def test_group_processing(self):
FILES = ['test_data/a_modest_proposal.txt',
'test_data/metamorphosis.txt',
'test_data/leviathan.txt']
texts = [open(name, 'r').read() for name in FILES]
top10 = json.loads(open('test_data/combined.json', 'r').read())
result = group(word_count.s(text) for text in texts).apply_async()
self.assertEqual(top_ten(reduce_word_count(result.get())), top10)
def test_group_processing(self):
FILES = [
'test_data/a_modest_proposal.txt', 'test_data/metamorphosis.txt',
'test_data/leviathan.txt'
]
texts = [open(name, 'r').read() for name in FILES]
top10 = json.loads(open('test_data/combined.json', 'r').read())
result = group(word_count.s(text) for text in texts).apply_async()
self.assertEqual(top_ten(reduce_word_count(result.get())), top10)
#
# This program is free software; you can redistribute it and/or
# modify it under the terms of the GNU General Public License
# as published by the Free Software Foundation; either version 2
# of the License, or (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, see <http://www.gnu.org/licenses/>.
from __future__ import absolute_import
from celery import group
import sys
from worker import word_count
from collector import reduce_word_count, top_ten
if len(sys.argv) == 1:
print(
"Simple distributed file indexer: counts top 10 words in files in\n"
"provided directories.\n"
"Usage: python scheduler.py FILE1 FILE2 ...")
else:
texts = [open(name, 'r').read() for name in sys.argv[1:]]
result = group(word_count.s(text) for text in texts).apply_async()
print top_ten(reduce_word_count(result.get()))
def test_two_dicts(self):
self.assertEqual(
reduce_word_count([Counter({'word': 1}),
Counter({'word': 2})]), Counter({'word': 3}))
# modify it under the terms of the GNU General Public License
# as published by the Free Software Foundation; either version 2
# of the License, or (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, see <http://www.gnu.org/licenses/>.
from __future__ import absolute_import
from celery import group
import sys
from worker import word_count
from collector import reduce_word_count, top_ten
if len(sys.argv) == 1:
print (
"Simple distributed file indexer: counts top 10 words in files in\n"
"provided directories.\n"
"Usage: python scheduler.py FILE1 FILE2 ..."
)
else:
texts = [open(name, "r").read() for name in sys.argv[1:]]
result = group(word_count.s(text) for text in texts).apply_async()
print top_ten(reduce_word_count(result.get()))
def test_single_dict(self):
self.assertEqual(reduce_word_count([Counter({'word': 1})]),
Counter({'word': 1}))
def test_empty(self):
self.assertEqual(reduce_word_count([]), Counter())
def test_two_dicts(self):
self.assertEqual(reduce_word_count(
[Counter({'word': 1}), Counter({'word': 2})]),
Counter({'word': 3}))
def test_single_dict(self):
self.assertEqual(reduce_word_count(
[Counter({'word': 1})]),
Counter({'word': 1}))
def test_empty(self):
self.assertEqual(reduce_word_count([]), Counter())
