# No.44 Perl Sample (code key - 65)
# Learning Perl: Place each sentence in one line 2（センテンスを1行毎に並べる）
# Tomonori Nagano <tnagano@gc.cuny.edu>
# Last Update: January 18, 2008
#
# This file is encoded in Unicode (UTF-8). If you see gibberish characters, 
# please re-encode the file in utf-8. 
# 

# modified version of Prof. Martin Chodorow's script
#

my $abbr ="(Mr|Mrs|Dr|U.S)";		# add more abbreviations 

while (<>){
	chomp;
	$text .= "$_ ";		#concatenate all the text
}

# if punctuation (.!?:) is followed by capital+small letters sequence, put an
# end-of-line character
$text =~ s/(^|[\.!\?\:])\s+([A-Z][a-z]|[A-Z]\s|$)/\1\n\2/g;

# remove an end-of-line character if a sentence ends with abbreviation
$text =~ s/(\b$abbr\.)\n/\1 /g;

print "$text\n";