46aa7e6c |
import sys
import collections
data = []
collect = []
for line in sys.stdin:
if '\xc2\xb7' in line:
if collect:
data.append(collect)
collect = []
else:
line = line.strip()
if line: collect.append(line)
commentors = collections.defaultdict(int)
for chunk in data:
line = chunk[0].split()
name_end = 1
while name_end < len(line) and (line[name_end].endswith('.') or len(line[name_end]) < 4):
name_end += 1
name = line[:name_end+1]
if len(name) > 2 and name[1] == 'HF': name = name[:2]
commentors[' '.join(name)] += 1
for x,y in commentors.iteritems():
print "%s\t%s" % (x,y)
|