mirror of
https://github.com/emilybache/GildedRose-Refactoring-Kata.git
synced 2026-02-09 11:41:37 +00:00
48 lines
1.5 KiB
Python
48 lines
1.5 KiB
Python
# Copyright 2009-2010 Yelp
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
|
|
"""An implementation of wc as an MRJob.
|
|
|
|
This is meant as an example of why mapper_final is useful."""
|
|
from mrjob.job import MRJob
|
|
|
|
|
|
class MRWordCountUtility(MRJob):
|
|
|
|
def __init__(self, *args, **kwargs):
|
|
super(MRWordCountUtility, self).__init__(*args, **kwargs)
|
|
self.chars = 0
|
|
self.words = 0
|
|
self.lines = 0
|
|
|
|
def mapper(self, _, line):
|
|
# Don't actually yield anything for each line. Instead, collect them
|
|
# and yield the sums when all lines have been processed. The results
|
|
# will be collected by the reducer.
|
|
self.chars += len(line) + 1 # +1 for newline
|
|
self.words += sum(1 for word in line.split() if word.strip())
|
|
self.lines += 1
|
|
|
|
def mapper_final(self):
|
|
yield('chars', self.chars)
|
|
yield('words', self.words)
|
|
yield('lines', self.lines)
|
|
|
|
def reducer(self, key, values):
|
|
yield(key, sum(values))
|
|
|
|
|
|
if __name__ == '__main__':
|
|
MRWordCountUtility.run()
|