Generated on Tue Oct 16 11:40:48 -0400 2007 with rcov 0.8.0
Code reported as executed by Ruby looks like this... and this: this line is also marked as covered. Lines considered as run by rcov, but not reported by Ruby, look like this, and this: these lines were inferred by rcov (using simple heuristics). Finally, here's a line marked as not executed.
| Name | Total lines | Lines of code | Total coverage | Code coverage | ||||||||
| lib/alexandria/book_providers/webster_it.rb | 163 | 114 |
|
|
1 # Copyright (C) 2007 Marco Costantini 2 # based on ibs_it.rb by Claudio Belotti 3 # 4 # Alexandria is free software; you can redistribute it and/or 5 # modify it under the terms of the GNU General Public License as 6 # published by the Free Software Foundation; either version 2 of the 7 # License, or (at your option) any later version. 8 # 9 # Alexandria is distributed in the hope that it will be useful, 10 # but WITHOUT ANY WARRANTY; without even the implied warranty of 11 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU 12 # General Public License for more details. 13 # 14 # You should have received a copy of the GNU General Public 15 # License along with Alexandria; see the file COPYING. If not, 16 # write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330, 17 # Boston, MA 02111-1307, USA. 18 19 require 'fileutils' 20 require 'net/http' 21 require 'open-uri' 22 #require 'cgi' 23 24 module Alexandria 25 class BookProviders 26 class Webster_itProvider < GenericProvider 27 BASE_URI = "http://www.libreriauniversitaria.it" # also "http://www.webster.it" 28 CACHE_DIR = File.join(Alexandria::Library::DIR, '.webster_it_cache') 29 REFERER = BASE_URI 30 LOCALE = "BIT" # used only for search by title/author/keyword. possible are: "BIT", "BUS", "BUK", "BDE", "MIT" 31 def initialize 32 super("Webster_it", "Webster (Italy)") 33 FileUtils.mkdir_p(CACHE_DIR) unless File.exists?(CACHE_DIR) 34 # no preferences for the moment 35 at_exit { clean_cache } 36 end 37 38 def search(criterion, type) 39 criterion = criterion.convert("ISO-8859-15", "UTF-8") 40 req = BASE_URI + "/" 41 req += case type 42 when SEARCH_BY_ISBN 43 "isbn/" # "#{LOCALE}/" 44 45 when SEARCH_BY_TITLE 46 "c_search.php?noinput=1&shelf=#{LOCALE}&title_query=" 47 48 when SEARCH_BY_AUTHORS 49 "c_search.php?noinput=1&shelf=#{LOCALE}&author_query=" 50 51 when SEARCH_BY_KEYWORD 52 "c_search.php?noinput=1&shelf=#{LOCALE}&subject_query=" 53 54 else 55 raise InvalidSearchTypeError 56 57 end 58 59 req += CGI.escape(criterion) 60 p req if $DEBUG 61 data = transport.get(URI.parse(req)) 62 if type == SEARCH_BY_ISBN 63 to_book(data) #rescue raise NoResultsError 64 else 65 begin 66 results = [] 67 each_book_page(data) do |code, title| 68 results << to_book(transport.get(URI.parse(BASE_URI + "/#{LOCALE}/" + code))) 69 end 70 return results 71 rescue 72 raise NoResultsError 73 end 74 end 75 end 76 77 def url(book) 78 BASE_URI + "/isbn/" + book.isbn 79 end 80 81 ####### 82 private 83 ####### 84 85 def to_book(data) 86 raise NoResultsError if /<font color="\#ffffff"><b>Prodotto non esistente<\/b><\/font>/.match(data) != nil 87 data = data.convert("UTF-8", "ISO-8859-15") 88 89 raise unless md = /<li><span class="product_label">Titolo:<\/span><span class="product_text"> ([^<]+)/.match(data) 90 title = CGI.unescape(md[1].strip) 91 if md = /<span class="product_heading_volume">([^<]+)/.match(data) 92 title += " " + CGI.unescape(md[1].strip) 93 end 94 95 authors = [] 96 if md = /<li><span class="product_label">Autor[ei]:<\/span> <span class="product_text">(<a href="[^>]+">([^<]+)<\/a>,? ?)+<\/span><li>/.match(data) 97 this = CGI.unescape(md[0].strip) 98 authors = this.scan(/<a href="[^>]+">([^<]+)<\/a>,?/) 99 authors = authors.collect {|author| author[0]} 100 #puts this 101 # md[1].strip.split(', ').each { |a| authors << CGI.unescape(a.strip) } 102 end 103 104 raise unless md = /<li><span class="product_label">ISBN:<\/span> <span class="product_text">([^<]+)/.match(data) 105 isbn = Library.canonicalise_ean( md[1].strip ) 106 107 #raise unless 108 md = /<li><span class="product_label">Editore:<\/span> <span class="product_text"><a href="[^>]+>([^<]+)/.match(data) 109 publisher = CGI.unescape(md[1].strip) or md 110 111 if md = /<li><span class="product_label">Pagine:<\/span> <span class="product_text">([^<]+)/.match(data) 112 edition = CGI.unescape(md[1].strip) + " p." 113 else 114 edition = nil 115 end 116 117 publish_year = nil 118 if md = /<li><span class="product_label">Data di Pubblicazione:<\/span> <span class="product_text">([^<]+)/.match(data) 119 publish_year = CGI.unescape(md[1].strip)[-4 .. -1].to_i 120 publish_year = nil if publish_year == 0 121 end 122 123 if data =~ /javascript:popImage/ and md = /<img border="0" alt="[^"]+" src="([^"]+)/.match(data) 124 cover_url = BASE_URI + md[1].strip 125 # use "p" instead of "g" for smaller image 126 if cover_url[-5] == 103 127 cover_url[-5] = 112 128 end 129 130 cover_filename = isbn + ".tmp" 131 Dir.chdir(CACHE_DIR) do 132 File.open(cover_filename, "w") do |file| 133 file.write open(cover_url, "Referer" => REFERER ).read rescue nil 134 end 135 end 136 137 medium_cover = CACHE_DIR + "/" + cover_filename 138 if File.size(medium_cover) > 0 139 puts medium_cover + " has non-0 size" if $DEBUG 140 return [ Book.new(title, authors, isbn, publisher, publish_year, edition),medium_cover ] 141 end 142 puts medium_cover + " has 0 size, removing ..." if $DEBUG 143 File.delete(medium_cover) 144 end 145 return [ Book.new(title, authors, isbn, publisher, publish_year, edition) ] 146 end 147 148 def each_book_page(data) 149 raise if data.scan(/<tr ><td width="10%" align="center""> <a href="#{LOCALE}\/([^\/]+)/) { |a| yield a}.empty? 150 end 151 152 def clean_cache 153 #FIXME begin ... rescue ... end? 154 Dir.chdir(CACHE_DIR) do 155 Dir.glob("*.tmp") do |file| 156 puts "removing " + file if $DEBUG 157 File.delete(file) 158 end 159 end 160 end 161 end 162 end 163 end
Generated using the rcov code coverage analysis tool for Ruby version 0.8.0.