From 9306cb60c32082c5403931de0823a9fd5daa196c Mon Sep 17 00:00:00 2001 From: Jason Katz-Brown Date: Sun, 25 Aug 2013 02:17:13 -0700 Subject: Initial git commit. --- .../perl_tools/generate_raw_words.pl | 23 ++++++++++++++++++++++ 1 file changed, 23 insertions(+) create mode 100755 new_language_generation/perl_tools/generate_raw_words.pl (limited to 'new_language_generation/perl_tools/generate_raw_words.pl') diff --git a/new_language_generation/perl_tools/generate_raw_words.pl b/new_language_generation/perl_tools/generate_raw_words.pl new file mode 100755 index 0000000..b32d810 --- /dev/null +++ b/new_language_generation/perl_tools/generate_raw_words.pl @@ -0,0 +1,23 @@ +#!/usr/bin/perl + +# USAGE: generate_raw_words.pl generate_words_output + +binmode STDOUT, ':utf8'; + +sub read_and_spit { + for my $arg (@ARGV) { + open (my $input, "<:encoding(utf8)", $arg); + + while (<$input>) { + chomp; + my ($word, $count) = split(/\s/, $_); + + my $clean_word = $word; + $clean_word =~ s/;//g; + + print "$clean_word\n"; + } + } +} + +read_and_spit(); -- cgit v1.2.3