alexandria-book-collection-manager 0.6.9 → 0.7.0

data/lib/alexandria/book_providers/bol_it.rb

@@ -1,5 +1,5 @@
 # Copyright (C) 2007 Marco Costantini
-# Copyright (C) 2014 Matijs van Zuijlen
+# Copyright (C) 2014, 2016 Matijs van Zuijlen
 # based on ibs_it.rb by Claudio Belotti
 #
 # Alexandria is free software; you can redistribute it and/or
@@ -25,10 +25,10 @@ require 'open-uri'
 module Alexandria
   class BookProviders
     class BOL_itProvider < GenericProvider
-      BASE_URI = 'http://www.bol.it'
+      BASE_URI = 'http://www.bol.it'.freeze
       CACHE_DIR = File.join(Alexandria::Library::DIR, '.bol_it_cache')
       REFERER = BASE_URI
-      LOCALE = 'libri' # possible locales are: "libri", "inglesi", "video", "musica", "choco"
+      LOCALE = 'libri'.freeze # possible locales are: "libri", "inglesi", "video", "musica", "choco"
       def initialize
         super('BOL_it', 'BOL (Italy)')
         FileUtils.mkdir_p(CACHE_DIR) unless File.exist?(CACHE_DIR)
@@ -37,7 +37,7 @@ module Alexandria
       end
 
       def search(criterion, type)
-        criterion = criterion.convert('ISO-8859-1', 'UTF-8')
+        criterion = criterion.encode('ISO-8859-1')
         req = BASE_URI + '/' + LOCALE + '/'
         req += case type
                when SEARCH_BY_ISBN
@@ -84,8 +84,8 @@ module Alexandria
       private
 
       def to_book(data)
-        raise NoResultsError if /Scheda libro non completa  \(TP null\)/.match(data)
-        data = data.convert('UTF-8', 'ISO-8859-1')
+        raise NoResultsError if data =~ /Scheda libro non completa  \(TP null\)/
+        data = data.encode('UTF-8')
 
         md = /<INPUT type =hidden name ="mailTitolo" value="([^"]+)/.match(data)
         raise 'No title' unless md
@@ -103,25 +103,25 @@ module Alexandria
 
         # raise unless
         md = /<INPUT type =HIDDEN name ="mailEditore" value="([^"]+)/.match(data)
-        publisher = CGI.unescape(md[1].strip) or md
+        (publisher = CGI.unescape(md[1].strip)) || md
 
         # raise unless
         md = /<INPUT type =HIDDEN name ="mailFormato" value="([^"]+)/.match(data)
-        edition = CGI.unescape(md[1].strip) or md
+        (edition = CGI.unescape(md[1].strip)) || md
 
         if (md = /#{edition}\&nbsp\;\|\&nbsp\;(\d+)\&nbsp\;\|\&nbsp\;/.match(data))
           nr_pages = CGI.unescape(md[1].strip)
         elsif (md = / (\d+) pagine \| /.match(data))
           nr_pages = CGI.unescape(md[1].strip)
         end
-        if nr_pages != '0' and !nr_pages.nil?
+        if (nr_pages != '0') && !nr_pages.nil?
           edition = nr_pages + ' p., ' + edition
         end
 
         publish_year = nil
         if (md = /<INPUT type =HIDDEN name ="mailAnnoPubbl" value="([^"]+)/.match(data))
           publish_year = CGI.unescape(md[1].strip).to_i
-          publish_year = nil if publish_year == 0
+          publish_year = nil if publish_year.zero?
         end
 
         cover_url = BASE_URI + '/bol/includes/tornaImmagine.jsp?cdSoc=BL&ean=' + isbn[0..11] + '&tipoOggetto=PIB&cdSito=BL' # use "FRB" instead of "PIB" for smaller images
@@ -133,7 +133,7 @@ module Alexandria
         end
 
         medium_cover = CACHE_DIR + '/' + cover_filename
-        if File.size(medium_cover) > 43 and File.size(medium_cover) != 2382 # 2382 is the size of the fake image "copertina non disponibile"
+        if File.size(medium_cover) > 43 && (File.size(medium_cover) != 2382) # 2382 is the size of the fake image "copertina non disponibile"
           puts medium_cover + ' has non-0 size' if $DEBUG
           return [Book.new(title, authors, isbn, publisher, publish_year, edition), medium_cover]
         end
@@ -147,7 +147,7 @@ module Alexandria
       end
 
       def clean_cache
-        # FIXME begin ... rescue ... end?
+        # FIXME: begin ... rescue ... end?
         Dir.chdir(CACHE_DIR) do
           Dir.glob('*.tmp') do |file|
             puts 'removing ' + file if $DEBUG

data/lib/alexandria/book_providers/deastore.rb

@@ -1,7 +1,7 @@
 # -*- ruby -*-
 #
 # Copyright (C) 2009 Cathal Mc Ginley
-# Copyright (C) 2011, 2014 Matijs van Zuijlen
+# Copyright (C) 2011, 2014, 2016 Matijs van Zuijlen
 #
 # Alexandria is free software; you can redistribute it and/or
 # modify it under the terms of the GNU General Public License as
@@ -31,8 +31,8 @@ module Alexandria
     class DeaStoreProvider < WebsiteBasedProvider
       include Alexandria::Logging
 
-      SITE = 'http://www.deastore.com'
-      BASE_SEARCH_URL = "#{SITE}/search/italian_books/0/%s/%s" # type/term
+      SITE = 'http://www.deastore.com'.freeze
+      BASE_SEARCH_URL = "#{SITE}/search/italian_books/0/%s/%s".freeze # type/term
 
       def initialize
         super('DeaStore', 'DeaStore (Italy)')
@@ -59,8 +59,8 @@ module Alexandria
 
       def search(criterion, type)
         begin
-          criterion = criterion.convert('ISO-8859-1', 'UTF-8') # still needed??
-        rescue GLib::ConvertError
+          criterion = criterion.encode('ISO-8859-1') # still needed??
+        rescue Encoding::UndefinedConversionError
           log.info { "Cannot search for non-ISO-8859-1 terms at DeaStore : #{criterion}" }
           raise NoResultsError
         end
@@ -87,18 +87,16 @@ module Alexandria
 
       def create_search_uri(search_type, search_term)
         # bah! very, very similar to the siciliano code! refactor out this duplication
-        search_type_code = { SEARCH_BY_ISBN => 'isbn',
-                             SEARCH_BY_TITLE => 'title',
-                             SEARCH_BY_AUTHORS => 'author',
-                             SEARCH_BY_KEYWORD => 'keywords'
-        }[search_type] or 'keywords'
+        (search_type_code = { SEARCH_BY_ISBN => 'isbn',
+                              SEARCH_BY_TITLE => 'title',
+                              SEARCH_BY_AUTHORS => 'author',
+                              SEARCH_BY_KEYWORD => 'keywords' }[search_type]) || 'keywords'
 
-        search_term_encoded = search_term
-        if search_type == SEARCH_BY_ISBN
-          search_term_encoded = Library.canonicalise_isbn(search_term) # isbn-10
-        else
-          search_term_encoded = CGI.escape(search_term)
-        end
+        search_term_encoded = if search_type == SEARCH_BY_ISBN
+                                Library.canonicalise_isbn(search_term) # isbn-10
+                              else
+                                CGI.escape(search_term)
+                              end
 
         uri = BASE_SEARCH_URL % [search_type_code, search_term_encoded]
         log.debug { uri }
@@ -142,7 +140,7 @@ module Alexandria
             title_link = (content / :a).first
             title = normalize(title_link.inner_text)
             link_to_description = title_link['href']
-            lookup_url =  "#{SITE}#{link_to_description}"
+            lookup_url = "#{SITE}#{link_to_description}"
 
             authors = []
             (content / 'a.info').each do |link|
@@ -245,17 +243,17 @@ module Alexandria
         # cover
         image_url = nil
         if cover_link
-          if cover_link =~ /^http/
-            # e.g. http://images.btol.com/ContentCafe/Jacket.aspx?\
-            # Return=1&amp;Type=M&amp;Value=9788873641803&amp;password=\
-            # CC70580&amp;userID=DEA40305
-            # seems not to work, or to be blank anyway, so set to nil
-            image_url = nil
-          elsif cover_link[0..0] != '/'
-            image_url = "#{SITE}/#{cover_link}"
-          else
-            image_url = "#{SITE}#{cover_link}"
-          end
+          image_url = if cover_link =~ /^http/
+                        # e.g. http://images.btol.com/ContentCafe/Jacket.aspx?\
+                        # Return=1&amp;Type=M&amp;Value=9788873641803&amp;password=\
+                        # CC70580&amp;userID=DEA40305
+                        # seems not to work, or to be blank anyway, so set to nil
+                        nil
+                      elsif cover_link[0..0] != '/'
+                        "#{SITE}/#{cover_link}"
+                      else
+                        "#{SITE}#{cover_link}"
+                      end
           log.debug { "Cover Image URL:: #{image_url}" }
         end
         book = Book.new(title, authors, isbn, publisher, publish_year, binding)
@@ -267,9 +265,7 @@ module Alexandria
       end
 
       def normalize(str)
-        unless str.nil?
-          str = str.squeeze(' ').strip
-        end
+        str = str.squeeze(' ').strip unless str.nil?
         str
       end
     end

data/lib/alexandria/book_providers/douban.rb

@@ -32,8 +32,8 @@ module Alexandria
     class DoubanProvider < GenericProvider
       include Alexandria::Logging
 
-      SITE = 'http://www.douban.com'
-      BASE_URL = 'http://api.douban.com/book/subjects?q=%s&max-results=5&alt=json'
+      SITE = 'http://www.douban.com'.freeze
+      BASE_URL = 'http://api.douban.com/book/subjects?q=%s&max-results=5&alt=json'.freeze
 
       def initialize
         super('Douban', 'Douban (China)')
@@ -51,9 +51,7 @@ module Alexandria
         search_response = transport.get_response(URI.parse(request_url))
 
         results = parse_search_result(search_response.body)
-        if results.length == 0
-          raise NoResultsError
-        end
+        raise NoResultsError if results.empty?
 
         if type == SEARCH_BY_ISBN
           return results.first
@@ -97,9 +95,7 @@ module Alexandria
               pubdate = nil
               binding = nil
               for av in item['db:attribute']
-                if av['@name'] == 'isbn13'
-                  isbn = av['$t']
-                end
+                isbn = av['$t'] if av['@name'] == 'isbn13'
                 if av['@name'] == 'publisher'
                   publisher = av['$t']
                 end
@@ -110,11 +106,11 @@ module Alexandria
                   binding = av['$t']
                 end
               end
-              if item['author']
-                authors = item['author'].map { |a| a['name']['$t'] }
-              else
-                authors = []
-              end
+              authors = if item['author']
+                          item['author'].map { |a| a['name']['$t'] }
+                        else
+                          []
+                        end
               image_url = nil
               for av in item['link']
                 if av['@rel'] == 'image'

data/lib/alexandria/book_providers/ibs_it.rb

@@ -1,5 +1,5 @@
 # Copyright (C) 2005-2006 Claudio Belotti
-# Copyright (C) 2014 Matijs van Zuijlen
+# Copyright (C) 2014, 2016 Matijs van Zuijlen
 #
 # Alexandria is free software; you can redistribute it and/or
 # modify it under the terms of the GNU General Public License as
@@ -24,7 +24,7 @@ require 'open-uri'
 module Alexandria
   class BookProviders
     class IBS_itProvider < GenericProvider
-      BASE_URI = 'http://www.internetbookshop.it'
+      BASE_URI = 'http://www.internetbookshop.it'.freeze
       CACHE_DIR = File.join(Alexandria::Library::DIR, '.ibs_it_cache')
       REFERER = BASE_URI
       def initialize
@@ -35,7 +35,7 @@ module Alexandria
       end
 
       def search(criterion, type)
-        criterion = criterion.convert('ISO-8859-1', 'UTF-8')
+        criterion = criterion.encode('ISO-8859-1')
         req = BASE_URI + '/ser/'
         req += case type
                when SEARCH_BY_ISBN
@@ -80,8 +80,8 @@ module Alexandria
       private
 
       def to_book(data)
-        raise NoResultsError if /<b>Il libro che hai cercato non &egrave; presente nel nostro catalogo<\/b><br>/.match(data)
-        data = data.convert('UTF-8', 'ISO-8859-1')
+        raise NoResultsError if data =~ /<b>Il libro che hai cercato non &egrave; presente nel nostro catalogo<\/b><br>/
+        data = data.encode('UTF-8')
 
         md = />Titolo<\/td><td valign="top" class="lbarrasup">([^<]+)/.match(data)
         raise 'No title' unless md
@@ -98,16 +98,16 @@ module Alexandria
 
         # raise "No publisher" unless
         md = /<b>Editore<\/b><\/td>.+<b>([^<]+)/.match(data)
-        publisher = CGI.unescape(md[1].strip) or md
+        (publisher = CGI.unescape(md[1].strip)) || md
 
         # raise "No edition" unless
         md = /Dati<\/b><\/td><td valign="top">([^<]+)/.match(data)
-        edition = CGI.unescape(md[1].strip) or md
+        (edition = CGI.unescape(md[1].strip)) || md
 
         publish_year = nil
         if (md = /Anno<\/b><\/td><td valign="top">([^<]+)/.match(data))
           publish_year = CGI.unescape(md[1].strip).to_i
-          publish_year = nil if publish_year == 0
+          publish_year = nil if publish_year.zero?
         end
 
         md = /src="http:\/\/giotto.ibs.it\/cop\/copt13.asp\?f=(\d+)">/.match(data)
@@ -120,7 +120,7 @@ module Alexandria
         end
 
         medium_cover = CACHE_DIR + '/' + cover_filename
-        if File.size(medium_cover) > 0 and File.size(medium_cover) != 1822 # 1822 is the size of the fake image "copertina non disponibile"
+        if File.size(medium_cover) > 0 && (File.size(medium_cover) != 1822) # 1822 is the size of the fake image "copertina non disponibile"
           puts medium_cover + ' has non-0 size' if $DEBUG
           return [Book.new(title, authors, isbn, publisher, publish_year, edition), medium_cover]
         end
@@ -134,7 +134,7 @@ module Alexandria
       end
 
       def clean_cache
-        # FIXME begin ... rescue ... end?
+        # FIXME: begin ... rescue ... end?
         Dir.chdir(CACHE_DIR) do
           Dir.glob('*.tmp') do |file|
             puts 'removing ' + file if $DEBUG

data/lib/alexandria/book_providers/mcu.rb

@@ -1,6 +1,6 @@
 # Copyright (C) 2004 Javier Fernandez-Sanguino
 # Copyright (C) 2007 Javier Fernandez-Sanguino and Marco Costantini
-# Copyright (C) 2011 Matijs van Zuijlen
+# Copyright (C) 2011, 2016 Matijs van Zuijlen
 #
 # Alexandria is free software; you can redistribute it and/or
 # modify it under the terms of the GNU General Public License as
@@ -32,10 +32,10 @@ module Alexandria
 
       LANGUAGES = {
         'es' => '1'
-      }
+      }.freeze
 
       #        BASE_URI = "http://www.mcu.es/cgi-bin/BRSCGI3701?"
-      BASE_URI = 'http://www.mcu.es/cgi-brs/BasesHTML/isbn/BRSCGI?'
+      BASE_URI = 'http://www.mcu.es/cgi-brs/BasesHTML/isbn/BRSCGI?'.freeze
       def initialize
         super('MCU', _('Spanish Culture Ministry'))
         # No preferences
@@ -44,12 +44,7 @@ module Alexandria
 
       def search(criterion, type)
         prefs.read
-        begin
-          criterion = criterion.convert('ISO-8859-1', 'UTF-8') # still needed??
-        rescue GLib::ConvertError
-          log.info { "Cannot search for non-ISO-8859-1 terms at MCU : #{criterion}" }
-          raise NoResultsError
-        end
+        criterion = criterion.encode('ISO-8859-1') # still needed??
         print "Doing search with MCU #{criterion}, type: #{type}\n" if $DEBUG # for DEBUGing
         req = BASE_URI + 'CMD=VERLST&BASE=ISBN&DOCS=1-15&CONF=AEISPA.cnf&OPDEF=AND&DOCS=1-1000&SEPARADOR=&'
         req += case type
@@ -71,9 +66,8 @@ module Alexandria
         products = {}
         print "Request page is #{req}\n" if $DEBUG # for DEBUGing
         transport.get(URI.parse(req)).each do |line|
-          # line = line.convert("ISO-8859-1", "UTF-8")
           print "Reading line: #{line}" if $DEBUG # for DEBUGing
-          if (line =~ /CMD=VERDOC.*&DOCN=([^&]*)&NDOC=([^&]*)/) and (!products[Regexp.last_match[1]]) and (book = parseBook(Regexp.last_match[1], Regexp.last_match[2]))
+          if (line =~ /CMD=VERDOC.*&DOCN=([^&]*)&NDOC=([^&]*)/) && (!products[Regexp.last_match[1]]) && (book = parseBook(Regexp.last_match[1], Regexp.last_match[2]))
             products[Regexp.last_match[1]] = book
             puts Regexp.last_match[1] if $DEBUG # for DEBUGing
           end
@@ -109,11 +103,11 @@ module Alexandria
           # - CDU      - Last update
 
           # There seems to be an issue with accented chars..
-          line = line.convert('UTF-8', 'ISO-8859-1')
+          line = line.encode('UTF-8')
           print "Reading line (robotstate #{robotstate}): #{line}" if $DEBUG # for DEBUGing
-          if line =~ /^<\/td>$/ or line =~ /^<\/tr>$/
+          if line =~ /^<\/td>$/ || line =~ /^<\/tr>$/
             robotstate = 0
-          elsif robotstate == 1 and line =~ /^([^<]+)</
+          elsif (robotstate == 1) && line =~ /^([^<]+)</
             author = Regexp.last_match[1].gsub('&nbsp;', ' ').sub(/ +$/, '')
             if author.length > 3
               # Only add authors of appropiate length
@@ -121,20 +115,20 @@ module Alexandria
               print "Authors are #{product['authors']}\n" if $DEBUG # for DEBUGing
               robotstate = 0
             end
-          elsif robotstate == 2 and line =~ /^(.*)$/ # The title es the next line to title declaration and has not tags on web src code
+          elsif (robotstate == 2) && line =~ /^(.*)$/ # The title es the next line to title declaration and has not tags on web src code
             product['name'] = Regexp.last_match[1].strip
             print "Name is #{product['name']}\n" if $DEBUG # for DEBUGing
             robotstate = 0
-          elsif robotstate == 3 and line =~ /^([0-9]+-[0-9]+-[0-9]+-[0-9]+-[0-9]).*/
+          elsif (robotstate == 3) && line =~ /^([0-9]+-[0-9]+-[0-9]+-[0-9]+-[0-9]).*/
             product['isbn'] = Regexp.last_match[1]
             print "ISBN is #{product['isbn']}\n" if $DEBUG # for DEBUGing
             robotstate = 0
-          elsif robotstate == 4 and line =~ /^([^<]+)</
+          elsif (robotstate == 4) && line =~ /^([^<]+)</
             product['manufacturer'] = Regexp.last_match[1].strip
             print "Manufacturer is #{product['manufacturer']}\n" if $DEBUG # for DEBUGing
             robotstate = 0
             #                elsif robotstate == 5 and line =~ /^([^<]+)</
-          elsif robotstate == 5 and line =~ /<span>([^<]+)</
+          elsif (robotstate == 5) && line =~ /<span>([^<]+)</
             product['media'] = Regexp.last_match[1].strip
             print "Media is #{product['media']}\n" if $DEBUG # for DEBUGing
             robotstate = 0

data/lib/alexandria/book_providers/proxis.rb

@@ -1,5 +1,5 @@
 # Copyright (C) 2009 Cathal Mc Ginley
-# Copyright (C) 2014,2015 Matijs van Zuijlen
+# Copyright (C) 2014-2016 Matijs van Zuijlen
 #
 # Alexandria is free software; you can redistribute it and/or
 # modify it under the terms of the GNU General Public License as
@@ -34,11 +34,11 @@ module Alexandria
       # it adds most to Alexandria (Amazon already has French and
       # English titles).
 
-      SITE = 'http://www.proxis.nl'
+      SITE = 'http://www.proxis.nl'.freeze
       BASE_SEARCH_URL = "#{SITE}/NLNL/Search/IndexGSA.aspx?search=%s" \
-        '&shop=100001NL&SelRubricLevel1Id=100001NL'
+        '&shop=100001NL&SelRubricLevel1Id=100001NL'.freeze
       ISBN_REDIRECT_BASE_URL = "#{SITE}/NLNL/Search/Index.aspx?search=%s" \
-        '&shop=100001NL&SelRubricLevel1Id=100001NL'
+        '&shop=100001NL&SelRubricLevel1Id=100001NL'.freeze
 
       def initialize
         super('Proxis', 'Proxis (Belgium)')
@@ -47,10 +47,6 @@ module Alexandria
         prefs.read
       end
 
-      ## criterion = criterion.convert("windows-1252", "UTF-8")
-      ## is the above still needed??
-      ## current pages are returned in UTF-8, so I think probably not!
-
       def search(criterion, type)
         req = create_search_uri(type, criterion)
         puts req if $DEBUG
@@ -75,12 +71,12 @@ module Alexandria
 
       def get_book_from_search_result(result)
         log.debug { "Fetching book from #{result[:lookup_url]}" }
-        html_data =  transport.get_response(URI.parse(result[:lookup_url]))
+        html_data = transport.get_response(URI.parse(result[:lookup_url]))
         parse_result_data(html_data.body)
       end
 
       def url(book)
-        if book.isbn.nil? or book.isbn.empty?
+        if book.isbn.nil? || book.isbn.empty?
           ISBN_REDIRECT_BASE_URL % Library.canonicalise_ean(book.isbn)
         end
       end
@@ -107,7 +103,7 @@ module Alexandria
       def parse_search_result_data(html)
         doc = html_to_doc(html)
         book_search_results = []
-        items = (doc.search('table.searchResult tr'))
+        items = doc.search('table.searchResult tr')
         items.each do |item|
           result = {}
           title_link = item % 'h5 a'
@@ -129,9 +125,7 @@ module Alexandria
       def data_for_header(th)
         tr = th.parent
         td = tr.at('td')
-        if td
-          text_of(td)
-        end
+        text_of(td) if td
       end
 
       def parse_result_data(html)
@@ -181,14 +175,12 @@ module Alexandria
 
         image_url = nil
         if (cover_img = doc.at("img[@id$='imgProduct']"))
-          if cover_img['src'] =~ /^http/
-            image_url = cover_img['src']
-          else
-            image_url = "#{SITE}/#{cover_img['src']}" # TODO use html <base>
-          end
-          if image_url =~ /ProductNoCover/
-            image_url = nil
-          end
+          image_url = if cover_img['src'] =~ /^http/
+                        cover_img['src']
+                      else
+                        "#{SITE}/#{cover_img['src']}" # TODO: use html <base>
+                      end
+          image_url = nil if image_url =~ /ProductNoCover/
         end
 
         book = Book.new(book_data[:title], book_data[:authors],