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/worldcat.rb | 165 | 106 |
|
|
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 # http://en.wikipedia.org/wiki/WorldCat 20 # See http://www.oclc.org/worldcat/policies/terms/ 21 22 require 'fileutils' 23 require 'net/http' 24 require 'open-uri' 25 #require 'cgi' 26 27 module Alexandria 28 class BookProviders 29 class WorldcatProvider < GenericProvider 30 BASE_URI = "http://worldcat.org" 31 CACHE_DIR = File.join(Alexandria::Library::DIR, '.worldcat_cache') 32 REFERER = BASE_URI 33 def initialize 34 super("Worldcat", "Worldcat") 35 FileUtils.mkdir_p(CACHE_DIR) unless File.exists?(CACHE_DIR) 36 # no preferences for the moment 37 at_exit { clean_cache } 38 end 39 40 def search(criterion, type) 41 req = BASE_URI + "/" 42 req += case type 43 when SEARCH_BY_ISBN 44 "isbn/" 45 46 when SEARCH_BY_TITLE 47 "search?q=ti%3A" 48 49 when SEARCH_BY_AUTHORS 50 "search?q=au%3A" 51 52 when SEARCH_BY_KEYWORD 53 "search?q=" 54 55 else 56 raise InvalidSearchTypeError 57 58 end 59 60 req += CGI.escape(criterion) 61 p req if $DEBUG 62 data = transport.get(URI.parse(req)) 63 if type == SEARCH_BY_ISBN 64 to_book(data) #rescue raise NoResultsError 65 else 66 begin 67 results = [] 68 each_book_page(data) do |code, title| 69 results << to_book(transport.get(URI.parse(BASE_URI + "/oclc/" + code))) 70 end 71 return results 72 rescue 73 raise NoResultsError 74 end 75 end 76 end 77 78 def url(book) 79 BASE_URI + "/isbn/" + book.isbn 80 end 81 82 ####### 83 private 84 ####### 85 86 def to_book(data) 87 raise NoResultsError if /<br><p>The page you tried was not found\./.match(data) != nil 88 89 raise unless md = /<h1 class="item-title"> ?(<div class=vernacular lang="[^"]+">)?([^<]+)/.match(data) 90 title = CGI.unescape(md[2].strip) 91 92 authors = [] 93 md = data.scan(/title="Search for more by this author">([^<]+)/) 94 # raise "No authors" unless md.length > 0 95 md = md.collect {|match| match[0]} 96 md.each {|match| 97 CGI.unescape(match.strip) 98 authors << match 99 } 100 # md[1].strip.split(', ').each { |a| authors << CGI.unescape(a.strip) } 101 102 # FIXME: The provider returns the first ISBN found. When searching by 103 # ISBN, it should instead return the ISBN searched 104 # Example: http://worldcat.org/isbn/9780805335576 105 106 if md = /<strong>ISBN: <\/strong>\w+\W+(\d+)\D/.match(data) 107 isbn = md[1].strip 108 else 109 isbn = nil 110 end 111 112 # The provider returns 113 # City : Publisher[ ; City2 : Publisher2], *year? [©year] 114 # currently the match is not good in case of City2 : Publisher2 and in case of ©year 115 116 # FIXME: if the field 'Publisher' contains "| Other Editions ..." (as for 9788441000469), then this regexp doesn't match; 117 # if not (as for 9785941454136), it is OK. 118 if md = /<div class="item-publisher"><strong>Publisher: <\/strong>(<span class=vernacular lang="[^<]+<\/span>)?[^:<]+ : ([^<]+), [^,<]*(\d\d\d\d).?<\/div>/.match(data) 119 publisher = CGI.unescape(md[2].strip) 120 publish_year = CGI.unescape(md[3].strip)[-4 .. -1].to_i 121 publish_year = nil if publish_year == 0 122 else 123 publisher = nil 124 publish_year = nil 125 end 126 127 edition = nil 128 129 130 if md = /<td class="illustration"><img src="([^"]+)/.match(data) 131 cover_url = BASE_URI + md[1].strip 132 cover_filename = isbn + ".tmp" 133 Dir.chdir(CACHE_DIR) do 134 File.open(cover_filename, "w") do |file| 135 file.write open(cover_url, "Referer" => REFERER ).read 136 end 137 end 138 139 medium_cover = CACHE_DIR + "/" + cover_filename 140 if File.size(medium_cover) > 0 141 puts medium_cover + " has non-0 size" if $DEBUG 142 return [ Book.new(title, authors, isbn, publisher, publish_year, edition),medium_cover ] 143 end 144 puts medium_cover + " has 0 size, removing ..." if $DEBUG 145 File.delete(medium_cover) 146 end 147 return [ Book.new(title, authors, isbn, publisher, publish_year, edition) ] 148 end 149 150 def each_book_page(data) 151 raise if data.scan(/<div class="name"><a href="\/oclc\/(\d+)&/) { |a| yield a}.empty? 152 end 153 154 def clean_cache 155 #FIXME begin ... rescue ... end? 156 Dir.chdir(CACHE_DIR) do 157 Dir.glob("*.tmp") do |file| 158 puts "removing " + file if $DEBUG 159 File.delete(file) 160 end 161 end 162 end 163 end 164 end 165 end
Generated using the rcov code coverage analysis tool for Ruby version 0.8.0.