to execute in a fork()d process. Also note that we f**k
up the result ordering, but relying on result ordering breaks
the mapreduce contract anyway. Note also that like many of the
mr_tools functions, we break on newlines in the emitted output
:param processor: an multiprocessing-safe instance of :py:class:`Mapper`
:param int workers: Number of concurrent workers.
:param int chunk_size: job size per worker
:param file fd: Input data stream (default is stdin)
:param file out: Output data stream (default is stdout)
:type processor: :py:class:`Mapper`
"""
if workers == 1:
return mr_map(processor, fd=fd, out=out)
pool = multiprocessing.Pool(workers)
for res in pool.imap_unordered(processor, fd, chunk_size):
for subres in res:
emit(subres, out=out)
def mr_map_parallel(processor, fd=stdin, workers=multiprocessing.cpu_count(), chunk_size=1000):
# `process` must be an instance of Mapper and promise that it is
# safe to execute in a fork()d process. Also note that we f**k
# up the result ordering, but relying on result ordering breaks
# the mapreduce contract anyway. Note also that like many of the
# mr_tools functions, we break on newlines in the emitted output
if workers == 1:
return mr_map(process, fd=fd)
pool = multiprocessing.Pool(workers)
for res in pool.imap_unordered(processor, fd, chunk_size):
for subres in res:
emit(subres)
def mr_map_parallel(processor, fd = stdin,
workers = multiprocessing.cpu_count(),
chunk_size = 1000):
# `process` must be an instance of Mapper and promise that it is
# safe to execute in a fork()d process. Also note that we f**k
# up the result ordering, but relying on result ordering breaks
# the mapreduce contract anyway. Note also that like many of the
# mr_tools functions, we break on newlines in the emitted output
if workers == 1:
return mr_map(process, fd=fd)
pool = multiprocessing.Pool(workers)
for res in pool.imap_unordered(processor, fd, chunk_size):
for subres in res:
emit(subres)
