alexandria-book-collection-manager 0.7.1 → 0.7.6

data/INSTALL.rdoc

@@ -1,148 +0,0 @@
-= Installing Alexandria
-
-Alexandria is written in Ruby with a GTK+2/GNOME user-interface. It
-currently only runs on UNIX-style systems, such as GNU/Linux.
-
-Alexandria is not an easy project to build from scratch. Apart from
-Ruby and GNOME, it has a lot of dependencies; however, many of these
-are now optional as detailed below. Once the dependencies have been
-installed, building and installing Alexandria is relatively
-straightforward.
-
-[Also note that there are pre-built packages for some distros, such as
-Fedora and Ubuntu.]
-
-== Dependencies
-
-The {Ruby-GNOME2}[http://ruby-gnome2.sourceforge.jp/] user-interface
-involves a number of packages:
-
-* <tt>ruby-gtk2</tt>
-* <tt>ruby-goocanvas</tt>
-* <tt>ruby-gst</tt>
-* <tt>ruby-pango</tt>
-
-You should have GTK+ >= 2.22.0, and use Ruby-GNOME2 >= 0.16.0.
-
-<tt>ruby-gettext</tt>[http://ponx.s5.xrea.com/hiki/ruby-gettext.html]
-is required for the internationalisation of the user interface.
-Requires version 1.7.0 or higher.
-
-=== Hpricot
-
-Alexandria uses +hpricot+[http://code.whytheluckystiff.net/hpricot] to
-parse the HTML from web pages for providers such as DeaStore and
-Siciliano. It is also used to parse the XML for the Amazon web
-service. You can install the +hpricot+ package natively or as a
-ruby gem.
-
-== HTMLEntities
-
-This is used by all website-based providers except MCU. 
- +htmlentities+[http://htmlentities.rubyforge.org/] is used to
-provide more flexible HTML parsing.
-
-== Build Dependencies
-
-=== Ruby Dependencies
-
-+rake+[http://rake.rubyforge.org] is required to build Alexandria from
-the project +Rakefile+.
-
-You also need +rubygems+[http://www.rubygems.org/] and
-+rspec+[http://rspec.rubyforge.org/] to run the RSpec test suite.
-
-=== Native Dependencies
-
-The +gettext+[http://www.gnu.org/software/gettext] package is needed
-to generate the binary +mo+ files used by <tt>ruby-gettext</tt> at
-runtime. You also need the
-+intltool+[http://www.freedesktop.org/wiki/Software/intltool] package
-to merge translations into generated files (and to extract
-translatable string from xml files during development).
-
-Note that these files are pre-generated in tar.gz releases, so you'll
-only need them if you're building from the SVN version, or want to
-change the translations.
-
-=== Ruby/ZOOM and Yaz
-
-For Z39.50 support and and the <b>Library of Congress</b> and
-<b>British Library</b> book providers you will need
-<tt>ruby-zoom</tt>[http://ruby-zoom.rubyforge.org], which in turn
-requires the non-Ruby package +yaz+[http://www.indexdata.dk/yaz].
-
-Note that if you install the recent Ruby/ZOOM as the +zoom+ gem, you
-will also need to install the +marc+ gem. (Older implementations of
-ruby-zoom contained their own implementation of MARC.)
-
-The Z39.50 Object-Orientation Model (ZOOM) is an international
-standard for communication between computer systems, particularly
-libraries and information-related systems.
-
-=== image_size
-
-You will need
-<tt>image_size</tt>[http://rubyforge.org/projects/imagesize/] for
-optimizing the cover images in exported libraries.
-
-== Build and Install
-
-To build Alexandria from a subversion checkout, go to the base project
-directory (where the Rakefile and this INSTALL file are located) and
-issue the command
-    rake build
-If you have downloaded a source package, this step will not usually be
-necessary.
-
-You must have root priveledges to install, so use +su+
-    su -c 'rake install'
-or +sudo+
-    sudo rake install
-
-Now you can check the version of the installed Alexandria
-    alexandria --version
-
-To launch Alexandria, simply use
-    alexandria
-
-If you wish to see more output on the console, you can use
-    alexandria --debug
-
-=== Staged installation for making packages
-
-When building a binary package (such as a deb or rpm) you will want to
-"install" Alexandria into a specified directory instead of the root
-filesystem. You should specify this as the DESTDIR environment variable
-and use the +install_package_staging+ task instead of +install+
-
-    DESTDIR=debian/alexandria rake install_package_staging
-
-If your distribution uses a specific directory to install Ruby
-packages, you should also set the RUBYLIBDIR.
-
-=== Installing in the home directory
-
-If you want to install Alexandria in your home directory, you should
-specify the PREFIX, SHARE and RUBYLIBDIR envrionment variables, and
-use the +install_package+ task instead of +install+.
-
-    PREFIX=$HOME SHARE=$HOME/.share RUBYLIBDIR=$HOME/.rubylib rake install_package
-
-This will install the +alexandria+ program into +$HOME/bin+ (which you
-should add to your +PATH+), and the ruby files to your
-+$HOME/.rubylib+ which you should add to your +RUBYLIBDIR+ environment
-variable.
-
-=== Uninstalling
-
-To uninstall, simply run
-
-    sudo rake uninstall
-
-(or +rake uninstall_package+ if you installed in your home directory).
-
-If you specified any of the environment variables PREFIX, SHARE,
-RUBYLIBDIR and DESTDIR during the installation, you should use the
-same variables during uninstallation (or rake won't know where to look
-for the files it has to remove).

data/dogtail/basic_run_test.py

@@ -1,9 +0,0 @@
-#!/usr/bin/env python
-
-from dogtail.tree import *
-from dogtail.utils import run
-
-run('bin/alexandria', appName = 'alexandria')
-app = root.application('alexandria')
-quit_item = app.menuItem('Quit')
-quit_item.doActionNamed('click')

data/lib/alexandria/book_providers/bol_it.rb

@@ -1,160 +0,0 @@
-# Copyright (C) 2007 Marco Costantini
-# 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
-# modify it under the terms of the GNU General Public License as
-# published by the Free Software Foundation; either version 2 of the
-# License, or (at your option) any later version.
-#
-# Alexandria 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 Alexandria; see the file COPYING.  If not,
-# write to the Free Software Foundation, Inc., 51 Franklin Street,
-# Fifth Floor, Boston, MA 02110-1301 USA.
-
-require 'fileutils'
-require 'net/http'
-require 'open-uri'
-# require 'cgi'
-
-module Alexandria
-  class BookProviders
-    class BOL_itProvider < GenericProvider
-      BASE_URI = 'http://www.bol.it'.freeze
-      CACHE_DIR = File.join(Alexandria::Library::DIR, '.bol_it_cache')
-      REFERER = BASE_URI
-      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)
-        # no preferences for the moment
-        at_exit { clean_cache }
-      end
-
-      def search(criterion, type)
-        criterion = criterion.encode('ISO-8859-1')
-        req = BASE_URI + '/' + LOCALE + '/'
-        req += case type
-               when SEARCH_BY_ISBN
-                 'scheda/'
-
-               when SEARCH_BY_TITLE
-                 'risultatoricerca?action=bolrisultatoricerca&skin=bol&filtro_ricerca=BOL&quick_type=Titolo&titolo='
-
-               when SEARCH_BY_AUTHORS
-                 'risultatoricerca?action=bolrisultatoricerca&skin=bol&filtro_ricerca=BOL&quick_type=Autore&titolo='
-
-               when SEARCH_BY_KEYWORD
-                 'risultatoricerca?action=bolrisultatoricerca&skin=bol&filtro_ricerca=BOL&quick_type=Parola%20chiave&titolo='
-
-               else
-                 raise InvalidSearchTypeError
-
-               end
-
-        ## warning: this provider uses pages like http://www.bol.it/libri/scheda/ea978888584104 with 12 numbers, without the checksum
-        criterion = 'ea' + Library.canonicalise_ean(criterion)[0..-2] + '.html' if type == SEARCH_BY_ISBN
-        req += CGI.escape(criterion)
-        p req if $DEBUG
-        data = transport.get(URI.parse(req))
-        if type == SEARCH_BY_ISBN
-          to_book(data) # rescue raise NoResultsError
-        else
-          begin
-            results = []
-            each_book_page(data) do |code, _title|
-              results << to_book(transport.get(URI.parse(BASE_URI + "/#{LOCALE}/scheda/ea" + code)))
-            end
-            return results
-          rescue
-            raise NoResultsError
-          end
-        end
-      end
-
-      def url(book)
-        BASE_URI + "/#{LOCALE}/scheda/ea" + Library.canonicalise_ean(book.isbn)[0..-2] + '.html'
-      end
-
-      private
-
-      def to_book(data)
-        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
-        title = CGI.unescape(md[1].strip)
-
-        authors = []
-        if (md = /<INPUT type =HIDDEN name ="mailAutore" value="([^"]+)/.match(data))
-          md[1].strip.split(', ').each { |a| authors << CGI.unescape(a.strip) }
-        end
-
-        md = /<INPUT type =HIDDEN name ="mailEAN" value="([^"]+)/.match(data)
-        raise 'No ISBN' unless md
-        isbn = md[1].strip
-        isbn += String(Library.ean_checksum(Library.extract_numbers(isbn)))
-
-        # raise unless
-        md = /<INPUT type =HIDDEN name ="mailEditore" value="([^"]+)/.match(data)
-        (publisher = CGI.unescape(md[1].strip)) || md
-
-        # raise unless
-        md = /<INPUT type =HIDDEN name ="mailFormato" value="([^"]+)/.match(data)
-        (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') && !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.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
-        cover_filename = isbn + '.tmp'
-        Dir.chdir(CACHE_DIR) do
-          File.open(cover_filename, 'w') do |file|
-            file.write open(cover_url, 'Referer' => REFERER).read
-          end
-        end
-
-        medium_cover = CACHE_DIR + '/' + cover_filename
-        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
-        puts medium_cover + ' has 0 size, removing ...' if $DEBUG
-        File.delete(medium_cover)
-        [Book.new(title, authors, isbn, publisher, publish_year, edition)]
-      end
-
-      def each_book_page(data)
-        raise if data.scan(/<a href="\/#{LOCALE}\/scheda\/ea(\d+)\.html;jsessionid=[^"]+">\s*Scheda completa\s*<\/a>/) { |a| yield a }.empty?
-      end
-
-      def clean_cache
-        # FIXME: begin ... rescue ... end?
-        Dir.chdir(CACHE_DIR) do
-          Dir.glob('*.tmp') do |file|
-            puts 'removing ' + file if $DEBUG
-            File.delete(file)
-          end
-        end
-      end
-    end
-  end
-end

data/lib/alexandria/book_providers/deastore.rb

@@ -1,273 +0,0 @@
-# -*- ruby -*-
-#
-# Copyright (C) 2009 Cathal Mc Ginley
-# 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
-# published by the Free Software Foundation; either version 2 of the
-# License, or (at your option) any later version.
-#
-# Alexandria 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 Alexandria; see the file COPYING.  If not,
-# write to the Free Software Foundation, Inc., 51 Franklin Street,
-# Fifth Floor, Boston, MA 02110-1301 USA.
-
-# New DeaStore provider, taken from the Palatina MetaDataSource and
-# modified to fit the structure of Alexandria book providers.
-# (24 Feb 2009)
-
-require 'cgi'
-require 'alexandria/net'
-require 'alexandria/book_providers/web'
-
-module Alexandria
-  class BookProviders
-    class DeaStoreProvider < WebsiteBasedProvider
-      include Alexandria::Logging
-
-      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)')
-        prefs.read
-        @agent = nil
-      end
-
-      def agent
-        unless @agent
-          @agent = Alexandria::WWWAgent.new
-          @agent.language = :it
-        end
-        @agent
-      end
-
-      def get_book_from_search_result(result)
-        log.debug { "Fetching book from #{result[:url]}" }
-        html_data = agent.get(result[:url])
-        # File.open("rsltflarn#{Time.now().usec()}.html", 'wb') do |f|
-        #  f.write(html_data.body)
-        # end
-        parse_result_data(html_data.body)
-      end
-
-      def search(criterion, type)
-        begin
-          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
-        html_data = agent.get(create_search_uri(type, criterion))
-        # File.open("flarn#{Time.now().usec()}.html", 'wb') do |f|
-        #  f.write(html_data.body)
-        # end
-        results = parse_search_result_data(html_data.body)
-        raise NoResultsError if results.empty?
-
-        if type == SEARCH_BY_ISBN
-          get_book_from_search_result(results.first)
-        else
-          results.map { |result| get_book_from_search_result(result) }
-        end
-      end
-
-      # it isn't possible to create a URL for a book given only the ISBN...
-      def url(_book)
-        nil
-      end
-
-      private
-
-      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]) || 'keywords'
-
-        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 }
-        uri
-      end
-
-      def parse_search_result_data(html)
-        doc = html_to_doc(html)
-        book_search_results = []
-
-        result_divs = doc.search('div.scheda_prodotto')
-        result_divs.each do |div|
-          begin
-            # The layout...
-            # a > img
-            # div.scheda_content
-            #  a[link->productpage] title ##  a.titolo_link
-            #  p (genre I think) ##  !ignore
-            #  a[link->author] author ## a.info
-            #  p.editore (publisher? editor?)
-            #  p Data di pubblicazione: \n     2009
-            #  p.prezzo (price)
-
-            #             cover_url = ''
-            #             cover_images = div/'a/img'
-            #             unless cover_images.empty?
-            #               img = cover_images.first
-            #               image_url = img['src']
-            #               if image_url =~ /^http/
-            #                 cover_url = '' # image_url
-            #               elsif image_url[0..0] != '/'
-            #                 cover_url = "#{SITE}/#{image_url}"
-            #               else
-            #                 cover_url = "#{SITE}#{image_url}"
-            #               end
-            #               log.debug { "Search Cover Image URL #{cover_url}" }
-
-            #             end
-
-            content = div / 'div.scheda_content'
-            title_link = (content / :a).first
-            title = normalize(title_link.inner_text)
-            link_to_description = title_link['href']
-            lookup_url = "#{SITE}#{link_to_description}"
-
-            authors = []
-            (content / 'a.info').each do |link|
-              authors << normalize(link.inner_text)
-            end
-
-            result = {}
-            result[:author] = authors.first # HACK, what about multiple authors
-            result[:title] = title
-            result[:url] = lookup_url
-
-            publishers = (content / 'p.editore')
-            unless publishers.empty?
-              result[:publisher] = normalize(publishers.first.inner_text)
-            end
-
-            book_search_results << result
-          rescue => ex
-            trace = ex.backtrace.join("\n> ")
-            log.error { "Failed parsing DeaStore search page #{ex.message}\n#{trace}" }
-          end
-        end
-        book_search_results
-      end
-
-      def parse_result_data(html)
-        doc = html_to_doc(html)
-        data = doc % 'div#dati_scheda'
-        # sotto_data_hdr = doc % 'div.sotto_schede/h1.titolo_sotto[text()*="Informazioni generali"]/..'
-        # title
-        title_span = data % 'h1.titolo_scheda'
-        title = normalize(title_span.inner_text)
-        # cover
-        cover_link = nil
-        cover_img = data / 'a/img'
-        unless cover_img.empty?
-          cover_link = cover_img.first['src']
-        end
-        # author(s)
-        authors = []
-        author_span = data % 'span.int_scheda[text()*=Autore]'
-        unless author_span
-          author_span = data % 'span.int_scheda[text()*=cura]' # editor
-        end
-        if author_span
-          author_links = author_span / 'a.info'
-          authors = []
-          author_links.each do |link|
-            authors << normalize(link.inner_html)
-          end
-        end
-        # if author_span
-        #  author_links = author_span/'a.info'
-        #  author_links.each do |link|
-        #    authors << normalize(link.inner_text)
-        #  end
-        # end
-        # publisher
-        publisher_par = data % 'span.int_scheda[text()*=Editore]/..'
-        publisher_link = publisher_par % 'a.info'
-        publisher = normalize(publisher_link.inner_text)
-        # skip 'Collana', (ummm, possibly genre information, Babelfish
-        # says "Necklace")
-        # format
-        format_par = data % 'span.int_scheda[text()*=Formato]/..'
-        format_par.inner_text =~ /:[\s]*(.+)[\s]*$/
-        binding = normalize(Regexp.last_match[1])
-        # year
-        date_par = data % 'span.int_scheda[text()*=Data di pubblicazione]/..'
-        date_par.inner_text =~ /:[\s]*([12][0-9]{3})[\s]*$/
-        publish_year = nil
-        if Regexp.last_match[1]
-          publish_year = Regexp.last_match[1].to_i
-        end
-        isbn_spans = data / 'div.sotto/span.isbn'
-        isbns = []
-        isbn_spans.each do |span|
-          span.inner_text =~ /:[\s]*(.+)[\s]*$/
-          isbns << Regexp.last_match[1]
-        end
-        isbn = nil
-        unless isbns.empty?
-          isbn = Library.canonicalise_isbn(isbns.first)
-        end
-        # Editore & Imprint : as publisher info above...
-        # pages
-        # page_par = data % 'span.int_scheda[text()*=Pagine]/..'
-        # if page_par
-        #  page_par.inner_text =~ /:[\s]*([0-9]+)[\s]*$/
-        #  pages = $1.to_i
-        # end
-        # synopsis_div = doc % 'div.sotto_schede' # exclude the first span though
-        # book = Book.new(title, isbns.first, authors)
-        # if publisher
-        #  book.publisher = Publisher.new(publisher)
-        # end
-        # if format
-        #  book.binding = CoverBinding.new(format, binding_type(format))
-        # end
-        # cover
-        image_url = nil
-        if cover_link
-          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)
-        return [book, image_url]
-      rescue => ex
-        trace = ex.backtrace.join("\n> ")
-        log.error { "Failed parsing DeaStore product page #{ex.message}\n#{trace}" }
-        return nil
-      end
-
-      def normalize(str)
-        str = str.squeeze(' ').strip unless str.nil?
-        str
-      end
-    end
-  end
-end