def parse_channel(channel, model, pool_size=DEFAULT_POOL_SIZE,
progress_monitor=NullProgressMonitor(), parse_refs=True):
manager = multiprocessing.Manager()
lock = manager.RLock()
work_units = pool_size * BUCKET_PER_WORKER
# Prepare Input
entries = []
for entry in model.entries:
if not entry.parsed:
entries.append((entry.local_paths, entry.url))
entry.parsed = True
entries_chunks = chunk_it(entries, work_units)
inputs = []
for entry_chunk in entries_chunks:
inputs.append((channel.parser, channel.pk, entry_chunk, parse_refs,
lock))
# Close connection to allow the new processes to create their own
connection.close()
progress_monitor.start('Parsing Channel Entries', len(inputs))
progress_monitor.info('Sending {0} chunks to worker pool'
.format(len(inputs)))
pool = multiprocessing.Pool(pool_size)
for result in pool.imap_unordered(sub_process_parse, inputs,
BUCKET_PER_WORKER):
progress_monitor.work('Parsed a chunk', 1)
pool.close()
progress_monitor.done()
def parse(document, pages, parse_refs=True,
progress_monitor=NullProgressMonitor(),
pool_size=DEFAULT_POOL_SIZE):
progress_monitor.start('Parsing Pages', pool_size + 1)
# Prepare input
pages = [(page.local_url, page.url) for page in
pages.values() if page.local_url is not None]
pages_chunks = chunk_it(pages, pool_size)
inputs = []
for pages_chunk in pages_chunks:
inputs.append((document.parser, document.pk, parse_refs, pages_chunk))
# Close connection to allow the new processes to create their own.
connection.close()
# Split work
progress_monitor.info('Sending {0} chunks to worker pool'
.format(len(inputs)))
pool = Pool(pool_size)
for result in pool.imap_unordered(sub_process_parse, inputs, 1):
progress_monitor.work('Parsed 1/{0} of the pages'.\
format(pool_size), 1)
# Word Count
word_count = 0
for page in document.pages.all():
word_count += page.word_count
document.word_count = word_count
document.save()
progress_monitor.work('Counted Total Words', 1)
pool.close()
progress_monitor.done()
def parse_channel(channel,
model,
pool_size=DEFAULT_POOL_SIZE,
progress_monitor=NullProgressMonitor(),
parse_refs=True):
manager = multiprocessing.Manager()
lock = manager.RLock()
work_units = pool_size * BUCKET_PER_WORKER
# Prepare Input
entries = []
for entry in model.entries:
if not entry.parsed:
entries.append((entry.local_paths, entry.url))
entry.parsed = True
entries_chunks = chunk_it(entries, work_units)
inputs = []
for entry_chunk in entries_chunks:
inputs.append(
(channel.parser, channel.pk, entry_chunk, parse_refs, lock))
# Close connection to allow the new processes to create their own
connection.close()
progress_monitor.start('Parsing Channel Entries', len(inputs))
progress_monitor.info('Sending {0} chunks to worker pool'.format(
len(inputs)))
pool = multiprocessing.Pool(pool_size)
for result in pool.imap_unordered(sub_process_parse, inputs,
BUCKET_PER_WORKER):
progress_monitor.work('Parsed a chunk', 1)
pool.close()
progress_monitor.done()
def parse(document,
pages,
parse_refs=True,
progress_monitor=NullProgressMonitor(),
pool_size=DEFAULT_POOL_SIZE):
progress_monitor.start('Parsing Pages', pool_size + 1)
# Prepare input
pages = [(page.local_url, page.url) for page in pages.values()
if page.local_url is not None]
pages_chunks = chunk_it(pages, pool_size)
inputs = []
for pages_chunk in pages_chunks:
inputs.append((document.parser, document.pk, parse_refs, pages_chunk))
# Close connection to allow the new processes to create their own.
connection.close()
# Split work
progress_monitor.info('Sending {0} chunks to worker pool'.format(
len(inputs)))
pool = Pool(pool_size)
for result in pool.imap_unordered(sub_process_parse, inputs, 1):
progress_monitor.work('Parsed 1/{0} of the pages'.\
format(pool_size), 1)
# Word Count
word_count = 0
for page in document.pages.all():
word_count += page.word_count
document.word_count = word_count
document.save()
progress_monitor.work('Counted Total Words', 1)
pool.close()
progress_monitor.done()
