Sha256: d53d4f321e7bc6bd433db4b1ddd35e3c96e1f8b82b868e01e4d451b96d607a16
Contents?: true
Size: 1.14 KB
Versions: 16
Compression:
Stored size: 1.14 KB
Contents
# this tool creates the basic structure(s) to use a dictionary
# for input dictionary structure, please see: https://stackoverflow.com/a/18386728/4352306
require "json"
require "csv"
require "pp"
module Eco
module Lexic
class Dictionary
DICTIONARY_FILE = File.join(__dir__, 'dictionary', 'dictionary.txt')
TAGS_FILE = File.join(__dir__, 'dictionary', 'tags.json')
PARSED_DICTIONARY = File.join(__dir__, 'dictionary', 'dictionary.json')
attr_reader :tags
def initialize()
# aplhabetical list of part-of-speech tags used in the Penn Treebank Project
# reference: https://www.ling.upenn.edu/courses/Fall_2003/ling001/penn_treebank_pos.html
tags = JSON.load(File.open(TAGS_FILE, "r"))
end
def parse_dictionary(dic_file = nil)
dic_file = DICTIONARY_FILE if !dic_file
data = CSV.open(dic_file, "r", { col_sep: "\t"})
i = 0
data.each do |row|
inflected_form, base_form, tag = row
#puts "%s %s %s" % [inflected_form, base_form, tag]
i += 1
exit(1) if i>100
end
end
end
end
end
Version data entries
16 entries across 16 versions & 1 rubygems