nhkore 0.3.7 → 0.3.11

data/lib/nhkore/sifter.rb

@@ -1,23 +1,11 @@
-#!/usr/bin/env ruby
 # encoding: UTF-8
 # frozen_string_literal: true
 
 #--
 # This file is part of NHKore.
-# Copyright (c) 2020 Jonathan Bradley Whited (@esotericpig)
-# 
-# NHKore is free software: you can redistribute it and/or modify
-# it under the terms of the GNU Lesser General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-# 
-# NHKore 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 Lesser General Public License for more details.
-# 
-# You should have received a copy of the GNU Lesser General Public License
-# along with NHKore.  If not, see <https://www.gnu.org/licenses/>.
+# Copyright (c) 2020-2021 Jonathan Bradley Whited
+#
+# SPDX-License-Identifier: LGPL-3.0-or-later
 #++
 
 
@@ -28,179 +16,179 @@ require 'nhkore/util'
 
 module NHKore
   ###
-  # @author Jonathan Bradley Whited (@esotericpig)
+  # @author Jonathan Bradley Whited
   # @since  0.2.0
   ###
   class Sifter
     include Fileable
-    
+
     DEFAULT_DIR = Util::CORE_DIR
-    
+
     DEFAULT_FUTSUU_FILENAME = 'sift_nhk_news_web_regular'
     DEFAULT_YASASHII_FILENAME = 'sift_nhk_news_web_easy'
-    
+
     def self.build_file(filename)
       return File.join(DEFAULT_DIR,filename)
     end
-    
+
     DEFAULT_FUTSUU_FILE = build_file(DEFAULT_FUTSUU_FILENAME)
     DEFAULT_YASASHII_FILE = build_file(DEFAULT_YASASHII_FILENAME)
-    
+
     attr_accessor :articles
     attr_accessor :caption
     attr_accessor :filters
     attr_accessor :ignores
     attr_accessor :output
-    
+
     def initialize(news)
-      @articles = news.articles.values.dup()
+      @articles = news.articles.values.dup
       @caption = nil
       @filters = {}
       @ignores = {}
       @output = nil
     end
-    
-    def build_header()
+
+    def build_header
       header = []
-      
+
       header << 'Frequency' unless @ignores[:freq]
       header << 'Word' unless @ignores[:word]
       header << 'Kana' unless @ignores[:kana]
       header << 'English' unless @ignores[:eng]
       header << 'Definition' unless @ignores[:defn]
-      
+
       return header
     end
-    
+
     def build_rows(words)
       rows = []
-      
-      words.each() do |word|
+
+      words.each do |word|
         rows << build_word_row(word)
       end
-      
+
       return rows
     end
-    
+
     def build_word_row(word)
       row = []
-      
+
       row << word.freq unless @ignores[:freq]
       row << word.word unless @ignores[:word]
       row << word.kana unless @ignores[:kana]
       row << word.eng unless @ignores[:eng]
       row << word.defn unless @ignores[:defn]
-      
+
       return row
     end
-    
+
     def filter?(article)
-      return false if @filters.empty?()
-      
+      return false if @filters.empty?
+
       datetime_filter = @filters[:datetime]
       title_filter = @filters[:title]
       url_filter = @filters[:url]
-      
-      if !datetime_filter.nil?()
+
+      if !datetime_filter.nil?
         datetime = article.datetime
-        
-        return true if datetime.nil?() ||
+
+        return true if datetime.nil? ||
           datetime < datetime_filter[:from] || datetime > datetime_filter[:to]
       end
-      
-      if !title_filter.nil?()
-        title = article.title.to_s()
+
+      if !title_filter.nil?
+        title = article.title.to_s
         title = Util.unspace_web_str(title) if title_filter[:unspace]
-        title = title.downcase() if title_filter[:uncase]
-        
+        title = title.downcase if title_filter[:uncase]
+
         return true unless title.include?(title_filter[:filter])
       end
-      
-      if !url_filter.nil?()
-        url = article.url.to_s()
+
+      if !url_filter.nil?
+        url = article.url.to_s
         url = Util.unspace_web_str(url) if url_filter[:unspace]
-        url = url.downcase() if url_filter[:uncase]
-        
+        url = url.downcase if url_filter[:uncase]
+
         return true unless url.include?(url_filter[:filter])
       end
-      
+
       return false
     end
-    
+
     def filter_by_datetime(datetime_filter=nil,from: nil,to: nil)
-      if !datetime_filter.nil?()
-        if datetime_filter.respond_to?(:'[]')
+      if !datetime_filter.nil?
+        if datetime_filter.respond_to?(:[])
           # If out-of-bounds, just nil.
-          from = datetime_filter[0] if from.nil?()
-          to = datetime_filter[1] if to.nil?()
+          from = datetime_filter[0] if from.nil?
+          to = datetime_filter[1] if to.nil?
         else
-          from = datetime_filter if from.nil?()
-          to = datetime_filter if to.nil?()
+          from = datetime_filter if from.nil?
+          to = datetime_filter if to.nil?
         end
       end
-      
-      from = to if from.nil?()
-      to = from if to.nil?()
-      
-      from = Util.jst_time(from) unless from.nil?()
-      to = Util.jst_time(to) unless to.nil?()
-      
+
+      from = to if from.nil?
+      to = from if to.nil?
+
+      from = Util.jst_time(from) unless from.nil?
+      to = Util.jst_time(to) unless to.nil?
+
       datetime_filter = [from,to]
-      
-      return self if datetime_filter.flatten().compact().empty?()
-      
+
+      return self if datetime_filter.flatten.compact.empty?
+
       @filters[:datetime] = {from: from,to: to}
-      
+
       return self
     end
-    
+
     def filter_by_title(title_filter,uncase: true,unspace: true)
       title_filter = Util.unspace_web_str(title_filter) if unspace
-      title_filter = title_filter.downcase() if uncase
-      
+      title_filter = title_filter.downcase if uncase
+
       @filters[:title] = {filter: title_filter,uncase: uncase,unspace: unspace}
-      
+
       return self
     end
-    
+
     def filter_by_url(url_filter,uncase: true,unspace: true)
       url_filter = Util.unspace_web_str(url_filter) if unspace
-      url_filter = url_filter.downcase() if uncase
-      
+      url_filter = url_filter.downcase if uncase
+
       @filters[:url] = {filter: url_filter,uncase: uncase,unspace: unspace}
-      
+
       return self
     end
-    
+
     def ignore(key)
       @ignores[key] = true
-      
+
       return self
     end
-    
+
     # This does not output {caption}.
-    def put_csv!()
+    def put_csv!
       require 'csv'
-      
-      words = sift()
-      
+
+      words = sift
+
       @output = CSV.generate(headers: :first_row,write_headers: true) do |csv|
-        csv << build_header()
-        
-        words.each() do |word|
+        csv << build_header
+
+        words.each do |word|
           csv << build_word_row(word)
         end
       end
-      
+
       return @output
     end
-    
-    def put_html!()
-      words = sift()
-      
-      @output = ''.dup()
-      
-      @output << <<~EOH
+
+    def put_html!
+      words = sift
+
+      @output = ''.dup
+
+      @output << <<~HTML
         <!DOCTYPE html>
         <html lang="ja">
         <head>
@@ -249,146 +237,144 @@ module NHKore
         <h1>NHKore</h1>
         <h2>#{@caption}</h2>
         <table>
-      EOH
-      #"
-      
+      HTML
+
       # If have too few or too many '<col>', invalid HTML.
-      @output << %Q{<col style="width:6em;">\n} unless @ignores[:freq]
-      @output << %Q{<col style="width:17em;">\n} unless @ignores[:word]
-      @output << %Q{<col style="width:17em;">\n} unless @ignores[:kana]
-      @output << %Q{<col style="width:5em;">\n} unless @ignores[:eng]
+      @output << %Q(<col style="width:6em;">\n) unless @ignores[:freq]
+      @output << %Q(<col style="width:17em;">\n) unless @ignores[:word]
+      @output << %Q(<col style="width:17em;">\n) unless @ignores[:kana]
+      @output << %Q(<col style="width:5em;">\n) unless @ignores[:eng]
       @output << "<col>\n" unless @ignores[:defn] # No width for defn, fills rest of page
-      
+
       @output << '<tr>'
-      
-      build_header().each() do |h|
+
+      build_header.each do |h|
         @output << "<th>#{h}</th>"
       end
-      
+
       @output << "</tr>\n"
-      
-      words.each() do |word|
+
+      words.each do |word|
         @output << '<tr>'
-        
-        build_word_row(word).each() do |w|
-          @output << "<td>#{Util.escape_html(w.to_s())}</td>"
+
+        build_word_row(word).each do |w|
+          @output << "<td>#{Util.escape_html(w.to_s)}</td>"
         end
-        
+
         @output << "</tr>\n"
       end
-      
-      @output << <<~EOH
+
+      @output << <<~HTML
         </table>
         </body>
         </html>
-      EOH
-      #/
-      
+      HTML
+
       return @output
     end
-    
-    def put_json!()
+
+    def put_json!
       require 'json'
-      
-      words = sift()
-      
-      @output = ''.dup()
-      
-      @output << <<~EOJ
+
+      words = sift
+
+      @output = ''.dup
+
+      @output << <<~JSON
         {
         "caption": #{JSON.generate(@caption)},
-        "header": #{JSON.generate(build_header())},
+        "header": #{JSON.generate(build_header)},
         "words": [
-      EOJ
-      
-      if !words.empty?()
+      JSON
+
+      if !words.empty?
         0.upto(words.length - 2) do |i|
           @output << "  #{JSON.generate(build_word_row(words[i]))},\n"
         end
-        
+
         @output << "  #{JSON.generate(build_word_row(words[-1]))}\n"
       end
-      
+
       @output << "]\n}\n"
-      
+
       return @output
     end
-    
-    def put_yaml!()
+
+    def put_yaml!
       require 'psychgus'
-      
-      words = sift()
-      
+
+      words = sift
+
       yaml = {
         caption: @caption,
-        header: build_header(),
+        header: build_header,
         words: build_rows(words),
       }
-      
-      header_styler = Class.new() do
+
+      header_styler = Class.new do
         include Psychgus::Styler
-        
+
         def style_sequence(sniffer,node)
           parent = sniffer.parent
-          
-          if !parent.nil?() && parent.node.respond_to?(:value) && parent.value == 'header'
+
+          if !parent.nil? && parent.node.respond_to?(:value) && parent.value == 'header'
             node.style = Psychgus::SEQUENCE_FLOW
           end
         end
       end
-      
+
       # Put each Word on one line (flow/inline style).
-      @output = Util.dump_yaml(yaml,flow_level: 4,stylers: header_styler.new())
-      
+      @output = Util.dump_yaml(yaml,flow_level: 4,stylers: header_styler.new)
+
       return @output
     end
-    
-    def sift()
-      master_article = Article.new()
-      
-      @articles.each() do |article|
+
+    def sift
+      master_article = Article.new
+
+      @articles.each do |article|
         next if filter?(article)
-        
-        article.words.values().each() do |word|
+
+        article.words.each_value do |word|
           master_article.add_word(word,use_freq: true)
         end
       end
-      
-      words = master_article.words.values()
-      
-      words.sort!() do |word1,word2|
+
+      words = master_article.words.values
+
+      words.sort! do |word1,word2|
         # Order by freq DESC (most frequent words to top).
         i = (word2.freq <=> word1.freq)
-        
+
         # Order by !defn.empty, word ASC, !kana.empty, kana ASC, defn.len DESC, defn ASC.
         i = compare_empty_str(word1.defn,word2.defn) if i == 0 # Favor words that have definitions
-        i = (word1.word.to_s() <=> word2.word.to_s()) if i == 0
+        i = (word1.word.to_s <=> word2.word.to_s) if i == 0
         i = compare_empty_str(word1.kana,word2.kana) if i == 0 # Favor words that have kana
-        i = (word1.kana.to_s() <=> word2.kana.to_s()) if i == 0
-        i = (word2.defn.to_s().length <=> word1.defn.to_s().length) if i == 0 # Favor longer definitions
-        i = (word1.defn.to_s() <=> word2.defn.to_s()) if i == 0
-        
+        i = (word1.kana.to_s <=> word2.kana.to_s) if i == 0
+        i = (word2.defn.to_s.length <=> word1.defn.to_s.length) if i == 0 # Favor longer definitions
+        i = (word1.defn.to_s <=> word2.defn.to_s) if i == 0
+
         i
       end
-      
+
       return words
     end
-    
+
     def compare_empty_str(str1,str2)
       has_str1 = !Util.empty_web_str?(str1)
       has_str2 = !Util.empty_web_str?(str2)
-      
+
       if has_str1 && !has_str2
         return -1 # Bubble word1 to top
       elsif !has_str1 && has_str2
         return 1 # Bubble word2 to top
       end
-      
+
       return 0 # Further comparison needed
     end
-    
-    def to_s()
-      return @output.to_s()
+
+    def to_s
+      return @output.to_s
     end
   end
 end

data/lib/nhkore/splitter.rb

@@ -1,23 +1,11 @@
-#!/usr/bin/env ruby
 # encoding: UTF-8
 # frozen_string_literal: true
 
 #--
 # This file is part of NHKore.
-# Copyright (c) 2020 Jonathan Bradley Whited (@esotericpig)
-# 
-# NHKore is free software: you can redistribute it and/or modify
-# it under the terms of the GNU Lesser General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-# 
-# NHKore 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 Lesser General Public License for more details.
-# 
-# You should have received a copy of the GNU Lesser General Public License
-# along with NHKore.  If not, see <https://www.gnu.org/licenses/>.
+# Copyright (c) 2020-2021 Jonathan Bradley Whited
+#
+# SPDX-License-Identifier: LGPL-3.0-or-later
 #++
 
 
@@ -26,24 +14,24 @@ require 'nhkore/util'
 
 module NHKore
   ###
-  # @author Jonathan Bradley Whited (@esotericpig)
+  # @author Jonathan Bradley Whited
   # @since  0.2.0
   ###
   class Splitter
     def begin_split(str)
       return str
     end
-    
+
     def split(str)
       str = begin_split(str)
       str = end_split(str)
-      
+
       return str
     end
   end
-  
+
   ###
-  # @author Jonathan Bradley Whited (@esotericpig)
+  # @author Jonathan Bradley Whited
   # @since  0.2.0
   ###
   class BasicSplitter < Splitter
@@ -51,43 +39,43 @@ module NHKore
       return str.split(Util::NORMALIZE_STR_REGEX)
     end
   end
-  
+
   ###
   # @since  0.2.0
   ###
   class BimyouSplitter < Splitter
     def initialize(*)
       require 'bimyou_segmenter'
-      
+
       super
     end
-    
+
     def end_split(str)
       return BimyouSegmenter.segment(str,symbol: false,white_space: false)
     end
   end
-  
+
   ###
   # @since  0.2.0
   ###
   class TinySplitter < Splitter
     attr_accessor :tiny
-    
+
     def initialize(*)
       require 'tiny_segmenter'
-      
+
       super
-      
-      @tiny = TinySegmenter.new()
+
+      @tiny = TinySegmenter.new
     end
-    
+
     def end_split(str)
       return @tiny.segment(str,ignore_punctuation: true)
     end
   end
-  
+
   ###
-  # @author Jonathan Bradley Whited (@esotericpig)
+  # @author Jonathan Bradley Whited
   # @since  0.2.0
   ###
   class BestSplitter < BimyouSplitter