uhferret-gem/bin/uhferret

#! /usr/bin/env ruby

# This file is part of uhferret, providing a command-line interface.
#
# Author::    Peter Lane
# Copyright:: Copyright 2012-20, Peter Lane.
# License::   GPLv3
#
# uhferret is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# uhferret is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with uhferret.  If not, see <http://www.gnu.org/licenses/>.

require "optparse"
require "uhferret"

MAX_TABLE_SIZE = 100
VERSION = "1.3.7"

# ------------------------------------------------------------------
# 
document_type = UHFerret::TextDocument
input_format = :from_argv
output_format = :similarity_table
definitions_file = nil
output_full_path = false
xml_output_file = ""

options = OptionParser.new do |opts|
  opts.banner = "Usage: uhferret [options] file1 file2 ..."
  opts.on("-h", "--help", "help message") do |v|
    puts options
    exit!
  end
  opts.on("-v", "--version", "version") do |v|
    puts "uhferret: version #{VERSION}"
    exit!
  end
  # -- document type
  opts.on("-c", "--code", "process documents as code") do |v| 
    document_type = UHFerret::CodeDocument
  end
  opts.on("-t", "--text", "process documents as text (default)") do |v| 
    document_type = UHFerret::TextDocument
  end
  # -- output format
  opts.on("-p", "--full-path", "output full path") do |v|
    output_full_path = true
  end
  opts.on("-d", "--data-table", "output similarity table (default)") do |v|
    output_format = :similarity_table
  end
  opts.on("-w", "--html-data-table", "output similarity table in html format") do |v|
    output_format = :html_similarity_table
  end
  opts.on("-l", "--list-trigrams", "output trigram list") do |v|
    output_format = :trigram_list
  end
  opts.on("-a", "--all-comparisons", "output list of all comparisons") do |v|
    output_format = :all_comparisons
  end
  opts.on("-x", "--xml-report OUTPUT_FILE", "generate xml report from two documents") do |file|
    output_format = :xml_output
    xml_output_file = file
  end
  # -- file source
  opts.on("-f FILE", "--definition-file FILE", "read document names from file") do |file|
    input_format = :from_file
    definitions_file = file
  end
end

begin
  # -- process input options
  options.parse!

  # -- check some errors
  if output_format == :xml_output
    unless ARGV.size == 2
      puts "Error: for xml report, only provide two input filenames"
      raise ArgumentError.new
    end
  end

  # -- add readable files, and run
  ferret = UHFerret::Ferret.new
  unless definitions_file.nil?
    if File.readable? definitions_file
      ferret.add_list_from_file(definitions_file, document_type)
    end
  end
  ARGV.each do |filename|
    if File.readable? filename
      ferret.add(filename, document_type)
    end
  end
  if ferret.size < 2
    puts "Error: not enough valid filenames"
    raise ArgumentError.new
  end
  ferret.run

  # -- display output
  case output_format
  when :similarity_table
    ferret.output_similarity_table output_full_path
  when :html_similarity_table
    ferret.output_html_similarity_table
  when :trigram_list
    ferret.output_trigram_list
  when :all_comparisons
    ferret.output_all_comparisons
  when :xml_output
    ferret.xml_output(xml_output_file, 0, 1)
  end

rescue Exception => err
  puts err
  puts options
end