<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN"
"http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">
<html xmlns="http://www.w3.org/1999/xhtml">
<head><meta http-equiv="content-type" content="text/html; charset=utf-8" /><style type="text/css"><!--
#msg dl { border: 1px #006 solid; background: #369; padding: 6px; color: #fff; }
#msg dt { float: left; width: 6em; font-weight: bold; }
#msg dt:after { content:':';}
#msg dl, #msg dt, #msg ul, #msg li, #header, #footer { font-family: verdana,arial,helvetica,sans-serif; font-size: 10pt; }
#msg dl a { font-weight: bold}
#msg dl a:link { color:#fc3; }
#msg dl a:active { color:#ff0; }
#msg dl a:visited { color:#cc6; }
h3 { font-family: verdana,arial,helvetica,sans-serif; font-size: 10pt; font-weight: bold; }
#msg pre { overflow: auto; background: #ffc; border: 1px #fc0 solid; padding: 6px; }
#msg ul, pre { overflow: auto; }
#header, #footer { color: #fff; background: #636; border: 1px #300 solid; padding: 6px; }
#patch { width: 100%; }
#patch h4 {font-family: verdana,arial,helvetica,sans-serif;font-size:10pt;padding:8px;background:#369;color:#fff;margin:0;}
#patch .propset h4, #patch .binary h4 {margin:0;}
#patch pre {padding:0;line-height:1.2em;margin:0;}
#patch .diff {width:100%;background:#eee;padding: 0 0 10px 0;overflow:auto;}
#patch .propset .diff, #patch .binary .diff {padding:10px 0;}
#patch span {display:block;padding:0 10px;}
#patch .modfile, #patch .addfile, #patch .delfile, #patch .propset, #patch .binary, #patch .copfile {border:1px solid #ccc;margin:10px 0;}
#patch ins {background:#dfd;text-decoration:none;display:block;padding:0 10px;}
#patch del {background:#fdd;text-decoration:none;display:block;padding:0 10px;}
#patch .lines, .info {color:#888;background:#fff;}
--></style>
<title>[617] trunk/alexandria: - repaired mcu.rb</title>
</head>
<body>
<div id="msg">
<dl>
<dt>Revision</dt> <dd>617</dd>
<dt>Author</dt> <dd>laurusnobilis</dd>
<dt>Date</dt> <dd>2007-02-23 16:56:39 -0500 (Fri, 23 Feb 2007)</dd>
</dl>
<h3>Log Message</h3>
<pre>- repaired mcu.rb
- now all the providers (except proxis) return EAN
- minor changes</pre>
<h3>Modified Paths</h3>
<ul>
<li><a href="#trunkalexandrialibalexandriabook_providersadlibrisrb">trunk/alexandria/lib/alexandria/book_providers/adlibris.rb</a></li>
<li><a href="#trunkalexandrialibalexandriabook_providersamazonrb">trunk/alexandria/lib/alexandria/book_providers/amazon.rb</a></li>
<li><a href="#trunkalexandrialibalexandriabook_providersbol_itrb">trunk/alexandria/lib/alexandria/book_providers/bol_it.rb</a></li>
<li><a href="#trunkalexandrialibalexandriabook_providerslsrb">trunk/alexandria/lib/alexandria/book_providers/ls.rb</a></li>
<li><a href="#trunkalexandrialibalexandriabook_providersmcurb">trunk/alexandria/lib/alexandria/book_providers/mcu.rb</a></li>
<li><a href="#trunkalexandrialibalexandriabook_providerswebster_itrb">trunk/alexandria/lib/alexandria/book_providers/webster_it.rb</a></li>
<li><a href="#trunkalexandrialibalexandriabook_providersworldcatrb">trunk/alexandria/lib/alexandria/book_providers/worldcat.rb</a></li>
<li><a href="#trunkalexandrialibalexandriabook_providersrb">trunk/alexandria/lib/alexandria/book_providers.rb</a></li>
<li><a href="#trunkalexandrialibalexandrialibraryrb">trunk/alexandria/lib/alexandria/library.rb</a></li>
<li><a href="#trunkalexandriateststest_providersrb">trunk/alexandria/tests/test_providers.rb</a></li>
</ul>
</div>
<div id="patch">
<h3>Diff</h3>
<a id="trunkalexandrialibalexandriabook_providersadlibrisrb"></a>
<div class="modfile"><h4>Modified: trunk/alexandria/lib/alexandria/book_providers/adlibris.rb (616 => 617)</h4>
<pre class="diff"><span>
<span class="info">--- trunk/alexandria/lib/alexandria/book_providers/adlibris.rb 2007-02-23 17:46:49 UTC (rev 616)
+++ trunk/alexandria/lib/alexandria/book_providers/adlibris.rb 2007-02-23 21:56:39 UTC (rev 617)
</span><span class="lines">@@ -141,7 +141,8 @@
</span><span class="cx"> product["title"] = CGI.unescape(md[1])
</span><span class="cx">
</span><span class="cx">
</span><del>- regx = /<tr><td colspan="2" class="text">F&#246;rfattare:&nbsp;<b>([^<]*)<\/b><\/td><\/tr>/
</del><ins>+# regx = /<tr><td colspan="2" class="text">F&#246;rfattare:&nbsp;<b>([^<]*)<\/b><\/td><\/tr>/
+ regx = /<tr><td colspan="2" class="text">F.rfattare:&nbsp;<b>([^<]*)<\/b><\/td><\/tr>/
</ins><span class="cx"> product["authors"] = []
</span><span class="cx"> data.scan(regx) do |md| next unless md[0] != md[1]
</span><span class="cx"> product["authors"] << translate_html_stuff(CGI.unescape(md[0]))
</span><span class="lines">@@ -156,8 +157,8 @@
</span><span class="cx">
</span><span class="cx"> product["edition"] = md[1] or nil
</span><span class="cx">
</span><del>-
- img_url = "covers/" + isbn[0 .. 0] + "/" + isbn[1 .. 2] + "/" + isbn + ".jpg"
</del><ins>+ isbn10 = Library.canonicalise_isbn(isbn)
+ img_url = "covers/" + isbn10[0 .. 0] + "/" + isbn10[1 .. 2] + "/" + isbn10 + ".jpg"
</ins><span class="cx"> #puts img_url
</span><span class="cx"> raise "No image found" unless md = data.match(img_url)
</span><span class="cx"> product["cover"] = BASE_URI + img_url
</span><span class="lines">@@ -165,7 +166,7 @@
</span><span class="cx"> book = Book.new(
</span><span class="cx"> translate_html_stuff(product["title"]),
</span><span class="cx"> product["authors"],
</span><del>- isbn,
</del><ins>+ Library.canonicalise_ean(isbn),
</ins><span class="cx"> translate_html_stuff(product["publisher"]),
</span><span class="cx"> publish_year = 0,
</span><span class="cx"> translate_html_stuff(product["edition"]))
</span></span></pre></div>
<a id="trunkalexandrialibalexandriabook_providersamazonrb"></a>
<div class="modfile"><h4>Modified: trunk/alexandria/lib/alexandria/book_providers/amazon.rb (616 => 617)</h4>
<pre class="diff"><span>
<span class="info">--- trunk/alexandria/lib/alexandria/book_providers/amazon.rb 2007-02-23 17:46:49 UTC (rev 616)
+++ trunk/alexandria/lib/alexandria/book_providers/amazon.rb 2007-02-23 21:56:39 UTC (rev 617)
</span><span class="lines">@@ -28,7 +28,7 @@
</span><span class="cx"> CACHE_DIR = File.join(Alexandria::Library::DIR, '.amazon_cache')
</span><span class="cx">
</span><span class="cx"> def initialize
</span><del>- super("Amazon", "Amazon (USA)")
</del><ins>+ super("Amazon", "Amazon (Usa)")
</ins><span class="cx"> prefs.add("locale", _("Locale"), "us",
</span><span class="cx"> Amazon::Search::LOCALES.keys)
</span><span class="cx"> prefs.add("dev_token", _("Development token"),
</span><span class="lines">@@ -118,10 +118,17 @@
</span><span class="cx"> media = product.media.squeeze(' ')
</span><span class="cx"> media = nil if media == 'Unknown Binding'
</span><span class="cx">
</span><ins>+ isbn = product.isbn.squeeze(' ')
+ if Library.valid_isbn?(isbn)
+ isbn = Library.canonicalise_ean(isbn)
+ else
+ isbn = nil # it may be an ASIN which is not an ISBN
+ end
+
</ins><span class="cx"> book = Book.new(title,
</span><span class="cx"> (product.authors.map { |x| x.squeeze(' ') } \
</span><span class="cx"> rescue [ ]),
</span><del>- product.isbn.squeeze(' '),
</del><ins>+ isbn,
</ins><span class="cx"> (product.manufacturer.squeeze(' ') \
</span><span class="cx"> rescue nil),
</span><span class="cx"> (Time.parse(product.release_date).year \
</span></span></pre></div>
<a id="trunkalexandrialibalexandriabook_providersbol_itrb"></a>
<div class="modfile"><h4>Modified: trunk/alexandria/lib/alexandria/book_providers/bol_it.rb (616 => 617)</h4>
<pre class="diff"><span>
<span class="info">--- trunk/alexandria/lib/alexandria/book_providers/bol_it.rb 2007-02-23 17:46:49 UTC (rev 616)
+++ trunk/alexandria/lib/alexandria/book_providers/bol_it.rb 2007-02-23 21:56:39 UTC (rev 617)
</span><span class="lines">@@ -57,7 +57,7 @@
</span><span class="cx"> end
</span><span class="cx">
</span><span class="cx"> ## warning: this provider uses pages like http://www.bol.it/libri/scheda/ea978888584104 with 12 numbers, without the checksum
</span><del>- criterion = "ea978" + Library.canonicalise_isbn(criterion)[0 .. -2] + ".html" if type == SEARCH_BY_ISBN
</del><ins>+ criterion = "ea" + Library.canonicalise_ean(criterion)[0 .. -2] + ".html" if type == SEARCH_BY_ISBN
</ins><span class="cx"> req += CGI.escape(criterion)
</span><span class="cx"> p req if $DEBUG
</span><span class="cx"> data = transport.get(URI.parse(req))
</span><span class="lines">@@ -77,7 +77,7 @@
</span><span class="cx"> end
</span><span class="cx">
</span><span class="cx"> def url(book)
</span><del>- BASE_URI + "/#{LOCALE}/scheda/ea978" + Library.canonicalise_isbn(book.isbn)[0 .. -2] + ".html"
</del><ins>+ BASE_URI + "/#{LOCALE}/scheda/ea" + Library.canonicalise_ean(book.isbn)[0 .. -2] + ".html"
</ins><span class="cx"> end
</span><span class="cx">
</span><span class="cx"> #######
</span></span></pre></div>
<a id="trunkalexandrialibalexandriabook_providerslsrb"></a>
<div class="modfile"><h4>Modified: trunk/alexandria/lib/alexandria/book_providers/ls.rb (616 => 617)</h4>
<pre class="diff"><span>
<span class="info">--- trunk/alexandria/lib/alexandria/book_providers/ls.rb 2007-02-23 17:46:49 UTC (rev 616)
+++ trunk/alexandria/lib/alexandria/book_providers/ls.rb 2007-02-23 21:56:39 UTC (rev 617)
</span><span class="lines">@@ -91,7 +91,7 @@
</span><span class="cx"> end
</span><span class="cx">
</span><span class="cx"> raise "No ISBN from Image" unless md = /<img src="capas\/([\dX]+)p?\.jpg" alt="" ?\/>/.match(data)
</span><del>- isbn = md[1].strip
</del><ins>+ isbn = Library.canonicalise_ean(md[1].strip)
</ins><span class="cx">
</span><span class="cx"> if md = /<br[^>]*>Editora: ([^<]+)<br>/.match(data)
</span><span class="cx"> publisher = md[1].strip
</span></span></pre></div>
<a id="trunkalexandrialibalexandriabook_providersmcurb"></a>
<div class="modfile"><h4>Modified: trunk/alexandria/lib/alexandria/book_providers/mcu.rb (616 => 617)</h4>
<pre class="diff"><span>
<span class="info">--- trunk/alexandria/lib/alexandria/book_providers/mcu.rb 2007-02-23 17:46:49 UTC (rev 616)
+++ trunk/alexandria/lib/alexandria/book_providers/mcu.rb 2007-02-23 21:56:39 UTC (rev 617)
</span><span class="lines">@@ -1,14 +1,5 @@
</span><del>-# This provider has switched from method "get" to method "post".
-# It would be nice to fix it. WWW:mechanize can be used, this is already done with provider deastore.
-# http://mechanize.rubyforge.org/
-# http://www.ntecs.de/blog-old/Blog/WWW-Mechanize.rdoc
-# http://rubyforge.org/projects/mechanize/
-# See also
-# http://www.mcu.es/libro/CE/AgenciaISBN/BBDDLibros/Sobre.html
-# https://rubyforge.org/tracker/index.php?func=detail&aid=2518&group_id=205&atid=863
-# https://rubyforge.org/tracker/index.php?func=detail&aid=2533&group_id=205&atid=863
-
</del><span class="cx"> # Copyright (C) 2004 Javier Fernandez-Sanguino
</span><ins>+# Copyright (C) 2007 Javier Fernandez-Sanguino and Marco Costantini
</ins><span class="cx"> #
</span><span class="cx"> # Alexandria is free software; you can redistribute it and/or
</span><span class="cx"> # modify it under the terms of the GNU General Public License as
</span><span class="lines">@@ -28,6 +19,9 @@
</span><span class="cx"> require 'cgi'
</span><span class="cx"> require 'net/http'
</span><span class="cx">
</span><ins>+# http://www.mcu.es/libro/CE/AgenciaISBN/BBDDLibros/Sobre.html
+# http://www.mcu.es/comun/bases/isbn/ISBN.html
+
</ins><span class="cx"> module Alexandria
</span><span class="cx"> class BookProviders
</span><span class="cx"> class MCUProvider < GenericProvider
</span><span class="lines">@@ -38,7 +32,8 @@
</span><span class="cx"> 'es' => '1'
</span><span class="cx"> }
</span><span class="cx">
</span><del>- BASE_URI = "http://www.mcu.es/cgi-bin/BRSCGI3701?"
</del><ins>+# BASE_URI = "http://www.mcu.es/cgi-bin/BRSCGI3701?"
+ BASE_URI = "http://www.mcu.es/cgi-brs/BasesHTML/isbn/BRSCGI?"
</ins><span class="cx"> def initialize
</span><span class="cx"> super("MCU", _("Spanish Culture Ministry"))
</span><span class="cx"> # No preferences
</span><span class="lines">@@ -46,21 +41,21 @@
</span><span class="cx">
</span><span class="cx"> def search(criterion, type)
</span><span class="cx"> prefs.read
</span><del>- criterion = criterion.convert("WINDOWS-1252", "UTF-8")
</del><ins>+ criterion = criterion.convert("iso-8859-1", "UTF-8")
</ins><span class="cx"> print "Doing search with MCU #{criterion}, type: #{type}\n" if $DEBUG # for DEBUGing
</span><del>- req = BASE_URI + "CMD=VERLST&BASE=ISBN&CONF=AEISPA.cnf&OPDEF=AND&DOCS=1-1000&SEPARADOR=&"
</del><ins>+ req = BASE_URI + "CMD=VERLST&BASE=ISBN&DOCS=1-15&CONF=AEISPA.cnf&OPDEF=AND&DOCS=1-1000&SEPARADOR=&"
</ins><span class="cx"> req += case type
</span><span class="cx"> when SEARCH_BY_ISBN
</span><del>- "WGEN-C=&WISB-C=#{CGI::escape(criterion)}&WAUT-C=&WTIT-C=&WMAT-C=&WEDI-C=&WFEP-C=&%40T353-GE=&%40T353-LE=&WSER-C=&WLUG-C=&WDIS-C=DISPONIBLE&WLEN-C=&WCLA-C=&WSOP-C="
</del><ins>+ "WGEN-C=&WISB-C=#{CGI::escape(criterion)}&WAUT-C=&WTIT-C=&WMAT-C=&WEDI-C=&WFEP-C=&%40T353-GE=&%40T353-LE=&WSER-C=&WLUG-C=&WDIS-C=%28DISPONIBLE+or+AGOTADO%29&WLEN-C=&WCLA-C=&WSOP-C="
</ins><span class="cx">
</span><span class="cx"> when SEARCH_BY_TITLE
</span><del>- "WGEN-C=&WISB-C=&WAUT-C=&WTIT-C=#{CGI::escape(criterion)}&WMAT-C=&WEDI-C=&WFEP-C=&%40T353-GE=&%40T353-LE=&WSER-C=&WLUG-C=&WDIS-C=DISPONIBLE&WLEN-C=&WCLA-C=&WSOP-C="
</del><ins>+ "WGEN-C=&WISB-C=&WAUT-C=&WTIT-C=#{CGI::escape(criterion)}&WMAT-C=&WEDI-C=&WFEP-C=&%40T353-GE=&%40T353-LE=&WSER-C=&WLUG-C=&WDIS-C=%28DISPONIBLE+or+AGOTADO%29&WLEN-C=&WCLA-C=&WSOP-C="
</ins><span class="cx">
</span><span class="cx"> when SEARCH_BY_AUTHORS
</span><del>- "WGEN-C=&WISB-C=&WAUT-C=#{CGI::escape(criterion)}&WTIT-C=&WMAT-C=&WEDI-C=&WFEP-C=&%40T353-GE=&%40T353-LE=&WSER-C=&WLUG-C=&WDIS-C=DISPONIBLE&WLEN-C=&WCLA-C=&WSOP-C="
</del><ins>+ "WGEN-C=&WISB-C=&WAUT-C=#{CGI::escape(criterion)}&WTIT-C=&WMAT-C=&WEDI-C=&WFEP-C=&%40T353-GE=&%40T353-LE=&WSER-C=&WLUG-C=&WDIS-C=%28DISPONIBLE+or+AGOTADO%29&WLEN-C=&WCLA-C=&WSOP-C="
</ins><span class="cx">
</span><span class="cx"> when SEARCH_BY_KEYWORD
</span><del>- "WGEN-C=#{CGI::escape(criterion)}&WISB-C=&WAUT-C=&WTIT-C=&WMAT-C=&WEDI-C=&WFEP-C=&%40T353-GE=&%40T353-LE=&WSER-C=&WLUG-C=&WDIS-C=DISPONIBLE&WLEN-C=&WCLA-C=&WSOP-C="
</del><ins>+ "WGEN-C=#{CGI::escape(criterion)}&WISB-C=&WAUT-C=&WTIT-C=&WMAT-C=&WEDI-C=&WFEP-C=&%40T353-GE=&%40T353-LE=&WSER-C=&WLUG-C=&WDIS-C=%28DISPONIBLE+or+AGOTADO%29&WLEN-C=&WCLA-C=&WSOP-C="
</ins><span class="cx">
</span><span class="cx"> else
</span><span class="cx"> raise InvalidSearchTypeError
</span><span class="lines">@@ -72,7 +67,7 @@
</span><span class="cx"> print "Reading line: #{line}" if $DEBUG # for DEBUGing
</span><span class="cx"> if (line =~ /CMD=VERDOC.*&DOCN=([^&]*)&NDOC=([^&]*)/) and (!products[$1]) and (book = parseBook($1,$2)) then
</span><span class="cx"> products[$1] = book
</span><del>- puts $1
</del><ins>+ puts $1 if $DEBUG # for DEBUGing
</ins><span class="cx"> end
</span><span class="cx"> end
</span><span class="cx">
</span><span class="lines">@@ -81,7 +76,7 @@
</span><span class="cx"> end
</span><span class="cx">
</span><span class="cx"> def url(book)
</span><del>- "http://www.mcu.es/cgi-bin/BRSCGI3701?CMD=VERLST&BASE=ISBN&CONF=AEISPA.cnf&OPDEF=AND&DOCS=1&SEPARADOR=&WGEN-C=&WISB-C=" + book.isbn + "&WAUT-C=&WTIT-C=&WMAT-C=&WEDI-C=&WFEP-C=&%40T353-GE=&%40T353-LE=&WSER-C=&WLUG-C=&WDIS-C=DISPONIBLE&WLEN-C=&WCLA-C=&WSOP-C="
</del><ins>+ "http://www.mcu.es/cgi-brs/BasesHTML/isbn/BRSCGI?CMD=VERLST&BASE=ISBN&DOCS=1-15&CONF=AEISPA.cnf&OPDEF=AND&DOCS=1&SEPARADOR=&WGEN-C=&WISB-C=" + book.isbn + "&WAUT-C=&WTIT-C=&WMAT-C=&WEDI-C=&WFEP-C=&%40T353-GE=&%40T353-LE=&WSER-C=&WLUG-C=&WDIS-C=%28DISPONIBLE+or+AGOTADO%29&WLEN-C=&WCLA-C=&WSOP-C="
</ins><span class="cx"> end
</span><span class="cx">
</span><span class="cx"> #######
</span><span class="lines">@@ -89,7 +84,7 @@
</span><span class="cx"> #######
</span><span class="cx">
</span><span class="cx"> def parseBook(docn,ndoc)
</span><del>- detailspage='http://www.mcu.es/cgi-bin/BRSCGI3701?CMD=VERDOC&CONF=AEISPA.cnf&BASE=ISBN&DOCN=' + docn + '&NDOC=' + ndoc
</del><ins>+ detailspage='http://www.mcu.es/cgi-brs/BasesHTML/isbn/BRSCGI?CMD=VERDOC&CONF=AEISPA.cnf&BASE=ISBN&DOCN=' + docn + '&NDOC=' + ndoc
</ins><span class="cx"> print "Looking at detailspage: #{detailspage}\n" if $DEBUG # for DEBUGing
</span><span class="cx"> product = {}
</span><span class="cx"> product['authors'] = []
</span><span class="lines">@@ -121,7 +116,7 @@
</span><span class="cx"> product['name'] = $1.strip
</span><span class="cx"> print "Name is #{product['name']}\n" if $DEBUG # for DEBUGing
</span><span class="cx"> robotstate = 0
</span><del>- elsif robotstate == 3 and line =~ /^([0-9]+-[0-9]+-[0-9]+-[0-9X]).*/
</del><ins>+ elsif robotstate == 3 and line =~ /^([0-9]+-[0-9]+-[0-9]+-[0-9]+-[0-9]).*/
</ins><span class="cx"> product['isbn'] = $1
</span><span class="cx"> print "ISBN is #{product['isbn']}\n" if $DEBUG # for DEBUGing
</span><span class="cx"> robotstate = 0
</span><span class="lines">@@ -129,19 +124,20 @@
</span><span class="cx"> product['manufacturer'] = $1.strip
</span><span class="cx"> print "Manufacturer is #{product['manufacturer']}\n" if $DEBUG # for DEBUGing
</span><span class="cx"> robotstate = 0
</span><del>- elsif robotstate == 5 and line =~ /^([^<]+)</
</del><ins>+# elsif robotstate == 5 and line =~ /^([^<]+)</
+ elsif robotstate == 5 and line =~ /<span>([^<]+)</
</ins><span class="cx"> product['media'] = $1.strip
</span><span class="cx"> print "Media is #{product['media']}\n" if $DEBUG # for DEBUGing
</span><span class="cx"> robotstate = 0
</span><span class="cx"> elsif line =~ /^.*>Autor:\s*</
</span><span class="cx"> robotstate = 1
</span><del>- elsif line =~ /^.*>T.tulo:\s*</
</del><ins>+ elsif line =~ /^.*>T(.|&iacute;)tulo:\s*</
</ins><span class="cx"> robotstate = 2
</span><del>- elsif line =~ /^.*>ISBN:\s*</
</del><ins>+ elsif line =~ /^.*>ISBN \(13\):\s*</
</ins><span class="cx"> robotstate = 3
</span><del>- elsif line =~ /^.*>Publicaci.n:\s*</
</del><ins>+ elsif line =~ /^.*>Publicaci(.|&oacute;)n:\s*</
</ins><span class="cx"> robotstate = 4
</span><del>- elsif line =~ /^.*>Encuadernaci.n:\s*</
</del><ins>+ elsif line =~ /^.*>Encuadernaci(.|&oacute;)n:\s*</
</ins><span class="cx"> robotstate = 5
</span><span class="cx"> end
</span><span class="cx"> end
</span></span></pre></div>
<a id="trunkalexandrialibalexandriabook_providerswebster_itrb"></a>
<div class="modfile"><h4>Modified: trunk/alexandria/lib/alexandria/book_providers/webster_it.rb (616 => 617)</h4>
<pre class="diff"><span>
<span class="info">--- trunk/alexandria/lib/alexandria/book_providers/webster_it.rb 2007-02-23 17:46:49 UTC (rev 616)
+++ trunk/alexandria/lib/alexandria/book_providers/webster_it.rb 2007-02-23 21:56:39 UTC (rev 617)
</span><span class="lines">@@ -98,13 +98,11 @@
</span><span class="cx"> authors = this.scan(/<a href="[^>]+">([^<]+)<\/a>,?/)
</span><span class="cx"> authors = authors.collect {|author| author[0]}
</span><span class="cx"> #puts this
</span><del>-
</del><span class="cx"> # md[1].strip.split(', ').each { |a| authors << CGI.unescape(a.strip) }
</span><span class="cx"> end
</span><span class="cx">
</span><span class="cx"> raise unless md = /<li><span class="product_label">ISBN:<\/span> <span class="product_text">([^<]+)/.match(data)
</span><del>- isbn = "978" + md[1].strip[0..8]
- isbn += String( Library.ean_checksum( Library.extract_numbers( isbn ) ) )
</del><ins>+ isbn = Library.canonicalise_ean( md[1].strip )
</ins><span class="cx">
</span><span class="cx"> raise unless md = /<li><span class="product_label">Editore:<\/span> <span class="product_text"><a href="[^>]+>([^<]+)/.match(data)
</span><span class="cx"> publisher = CGI.unescape(md[1].strip)
</span></span></pre></div>
<a id="trunkalexandrialibalexandriabook_providersworldcatrb"></a>
<div class="modfile"><h4>Modified: trunk/alexandria/lib/alexandria/book_providers/worldcat.rb (616 => 617)</h4>
<pre class="diff"><span>
<span class="info">--- trunk/alexandria/lib/alexandria/book_providers/worldcat.rb 2007-02-23 17:46:49 UTC (rev 616)
+++ trunk/alexandria/lib/alexandria/book_providers/worldcat.rb 2007-02-23 21:56:39 UTC (rev 617)
</span><span class="lines">@@ -90,7 +90,7 @@
</span><span class="cx">
</span><span class="cx"> authors = []
</span><span class="cx"> md = data.scan(/title="Search for more by this author">([^<]+)/)
</span><del>- raise "No authors" unless md.length > 0
</del><ins>+# raise "No authors" unless md.length > 0
</ins><span class="cx"> md = md.collect {|match| match[0]}
</span><span class="cx"> md.each {|match|
</span><span class="cx"> CGI.unescape(match.strip)
</span></span></pre></div>
<a id="trunkalexandrialibalexandriabook_providersrb"></a>
<div class="modfile"><h4>Modified: trunk/alexandria/lib/alexandria/book_providers.rb (616 => 617)</h4>
<pre class="diff"><span>
<span class="info">--- trunk/alexandria/lib/alexandria/book_providers.rb 2007-02-23 17:46:49 UTC (rev 616)
+++ trunk/alexandria/lib/alexandria/book_providers.rb 2007-02-23 21:56:39 UTC (rev 617)
</span><span class="lines">@@ -231,7 +231,7 @@
</span><span class="cx">
</span><span class="cx"> require 'alexandria/book_providers/bn'
</span><span class="cx"> require 'alexandria/book_providers/proxis'
</span><del>- #require 'alexandria/book_providers/mcu'
</del><ins>+ require 'alexandria/book_providers/mcu'
</ins><span class="cx"> require 'alexandria/book_providers/thalia'
</span><span class="cx"> require 'alexandria/book_providers/ibs_it'
</span><span class="cx"> require 'alexandria/book_providers/renaud'
</span></span></pre></div>
<a id="trunkalexandrialibalexandrialibraryrb"></a>
<div class="modfile"><h4>Modified: trunk/alexandria/lib/alexandria/library.rb (616 => 617)</h4>
<pre class="diff"><span>
<span class="info">--- trunk/alexandria/lib/alexandria/library.rb 2007-02-23 17:46:49 UTC (rev 616)
+++ trunk/alexandria/lib/alexandria/library.rb 2007-02-23 21:56:39 UTC (rev 617)
</span><span class="lines">@@ -228,9 +228,24 @@
</span><span class="cx"> self.extract_numbers(AMERICAN_UPC_LOOKUP[test_upc])
</span><span class="cx"> end
</span><span class="cx">
</span><ins>+ def self.canonicalise_ean(code)
+ if self.valid_ean?(code)
+ return code
+ elsif self.valid_isbn?(code)
+ code = "978" + code[0..8]
+ return code + String( self.ean_checksum( self.extract_numbers( code ) ) )
+ elsif self.valid_upc?(code)
+ raise "fix function Alexandria::Library.canonicalise_ean"
+ else
+ raise InvalidISBNError.new(code)
+ end
+ end
+
</ins><span class="cx"> def self.canonicalise_isbn(isbn)
</span><span class="cx"> numbers = self.extract_numbers(isbn)
</span><del>-
</del><ins>+if self.valid_ean?(isbn) and numbers[0 .. 2] != [9,7,8]
+ return isbn
+end
</ins><span class="cx"> canonical = if self.valid_ean?(isbn)
</span><span class="cx"> # Looks like an EAN number -- extract the intersting part and
</span><span class="cx"> # calculate a checksum. It would be nice if we could validate
</span></span></pre></div>
<a id="trunkalexandriateststest_providersrb"></a>
<div class="modfile"><h4>Modified: trunk/alexandria/tests/test_providers.rb (616 => 617)</h4>
<pre class="diff"><span>
<span class="info">--- trunk/alexandria/tests/test_providers.rb 2007-02-23 17:46:49 UTC (rev 616)
+++ trunk/alexandria/tests/test_providers.rb 2007-02-23 21:56:39 UTC (rev 617)
</span><span class="lines">@@ -31,7 +31,7 @@
</span><span class="cx">
</span><span class="cx"> def test_amazon_isbn
</span><span class="cx"> __test_provider(Alexandria::BookProviders::AmazonProvider,
</span><del>- '0385504209')
</del><ins>+ '9780385504201')
</ins><span class="cx"> end
</span><span class="cx">
</span><span class="cx"> def test_amazon_title
</span><span class="lines">@@ -54,10 +54,10 @@
</span><span class="cx"> '9780961328917') # see #1433
</span><span class="cx"> end
</span><span class="cx">
</span><del>-# def test_mcu
-# __test_provider(Alexandria::BookProviders::MCUProvider,
-# '8420636665')
-# end
</del><ins>+ def test_mcu
+ __test_provider(Alexandria::BookProviders::MCUProvider,
+ '9788420636665')
+ end
</ins><span class="cx">
</span><span class="cx"> def test_proxis
</span><span class="cx"> __test_provider(Alexandria::BookProviders::ProxisProvider,
</span><span class="lines">@@ -82,12 +82,12 @@
</span><span class="cx">
</span><span class="cx"> def test_adlibris
</span><span class="cx"> __test_provider(Alexandria::BookProviders::AdlibrisProvider,
</span><del>- '9100109339')
</del><ins>+ '9789100109332')
</ins><span class="cx"> end
</span><span class="cx">
</span><span class="cx"> def test_siciliano
</span><span class="cx"> __test_provider(Alexandria::BookProviders::SicilianoProvider,
</span><del>- '8599170384')
</del><ins>+ '9788599170380')
</ins><span class="cx"> end
</span><span class="cx">
</span><span class="cx"> def test_dea
</span></span></pre>
</div>
</div>
</body>
</html>