20486d5053
import/export of file data should work for all file types _except_ snapshots (in this situation, export is working, but import is not yet complete; see #193) also, fixes a potential security issue that could have allowed malicious web translators to post local data to remote sites (although, given we maintain the central repository and there's no easy way to install a translator, the risk would have been minimal to begin with).
5599 lines
No EOL
175 KiB
SQL
5599 lines
No EOL
175 KiB
SQL
-- 51
|
||
|
||
-- Set the following timestamp to the most recent scraper update date
|
||
REPLACE INTO "version" VALUES ('repository', STRFTIME('%s', '2006-08-15 15:42:00'));
|
||
|
||
REPLACE INTO "translators" VALUES ('96b9f483-c44d-5784-cdad-ce21b984fe01', '2006-08-11 11:18:00', 4, 'Amazon.com', 'Simon Kornblith', '^http://www\.amazon\.com/(?:gp/(?:product|search)/|exec/obidos/search-handle-url/|s/)',
|
||
'function detectWeb(doc, url) {
|
||
var searchRe = new RegExp(''^http://www\.amazon\.com/(gp/search/|exec/obidos/search-handle-url/|s/)'');
|
||
if(searchRe.test(doc.location.href)) {
|
||
return "multiple";
|
||
} else {
|
||
return "book";
|
||
}
|
||
}
|
||
',
|
||
'function scrape(doc) {
|
||
var namespace = doc.documentElement.namespaceURI;
|
||
var nsResolver = namespace ? function(prefix) {
|
||
if (prefix == ''x'') return namespace; else return null;
|
||
} : null;
|
||
|
||
var newItem = new Scholar.Item("book");
|
||
|
||
// Retrieve authors
|
||
try {
|
||
var xpath = ''/html/body/table/tbody/tr/td[2]/form/div[@class="buying"]/a/text()[1]'';
|
||
var elmts = doc.evaluate(xpath, doc, nsResolver, XPathResult.ANY_TYPE, null);
|
||
var elmt;
|
||
while(elmt = elmts.iterateNext()) {
|
||
newItem.creators.push(Scholar.Utilities.cleanAuthor(elmt.nodeValue, "author"));
|
||
}
|
||
} catch(ex) {Scholar.Utilities.debug(ex);}
|
||
|
||
// Retrieve data from "Product Details" box
|
||
var xpath = ''/html/body/table/tbody/tr/td[2]/table/tbody/tr/td[@class="bucket"]/div[@class="content"]/ul/li'';
|
||
var elmts = doc.evaluate(xpath, doc, nsResolver, XPathResult.ANY_TYPE, null);
|
||
var elmt;
|
||
|
||
newItem.extra = "";
|
||
while(elmt = elmts.iterateNext()) {
|
||
try {
|
||
var attribute = Scholar.Utilities.cleanString(doc.evaluate(''./B[1]/text()[1]'', elmt, nsResolver, XPathResult.ANY_TYPE, null).iterateNext().nodeValue);
|
||
var value = Scholar.Utilities.getNodeString(doc, elmt, ''./descendant-or-self::*[name() != "B"]/text()'', nsResolver);
|
||
if(value) {
|
||
value = Scholar.Utilities.cleanString(value);
|
||
|
||
if(attribute == "Publisher:") {
|
||
if(value.lastIndexOf("(") != -1) {
|
||
var date = value.substring(value.lastIndexOf("(")+1, value.length-1);
|
||
jsDate = new Date(date);
|
||
if(!isNaN(jsDate.valueOf())) {
|
||
date = Scholar.Utilities.dateToSQL(jsDate);
|
||
}
|
||
newItem.date = date;
|
||
|
||
value = value.substring(0, value.lastIndexOf("(")-1);
|
||
}
|
||
if(value.lastIndexOf(";") != -1) {
|
||
newItem.edition = value.substring(value.lastIndexOf(";")+2, value.length);
|
||
|
||
value = value.substring(0, value.lastIndexOf(";"));
|
||
}
|
||
newItem.publisher = value;
|
||
} else if(attribute == "ISBN:") {
|
||
newItem.ISBN = value;
|
||
} else if(value.substring(value.indexOf(" ")+1, value.length) == "pages") {
|
||
newItem.pages = value.substring(0, value.indexOf(" "));
|
||
} else if(attribute != "Average Customer Review:") {
|
||
Scholar.Utilities.debug(''"''+attribute+''"'');
|
||
if(attribute == "In-Print Editions:") {
|
||
value = value.replace(" | All Editions", "");
|
||
} else {
|
||
value = value.replace(/\([^)]*\)/g, "");
|
||
}
|
||
|
||
newItem.extra += attribute+" "+value+"\n";
|
||
}
|
||
}
|
||
} catch(ex) {}
|
||
}
|
||
|
||
Scholar.Utilities.debug(newItem.extra);
|
||
if(newItem.extra) {
|
||
newItem.extra = newItem.extra.substr(0, newItem.extra.length-1);
|
||
}
|
||
|
||
newItem.attachments.push({title:"Amazon.com Product Page", document:doc});
|
||
|
||
var xpath = ''/html/body/table/tbody/tr/td[2]/form/div[@class="buying"]/b[@class="sans"]/text()[1]'';
|
||
var title = doc.evaluate(xpath, doc, nsResolver, XPathResult.ANY_TYPE, null).iterateNext().nodeValue;
|
||
title = Scholar.Utilities.cleanString(title);
|
||
if(title.lastIndexOf("(") != -1 && title.lastIndexOf(")") == title.length-1) {
|
||
title = title.substring(0, title.lastIndexOf("(")-1);
|
||
}
|
||
newItem.title = title;
|
||
|
||
newItem.complete();
|
||
}
|
||
|
||
function doWeb(doc, url) {
|
||
var searchRe = new RegExp(''^http://www\.amazon\.com/(gp/search/|exec/obidos/search-handle-url/|s/)'');
|
||
var m = searchRe.exec(doc.location.href)
|
||
if(m) {
|
||
var namespace = doc.documentElement.namespaceURI;
|
||
var nsResolver = namespace ? function(prefix) {
|
||
if (prefix == ''x'') return namespace; else return null;
|
||
} : null;
|
||
|
||
// Why can''t amazon use the same stylesheets
|
||
var xpath;
|
||
if(m == "exec/obidos/search-handle-url/") {
|
||
xpath = ''//table[@cellpadding="3"]'';
|
||
} else {
|
||
xpath = ''//table[@class="searchresults"]'';
|
||
}
|
||
|
||
var searchresults = Scholar.Utilities.gatherElementsOnXPath(doc, doc, xpath, nsResolver);
|
||
var items = Scholar.Utilities.getItemArray(doc, searchresults, ''^http://www\.amazon\.com/(gp/product/|exec/obidos/tg/detail/)'', ''^(Buy new|Hardcover|Paperback|Digital)$'');
|
||
items = Scholar.selectItems(items);
|
||
|
||
if(!items) {
|
||
return true;
|
||
}
|
||
|
||
var uris = new Array();
|
||
for(var i in items) {
|
||
uris.push(i);
|
||
}
|
||
|
||
Scholar.Utilities.processDocuments(uris, function(doc) { scrape(doc) },
|
||
function() { Scholar.done(); }, null);
|
||
|
||
Scholar.wait();
|
||
} else {
|
||
scrape(doc);
|
||
}
|
||
}');
|
||
|
||
REPLACE INTO "translators" VALUES ('838d8849-4ffb-9f44-3d0d-aa8a0a079afe', '2006-06-26 16:01:00', 4, 'WorldCat', 'Simon Kornblith', '^http://(?:new)?firstsearch\.oclc\.org/WebZ/',
|
||
'function detectWeb(doc, url) {
|
||
if(doc.title == ''FirstSearch: WorldCat Detailed Record'') {
|
||
return "book";
|
||
} else if(doc.title == ''FirstSearch: WorldCat List of Records'') {
|
||
return "multiple";
|
||
}
|
||
}',
|
||
'function processURLs(urls) {
|
||
if(!urls.length) { // last url
|
||
Scholar.done();
|
||
return;
|
||
}
|
||
|
||
var newUrl = urls.shift();
|
||
|
||
Scholar.Utilities.HTTP.doPost(newUrl,
|
||
''exportselect=record&exporttype=plaintext'', function(text) {
|
||
Scholar.Utilities.debug(text);
|
||
var lineRegexp = new RegExp();
|
||
lineRegexp.compile("^([\\w() ]+): *(.*)$");
|
||
|
||
var newItem = new Scholar.Item("book");
|
||
newItem.extra = "";
|
||
|
||
var lines = text.split(''\n'');
|
||
for(var i=0;i<lines.length;i++) {
|
||
var testMatch = lineRegexp.exec(lines[i]);
|
||
if(testMatch) {
|
||
var match = newMatch;
|
||
var newMatch = testMatch
|
||
} else {
|
||
var match = false;
|
||
}
|
||
|
||
if(match) {
|
||
// is a useful match
|
||
if(match[1] == ''Title'') {
|
||
var title = match[2];
|
||
if(!lineRegexp.test(lines[i+1])) {
|
||
i++;
|
||
title += '' ''+lines[i];
|
||
}
|
||
if(title.substring(title.length-2) == " /") {
|
||
title = title.substring(0, title.length-2);
|
||
}
|
||
newItem.title = title;
|
||
} else if(match[1] == ''Author(s)'') {
|
||
var yearRegexp = /[0-9]{4}-([0-9]{4})?/;
|
||
|
||
var authors = match[2].split('';'');
|
||
if(authors) {
|
||
newItem.creators.push(Scholar.Utilities.cleanAuthor(authors[0], "author", true));
|
||
for(var j=1; j<authors.length; j+=2) {
|
||
if(authors[j-1].substring(0, 1) != ''('' && !yearRegexp.test(authors[j])) {
|
||
// ignore places where there are parentheses
|
||
newItem.creators.push(Scholar.Utilities.cleanAuthor(authors[j], "author", true));
|
||
}
|
||
}
|
||
} else {
|
||
newItem.creators.push(Scholar.Utilities.cleanString(match[2]));
|
||
}
|
||
} else if(match[1] == ''Publication'') {
|
||
// Don''t even try to deal with this. The WorldCat metadata is of poor enough quality that this isn''t worth it.
|
||
match[2] = Scholar.Utilities.cleanString(match[2]);
|
||
if(match[2].substring(match[2].length-1) == '','') {
|
||
match[2] = match[2].substring(0, match[2].length-1);
|
||
}
|
||
newItem.publisher = match[2];
|
||
} else if(match[1] == ''Standard No'') {
|
||
var identifiers = match[2].split(/ +/);
|
||
var j=0;
|
||
while(j<(identifiers.length-1)) {
|
||
var type = identifiers[j].substring(0, identifiers[j].length-1);
|
||
var lastChar;
|
||
var value;
|
||
|
||
j++;
|
||
while(j<identifiers.length && (lastChar = identifiers[j].substring(identifiers[j].length-1)) != '':'') {
|
||
if(identifiers[j].substring(0, 1) != ''('') {
|
||
if(lastChar == '';'') {
|
||
value = identifiers[j].substring(0, identifiers[j].length-1);
|
||
} else {
|
||
value = identifiers[j];
|
||
}
|
||
if(type == "ISBN" || type == "ISSN") {
|
||
newItem[type] = value;
|
||
}
|
||
}
|
||
j++;
|
||
}
|
||
}
|
||
} else if(match[1] == ''Year'') {
|
||
newItem.date = match[2];
|
||
} else if(match[1] == "Descriptor") {
|
||
if(match[2][match[2].length-1] == ".") {
|
||
match[2] = match[2].substr(0, match[2].length-1);
|
||
}
|
||
|
||
var tags = match[2].split("--");
|
||
for(var j in tags) {
|
||
newItem.tags.push(Scholar.Utilities.cleanString(tags[j]));
|
||
}
|
||
} else if(match[1] == "Accession No") {
|
||
newItem.accessionNumber = Scholar.Utilities.superCleanString(match[2]);
|
||
} else if(match[1] != "Database") {
|
||
newItem.extra += match[1]+": "+match[2]+"\n";
|
||
}
|
||
} else {
|
||
if(lines[i] != "" && lines[i] != "SUBJECT(S)") {
|
||
newMatch[2] += " "+lines[i];
|
||
}
|
||
}
|
||
}
|
||
|
||
if(newItem.extra) {
|
||
newItem.extra = newItem.extra.substr(0, newItem.extra.length-1);
|
||
}
|
||
|
||
newItem.complete();
|
||
processURLs(urls);
|
||
});
|
||
}
|
||
|
||
function doWeb(doc, url) {
|
||
var sessionRegexp = /(?:\?|\:)sessionid=([^?:]+)(?:\?|\:|$)/;
|
||
var numberRegexp = /(?:\?|\:)recno=([^?:]+)(?:\?|\:|$)/;
|
||
var resultsetRegexp = /(?:\?|\:)resultset=([^?:]+)(?:\?|\:|$)/;
|
||
var hostRegexp = new RegExp("http://([^/]+)/");
|
||
|
||
var sMatch = sessionRegexp.exec(url);
|
||
var sessionid = sMatch[1];
|
||
|
||
var hMatch = hostRegexp.exec(url);
|
||
var host = hMatch[1];
|
||
|
||
var newUri, exportselect;
|
||
|
||
if(doc.title == ''FirstSearch: WorldCat Detailed Record'') {
|
||
var publisherRegexp = /^(.*), (.*?),?$/;
|
||
|
||
var nMatch = numberRegexp.exec(url);
|
||
if(nMatch) {
|
||
var number = nMatch[1];
|
||
} else {
|
||
number = 1;
|
||
}
|
||
|
||
var rMatch = resultsetRegexp.exec(url);
|
||
if(rMatch) {
|
||
var resultset = rMatch[1];
|
||
} else {
|
||
// It''s in an XPCNativeWrapper, so we have to do this black magic
|
||
resultset = doc.forms.namedItem(''main'').elements.namedItem(''resultset'').value;
|
||
}
|
||
|
||
urls = [''http://''+host+''/WebZ/DirectExport?numrecs=10:smartpage=directexport:entityexportnumrecs=10:entityexportresultset='' + resultset + '':entityexportrecno='' + number + '':sessionid='' + sessionid + '':entitypagenum=35:0''];
|
||
} else {
|
||
var items = Scholar.Utilities.getItemArray(doc, doc, ''/WebZ/FSFETCH\\?fetchtype=fullrecord'', ''^(See more details for locating this item|Detailed Record)$'');
|
||
items = Scholar.selectItems(items);
|
||
|
||
if(!items) {
|
||
return true;
|
||
}
|
||
|
||
var urls = new Array();
|
||
|
||
for(var i in items) {
|
||
var nMatch = numberRegexp.exec(i);
|
||
var rMatch = resultsetRegexp.exec(i);
|
||
if(rMatch && nMatch) {
|
||
var number = nMatch[1];
|
||
var resultset = rMatch[1];
|
||
urls.push(''http://''+host+''/WebZ/DirectExport?numrecs=10:smartpage=directexport:entityexportnumrecs=10:entityexportresultset='' + resultset + '':entityexportrecno='' + number + '':sessionid='' + sessionid + '':entitypagenum=35:0'');
|
||
}
|
||
}
|
||
}
|
||
|
||
processURLs(urls);
|
||
Scholar.wait();
|
||
}');
|
||
|
||
REPLACE INTO "translators" VALUES ('88915634-1af6-c134-0171-56fd198235ed', '2006-06-26 21:40:00', 4, 'LOC/Voyager WebVoyage', 'Simon Kornblith', 'Pwebrecon\.cgi',
|
||
'function detectWeb(doc, url) {
|
||
var export_options = doc.forms.namedItem(''frm'').elements.namedItem(''RD'').options;
|
||
for(var i in export_options) {
|
||
if(export_options[i].text == ''Latin1 MARC''
|
||
|| export_options[i].text == ''Raw MARC''
|
||
|| export_options[i].text == ''UTF-8''
|
||
|| export_options[i].text == ''MARC (Unicode/UTF-8)''
|
||
|| export_options[i].text == ''MARC (non-Unicode/MARC-8)'') {
|
||
// We have an exportable single record
|
||
if(doc.forms.namedItem(''frm'').elements.namedItem(''RC'')) {
|
||
return "multiple";
|
||
} else {
|
||
return "book";
|
||
}
|
||
}
|
||
}
|
||
}',
|
||
'function doWeb(doc, url) {
|
||
var postString = '''';
|
||
var form = doc.forms.namedItem(''frm'');
|
||
var newUri = form.action;
|
||
var multiple = false;
|
||
|
||
if(doc.forms.namedItem(''frm'').elements.namedItem(''RC'')) {
|
||
multiple = true;
|
||
|
||
var availableItems = new Object(); // Technically, associative arrays are objects
|
||
|
||
var namespace = doc.documentElement.namespaceURI;
|
||
var nsResolver = namespace ? function(prefix) {
|
||
if (prefix == ''x'') return namespace; else return null;
|
||
} : null;
|
||
|
||
// Require link to match this
|
||
var tagRegexp = new RegExp();
|
||
tagRegexp.compile(''Pwebrecon\\.cgi\\?.*v1=[0-9]+\\&.*ti='');
|
||
// Do not allow text to match this
|
||
var rejectRegexp = new RegExp();
|
||
rejectRegexp.compile(''\[ [0-9]+ \]'');
|
||
|
||
var checkboxes = new Array();
|
||
var urls = new Array();
|
||
|
||
var tableRows = doc.evaluate(''/html/body/form/table/tbody/tr[td/input[@type="checkbox"]]'', doc, nsResolver, XPathResult.ANY_TYPE, null);
|
||
// Go through table rows
|
||
var tableRow;
|
||
var i = 0;
|
||
while(tableRow = tableRows.iterateNext()) {
|
||
i++;
|
||
// CHK is what we need to get it all as one file
|
||
var input = doc.evaluate(''./td/input[@name="CHK"]'', tableRow, nsResolver, XPathResult.ANY_TYPE, null).iterateNext();
|
||
checkboxes[i] = input.value;
|
||
var links = tableRow.getElementsByTagName("a");
|
||
// Go through links
|
||
for(var j=0; j<links.length; j++) {
|
||
if(tagRegexp.test(links[j].href)) {
|
||
var text = Scholar.Utilities.getNodeString(doc, links[j], ".//text()", null);
|
||
if(text) {
|
||
text = Scholar.Utilities.cleanString(text);
|
||
if(!rejectRegexp.test(text)) {
|
||
if(availableItems[i]) {
|
||
availableItems[i] += " "+text;
|
||
} else {
|
||
availableItems[i] = text;
|
||
}
|
||
}
|
||
}
|
||
}
|
||
}
|
||
}
|
||
|
||
var items = Scholar.selectItems(availableItems);
|
||
if(!items) {
|
||
return true;
|
||
}
|
||
|
||
// add arguments for items we need to grab
|
||
for(var i in items) {
|
||
postString += "CHK="+checkboxes[i]+"&";
|
||
}
|
||
}
|
||
|
||
var raw, unicode, latin1;
|
||
|
||
for(var i=0; i<form.elements.length; i++) {
|
||
if(form.elements[i].type && form.elements[i].type.toLowerCase() == ''hidden'') {
|
||
postString += escape(form.elements[i].name)+''=''+escape(form.elements[i].value)+''&'';
|
||
}
|
||
}
|
||
|
||
var export_options = form.elements.namedItem(''RD'').options;
|
||
for(var i=0; i<export_options.length; i++) {
|
||
if(export_options[i].text == ''Raw MARC''
|
||
|| export_options[i].text == ''MARC (non-Unicode/MARC-8)'') {
|
||
raw = i;
|
||
} if(export_options[i].text == ''Latin1 MARC'') {
|
||
latin1 = i;
|
||
} else if(export_options[i].text == ''UTF-8''
|
||
|| export_options[i].text == ''MARC (Unicode/UTF-8)'') {
|
||
unicode = i;
|
||
}
|
||
}
|
||
|
||
if(unicode) {
|
||
var rd = unicode;
|
||
} else if(latin1) {
|
||
var rd = latin1;
|
||
} else if(raw) {
|
||
var rd = raw;
|
||
} else {
|
||
return false;
|
||
}
|
||
|
||
postString += ''RD=''+rd+''&MAILADDY=&SAVE=Press+to+SAVE+or+PRINT'';
|
||
|
||
// No idea why this doesn''t work as post
|
||
Scholar.Utilities.HTTP.doGet(newUri+''?''+postString, function(text) {
|
||
// load translator for MARC
|
||
var marc = Scholar.loadTranslator("import", "a6ee60df-1ddc-4aae-bb25-45e0537be973");
|
||
marc.Scholar.write(text);
|
||
marc.Scholar.eof();
|
||
marc.doImport(url);
|
||
|
||
Scholar.done();
|
||
})
|
||
Scholar.wait();
|
||
}');
|
||
|
||
REPLACE INTO "translators" VALUES ('d921155f-0186-1684-615c-ca57682ced9b', '2006-06-26 16:01:00', 4, 'JSTOR', 'Simon Kornblith', '^http://www\.jstor\.org/(?:view|browse|search/)',
|
||
'function detectWeb(doc, url) {
|
||
var namespace = doc.documentElement.namespaceURI;
|
||
var nsResolver = namespace ? function(prefix) {
|
||
if (prefix == ''x'') return namespace; else return null;
|
||
} : null;
|
||
|
||
// See if this is a seach results page
|
||
if(doc.title == "JSTOR: Search Results") {
|
||
return "multiple";
|
||
}
|
||
|
||
// If this is a view page, find the link to the citation
|
||
var xpath = ''/html/body/div[@class="indent"]/center//a[@class="nav"]'';
|
||
var elmts = doc.evaluate(xpath, doc, nsResolver, XPathResult.ANY_TYPE, null);
|
||
if(elmts.iterateNext()) {
|
||
return "journalArticle";
|
||
}
|
||
}',
|
||
'function getList(urls, each, done) {
|
||
var url = urls.shift();
|
||
Scholar.Utilities.HTTP.doGet(url, function(text) {
|
||
if(each) {
|
||
each(text);
|
||
}
|
||
|
||
if(urls.length) {
|
||
getList(urls, each, done);
|
||
} else if(done) {
|
||
done(text);
|
||
}
|
||
});
|
||
}
|
||
|
||
function getJSTORAttachment(viewURL) {
|
||
var viewRe = new RegExp("(^http://[^/]+/)view([^?]+)");
|
||
var m = viewRe.exec(viewURL);
|
||
if(m) {
|
||
return {url:m[1]+"cgi-bin/jstor/printpage"+m[2]+".pdf?dowhat=Acrobat",
|
||
mimeType:"application/pdf", title:"JSTOR Full Text PDF",
|
||
downloadable:true};
|
||
} else {
|
||
return false;
|
||
}
|
||
}
|
||
|
||
function itemComplete(newItem, url) {
|
||
if(newItem.url) {
|
||
newItem.attachments.push({url:newItem.url, mimeType:"text/html",
|
||
title:"JSTOR Web-Readable Version"});
|
||
} else {
|
||
if(newItem.ISSN) {
|
||
newItem.url = "http://www.jstor.org/browse/"+newItem.ISSN;
|
||
} else {
|
||
newItem.url = url;
|
||
}
|
||
}
|
||
|
||
newItem.complete();
|
||
}
|
||
|
||
function doWeb(doc, url) {
|
||
var namespace = doc.documentElement.namespaceURI;
|
||
var nsResolver = namespace ? function(prefix) {
|
||
if (prefix == ''x'') return namespace; else return null;
|
||
} : null;
|
||
var saveCitations = new Array();
|
||
var viewPages = new Array();
|
||
|
||
if(doc.title == "JSTOR: Search Results") {
|
||
var availableItems = new Object();
|
||
|
||
// Require link to match this
|
||
var tagRegexp = new RegExp();
|
||
tagRegexp.compile(''citationAction='');
|
||
|
||
var tableRows = doc.evaluate(''/html/body/div[@class="indent"]/table/tbody/tr[td/span[@class="printDownloadSaveLinks"]]'', doc, nsResolver, XPathResult.ANY_TYPE, null);
|
||
var tableRow;
|
||
// Go through table rows
|
||
var tableView = new Array();
|
||
var tableSave = new Array();
|
||
var i = 0;
|
||
while(tableRow = tableRows.iterateNext()) {
|
||
i++;
|
||
var links = tableRow.getElementsByTagName("a");
|
||
// Go through links
|
||
for(var j=0; j<links.length; j++) {
|
||
if(links[j].href.indexOf("citationAction=") != -1) {
|
||
tableSave[i] = links[j].href;
|
||
var link = doc.evaluate(''.//a[strong]'', tableRow, null, XPathResult.ANY_TYPE, null).iterateNext();
|
||
if(link) {
|
||
tableView[i] = link.href;
|
||
}
|
||
|
||
var text = doc.evaluate(''.//strong/text()'', tableRow, null, XPathResult.ANY_TYPE, null).iterateNext();
|
||
if(text && text.nodeValue) {
|
||
text = Scholar.Utilities.cleanString(text.nodeValue);
|
||
if(availableItems[i]) {
|
||
availableItems[i] += " "+text;
|
||
} else {
|
||
availableItems[i] = text;
|
||
}
|
||
}
|
||
}
|
||
}
|
||
}
|
||
|
||
var items = Scholar.selectItems(availableItems);
|
||
if(!items) {
|
||
return true;
|
||
}
|
||
|
||
for(var i in items) {
|
||
viewPages.push(tableView[i]);
|
||
saveCitations.push(tableSave[i].replace(''citationAction=remove'', ''citationAction=save''));
|
||
}
|
||
} else {
|
||
// If this is a view page, find the link to the citation
|
||
var xpath = ''/html/body/div[@class="indent"]/center//a[@class="nav"]'';
|
||
var elmts = doc.evaluate(xpath, doc, nsResolver, XPathResult.ANY_TYPE, null);
|
||
var saveCitation = elmts.iterateNext();
|
||
var viewSavedCitations = elmts.iterateNext();
|
||
|
||
if(saveCitation && viewSavedCitations) {
|
||
viewPages.push(url);
|
||
saveCitations.push(saveCitation.href.replace(''citationAction=remove'', ''citationAction=save''));
|
||
} else {
|
||
throw("Could not find citation save links");
|
||
}
|
||
}
|
||
|
||
Scholar.Utilities.HTTP.doGet(''http://www.jstor.org/browse?citationAction=removeAll&confirmRemAll=on&viewCitations=1'', function() { // clear marked
|
||
// Mark all our citations
|
||
getList(saveCitations, null, function() { // mark this
|
||
Scholar.Utilities.HTTP.doGet(''http://www.jstor.org/browse/citations.txt?exportAction=Save+as+Text+File&exportFormat=cm&viewCitations=1'', function(text) {
|
||
// get marked
|
||
Scholar.Utilities.debug(text);
|
||
var k = 0;
|
||
var lines = text.split("\n");
|
||
var haveStarted = false;
|
||
var newItemRe = /^<[0-9]+>/;
|
||
|
||
var newItem = new Scholar.Item("journalArticle");
|
||
newItem.attachments.push(getJSTORAttachment(viewPages[k]));
|
||
|
||
for(var i in lines) {
|
||
if(lines[i].substring(0,3) == "<1>") {
|
||
haveStarted = true;
|
||
} else if(newItemRe.test(lines[i])) {
|
||
itemComplete(newItem, url);
|
||
k++;
|
||
|
||
newItem = new Scholar.Item("journalArticle");
|
||
newItem.attachments.push(getJSTORAttachment(viewPages[k]));
|
||
} else if(lines[i].substring(2, 5) == " : " && haveStarted) {
|
||
var fieldCode = lines[i].substring(0, 2);
|
||
var fieldContent = Scholar.Utilities.cleanString(lines[i].substring(5))
|
||
|
||
if(fieldCode == "TI") {
|
||
if(fieldContent) {
|
||
newItem.title = fieldContent;
|
||
} else {
|
||
newItem.title = "[untitled]";
|
||
}
|
||
} else if(fieldCode == "AU") {
|
||
var authors = fieldContent.split(";");
|
||
for(j in authors) {
|
||
if(authors[j]) {
|
||
newItem.creators.push(Scholar.Utilities.cleanAuthor(authors[j], "author", true));
|
||
}
|
||
}
|
||
} else if(fieldCode == "SO") {
|
||
newItem.publicationTitle = fieldContent;
|
||
} else if(fieldCode == "VO") {
|
||
newItem.volume = fieldContent;
|
||
} else if(fieldCode == "NO") {
|
||
newItem.issue = fieldContent;
|
||
} else if(fieldCode == "SE") {
|
||
newItem.seriesTitle = fieldContent;
|
||
} else if(fieldCode == "DA") {
|
||
var date = new Date(fieldContent.replace(".", ""));
|
||
if(isNaN(date.valueOf())) {
|
||
newItem.date = fieldContent;
|
||
} else {
|
||
newItem.date = Scholar.Utilities.dateToSQL(date);
|
||
}
|
||
} else if(fieldCode == "PP") {
|
||
newItem.pages = fieldContent;
|
||
} else if(fieldCode == "EI") {
|
||
newItem.url = fieldContent;
|
||
} else if(fieldCode == "IN") {
|
||
newItem.ISSN = fieldContent;
|
||
} else if(fieldCode == "PB") {
|
||
newItem.publisher = fieldContent;
|
||
}
|
||
}
|
||
}
|
||
|
||
// last item is complete
|
||
if(haveStarted) {
|
||
itemComplete(newItem, url);
|
||
}
|
||
|
||
Scholar.done();
|
||
});
|
||
});
|
||
});
|
||
|
||
Scholar.wait();
|
||
}');
|
||
|
||
REPLACE INTO "translators" VALUES ('e85a3134-8c1a-8644-6926-584c8565f23e', '2006-06-26 16:01:00', 4, 'History Cooperative', 'Simon Kornblith', '^http://www\.historycooperative\.org/(?:journals/.+/.+/.+\.s?html$|cgi-bin/search.cgi)',
|
||
'function detectWeb(doc, url) {
|
||
if(doc.title == "History Cooperative: Search Results") {
|
||
return "multiple";
|
||
} else {
|
||
return "journalArticle";
|
||
}
|
||
}',
|
||
'function associateMeta(newItem, metaTags, field, scholarField) {
|
||
var field = metaTags.namedItem(field);
|
||
if(field) {
|
||
newItem[scholarField] = field.getAttribute("content");
|
||
}
|
||
}
|
||
|
||
function scrape(doc) {
|
||
var newItem = new Scholar.Item("journalArticle");
|
||
newItem.url = doc.location.href;
|
||
|
||
var month, year;
|
||
var metaTags = doc.getElementsByTagName("meta");
|
||
associateMeta(newItem, metaTags, "Title", "title");
|
||
associateMeta(newItem, metaTags, "Journal", "publicationTitle");
|
||
associateMeta(newItem, metaTags, "Volume", "volume");
|
||
associateMeta(newItem, metaTags, "Issue", "issue");
|
||
|
||
var author = metaTags.namedItem("Author");
|
||
if(author) {
|
||
var authors = author.getAttribute("content").split(" and ");
|
||
for(j in authors) {
|
||
newItem.creators.push(Scholar.Utilities.cleanAuthor(authors[j], "author"));
|
||
}
|
||
}
|
||
|
||
newItem.attachments.push({document:doc, title:"History Cooperative Full Text",
|
||
downloadable:true});
|
||
|
||
newItem.complete();
|
||
|
||
// don''t actually need date info for a journal article
|
||
var month = metaTags.namedItem("PublicationMonth");
|
||
var year = metaTags.namedItem("PublicationYear");
|
||
if(month && year) {
|
||
newItem.date = month.getAttribute("content")+" "+year.getAttribute("content");
|
||
}
|
||
}
|
||
|
||
function doWeb(doc, url) {
|
||
if(doc.title == "History Cooperative: Search Results") {
|
||
var items = Scholar.Utilities.getItemArray(doc, doc, ''^http://[^/]+/journals/.+/.+/.+\.html$'');
|
||
items = Scholar.selectItems(items);
|
||
|
||
if(!items) {
|
||
return true;
|
||
}
|
||
|
||
var uris = new Array();
|
||
for(var i in items) {
|
||
uris.push(i);
|
||
}
|
||
|
||
Scholar.Utilities.processDocuments(uris, function(doc) { scrape(doc) },
|
||
function() { Scholar.done(); }, null);
|
||
|
||
Scholar.wait();
|
||
} else {
|
||
scrape(doc);
|
||
}
|
||
}');
|
||
|
||
REPLACE INTO "translators" VALUES ('4fd6b89b-2316-2dc4-fd87-61a97dd941e8', '2006-08-06 21:45:00', 4, 'InnoPAC', 'Simon Kornblith', '^http://[^/]+/(?:search/|record=)',
|
||
'function detectWeb(doc, url) {
|
||
// First, check to see if the URL alone reveals InnoPAC, since some sites don''t reveal the MARC button
|
||
var matchRegexp = new RegExp(''^(http://[^/]+/search/[^/]+/[^/]+/1\%2C[^/]+/)frameset(.+)$'');
|
||
if(matchRegexp.test(doc.location.href)) {
|
||
return "book";
|
||
}
|
||
// Next, look for the MARC button
|
||
var namespace = doc.documentElement.namespaceURI;
|
||
var nsResolver = namespace ? function(prefix) {
|
||
if (prefix == ''x'') return namespace; else return null;
|
||
} : null;
|
||
|
||
var xpath = ''//a[img[@src="/screens/marcdisp.gif" or @alt="MARC Display" or @src="/screens/regdisp.gif" or @alt="REGULAR RECORD DISPLAY"]]'';
|
||
var elmt = doc.evaluate(xpath, doc, nsResolver, XPathResult.ANY_TYPE, null).iterateNext();
|
||
if(elmt) {
|
||
return "book";
|
||
}
|
||
// Also, check for links to an item display page
|
||
var tags = doc.getElementsByTagName("a");
|
||
for(var i=0; i<tags.length; i++) {
|
||
if(matchRegexp.test(tags[i].href)) {
|
||
return "multiple";
|
||
}
|
||
}
|
||
|
||
return false;
|
||
}',
|
||
'function scrape(marc, newDoc) {
|
||
var namespace = newDoc.documentElement.namespaceURI;
|
||
var nsResolver = namespace ? function(prefix) {
|
||
if (prefix == ''x'') return namespace; else return null;
|
||
} : null;
|
||
|
||
var xpath = ''//pre/text()[1]'';
|
||
var text = newDoc.evaluate(xpath, newDoc, nsResolver,
|
||
XPathResult.ANY_TYPE, null).iterateNext().nodeValue;
|
||
var newItem = new Scholar.Item();
|
||
|
||
var record = new marc.MARC_Record();
|
||
|
||
var linee = text.split("\n");
|
||
for (var i=0; i<linee.length; i++) {
|
||
linee[i] = linee[i].replace(/\xA0|_|\t/g,'' '');
|
||
if (linee[i] == '''') continue; // jumps empty lines
|
||
var replacer = record.subfield_delimiter+''$1'';
|
||
linee[i] = linee[i].replace(/\|(.)/g,replacer);
|
||
linee[i] = linee[i].replace(/\|/g,this.subfield_delimiter);
|
||
var tag = linee[i].substr(0,3);
|
||
var ind1 = linee[i].substr(4,1);
|
||
var ind2 = linee[i].substr(5,1);
|
||
var value = record.subfield_delimiter+''a''+linee[i].substr(7);
|
||
if(linee[i].substr(0, 6) == "LEADER") {
|
||
value = linee[i].substr(7);
|
||
record.leader.record_length = ''00000'';
|
||
record.leader.record_status = value.substr(5,1);
|
||
record.leader.type_of_record = value.substr(6,1);
|
||
record.leader.bibliographic_level = value.substr(7,1);
|
||
record.leader.type_of_control = value.substr(8,1);
|
||
record.leader.character_coding_scheme = value.substr(9,1);
|
||
record.leader.indicator_count = ''2'';
|
||
record.leader.subfield_code_length = ''2'';
|
||
record.leader.base_address_of_data = ''00000'';
|
||
record.leader.encoding_level = value.substr(17,1);
|
||
record.leader.descriptive_cataloging_form = value.substr(18,1);
|
||
record.leader.linked_record_requirement = value.substr(19,1);
|
||
record.leader.entry_map = ''4500'';
|
||
|
||
record.directory = '''';
|
||
record.directory_terminator = record.field_terminator;
|
||
record.variable_fields = new Array();
|
||
}
|
||
else if (tag > ''008'' && tag < ''899'') { // jumps low and high tags
|
||
if (tag != ''040'') record.add_field(tag,ind1,ind2,value);
|
||
}
|
||
}
|
||
|
||
record.translate(newItem);
|
||
newItem.complete();
|
||
}
|
||
|
||
function pageByPage(marc, urls) {
|
||
Scholar.Utilities.processDocuments(urls, function(newDoc) {
|
||
scrape(marc, newDoc);
|
||
}, function() { Scholar.done() });
|
||
}
|
||
|
||
function doWeb(doc, url) {
|
||
var uri = doc.location.href;
|
||
var newUri;
|
||
|
||
// load translator for MARC
|
||
var marc = Scholar.loadTranslator("import", "a6ee60df-1ddc-4aae-bb25-45e0537be973");
|
||
|
||
var matchRegexp = new RegExp(''^(http://[^/]+/search/[^/]+/[^/]+/1\%2C[^/]+/)frameset(.+)$'');
|
||
var m = matchRegexp.exec(uri);
|
||
if(m) {
|
||
newUri = m[1]+''marc''+m[2];
|
||
} else {
|
||
var namespace = doc.documentElement.namespaceURI;
|
||
var nsResolver = namespace ? function(prefix) {
|
||
if (prefix == ''x'') return namespace; else return null;
|
||
} : null;
|
||
|
||
var xpath = ''//a[img[@src="/screens/marcdisp.gif" or @alt="MARC Display"]]'';
|
||
var aTag = doc.evaluate(xpath, doc, nsResolver, XPathResult.ANY_TYPE, null).iterateNext();
|
||
if(aTag) {
|
||
newUri = aTag.href;
|
||
} else {
|
||
var xpath = ''//a[img[@src="/screens/regdisp.gif" or @alt="REGULAR RECORD DISPLAY"]]'';
|
||
var aTag = doc.evaluate(xpath, doc, nsResolver, XPathResult.ANY_TYPE, null).iterateNext();
|
||
if(aTag) {
|
||
scrape(marc, doc);
|
||
return;
|
||
}
|
||
}
|
||
}
|
||
|
||
if(newUri) { // single page
|
||
pageByPage(marc, [newUri]);
|
||
} else { // Search results page
|
||
// Require link to match this
|
||
var tagRegexp = new RegExp();
|
||
tagRegexp.compile(''^http://[^/]+/search/[^/]+/[^/]+/1\%2C[^/]+/frameset'');
|
||
|
||
var checkboxes = new Array();
|
||
var urls = new Array();
|
||
var availableItems = new Array();
|
||
|
||
var tableRows = doc.evaluate(''//table[@class="browseScreen"]//tr[@class="browseEntry" or @class="briefCitRow" or td/input[@type="checkbox"]]'',
|
||
doc, nsResolver, XPathResult.ANY_TYPE, null);
|
||
// Go through table rows
|
||
var i = 0;
|
||
while(tableRow = tableRows.iterateNext()) {
|
||
Scholar.Utilities.debug("row");
|
||
// CHK is what we need to get it all as one file
|
||
var input = doc.evaluate(''./td/input[@type="checkbox"]'', tableRow,
|
||
nsResolver, XPathResult.ANY_TYPE, null).iterateNext();
|
||
if(input) {
|
||
checkboxes[i] = input.name+"="+escape(input.value);
|
||
}
|
||
|
||
// get link
|
||
var links = doc.evaluate(''.//span[@class="briefcitTitle"]/a'', tableRow,
|
||
nsResolver, XPathResult.ANY_TYPE, null);
|
||
var link = links.iterateNext();
|
||
if(!link) {
|
||
var links = doc.evaluate(".//a", tableRow, nsResolver,
|
||
XPathResult.ANY_TYPE, null);
|
||
link = links.iterateNext();
|
||
}
|
||
|
||
if(link) {
|
||
urls[i] = link.href;
|
||
// Go through links
|
||
while(link) {
|
||
if(tagRegexp.test(link.href)) {
|
||
Scholar.Utilities.debug("hello");
|
||
var text = Scholar.Utilities.getNodeString(doc, link,
|
||
".//text()", null);
|
||
if(text) {
|
||
text = Scholar.Utilities.cleanString(text);
|
||
if(availableItems[i]) {
|
||
availableItems[i] += " "+text;
|
||
} else {
|
||
availableItems[i] = text;
|
||
}
|
||
}
|
||
}
|
||
link = links.iterateNext();
|
||
}
|
||
}
|
||
|
||
i++;
|
||
};
|
||
|
||
var items = Scholar.selectItems(availableItems);
|
||
|
||
if(!items) {
|
||
return true;
|
||
}
|
||
|
||
var urlRe = new RegExp("^(http://[^/]+(/search/[^/]+/))");
|
||
var m = urlRe.exec(urls[0]);
|
||
var clearUrl = m[0]+"?clear_saves=1";
|
||
var postUrl = m[0];
|
||
var exportUrl = m[1]+"++export/1,-1,-1,B/export";
|
||
|
||
var newUrls = new Array();
|
||
var postString = "";
|
||
var number = 0;
|
||
for(var i in items) {
|
||
if(checkboxes[i]) {
|
||
postString += checkboxes[i]+"&";
|
||
number++;
|
||
}
|
||
var m = matchRegexp.exec(urls[i]);
|
||
newUrls.push(m[1]+"marc"+m[2]);
|
||
}
|
||
|
||
if(postString && number > 1) {
|
||
postString += "save_func=save_marked";
|
||
|
||
|
||
Scholar.Utilities.HTTP.doGet(clearUrl, function() {
|
||
Scholar.Utilities.HTTP.doPost(postUrl, postString, function() {
|
||
Scholar.Utilities.HTTP.doPost(exportUrl, "ex_format=50&ex_device=45&SUBMIT=Submit", function(text) {
|
||
var notSpace = /[^\s]/
|
||
if(notSpace.test(text)) {
|
||
marc.Scholar.write(text);
|
||
marc.Scholar.eof();
|
||
marc.doImport();
|
||
|
||
Scholar.done();
|
||
} else {
|
||
pageByPage(marc, newUrls);
|
||
}
|
||
});
|
||
});
|
||
});
|
||
} else {
|
||
pageByPage(marc, newUrls);
|
||
}
|
||
}
|
||
|
||
Scholar.wait();
|
||
}');
|
||
|
||
REPLACE INTO "translators" VALUES ('add7c71c-21f3-ee14-d188-caf9da12728b', '2006-06-26 16:01:00', 4, 'SIRSI 2003+', 'Simon Kornblith', '/uhtbin/cgisirsi',
|
||
'function detectWeb(doc, url) {
|
||
var namespace = doc.documentElement.namespaceURI;
|
||
var nsResolver = namespace ? function(prefix) {
|
||
if (prefix == ''x'') return namespace; else return null;
|
||
} : null;
|
||
|
||
var xpath = ''//tr[th[@class="viewmarctags"]][td[@class="viewmarctags"]]'';
|
||
if(doc.evaluate(xpath, doc, nsResolver, XPathResult.ANY_TYPE, null).iterateNext()) {
|
||
return "book";
|
||
}
|
||
var xpath = ''//td[@class="searchsum"]/table'';
|
||
if(doc.evaluate(xpath, doc, nsResolver, XPathResult.ANY_TYPE, null).iterateNext()) {
|
||
return "multiple";
|
||
}
|
||
}',
|
||
'function scrape(doc) {
|
||
var namespace = doc.documentElement.namespaceURI;
|
||
var nsResolver = namespace ? function(prefix) {
|
||
if (prefix == ''x'') return namespace; else return null;
|
||
} : null;
|
||
|
||
var xpath = ''//tr[th[@class="viewmarctags"]][td[@class="viewmarctags"]]'';
|
||
var elmts = doc.evaluate(xpath, doc, nsResolver, XPathResult.ANY_TYPE, null);
|
||
var elmt = elmts.iterateNext();
|
||
if(!elmt) {
|
||
return false;
|
||
}
|
||
|
||
var newItem = new Scholar.Item("book");
|
||
newItem.extra = "";
|
||
|
||
while(elmt) {
|
||
try {
|
||
var node = doc.evaluate(''./TD[1]/A[1]/text()[1]'', elmt, nsResolver, XPathResult.ANY_TYPE, null).iterateNext();
|
||
if(!node) {
|
||
var node = doc.evaluate(''./TD[1]/text()[1]'', elmt, nsResolver, XPathResult.ANY_TYPE, null).iterateNext();
|
||
}
|
||
|
||
if(node) {
|
||
var casedField = Scholar.Utilities.superCleanString(doc.evaluate(''./TH[1]/text()[1]'', elmt, nsResolver, XPathResult.ANY_TYPE, null).iterateNext().nodeValue);
|
||
field = casedField.toLowerCase();
|
||
var value = Scholar.Utilities.superCleanString(node.nodeValue);
|
||
if(field == "publisher") {
|
||
newItem.publisher = value;
|
||
} else if(field == "pub date") {
|
||
var re = /[0-9]+/;
|
||
var m = re.exec(value);
|
||
newItem.date = m[0];
|
||
} else if(field == "isbn") {
|
||
var re = /^[0-9](?:[0-9X]+)/;
|
||
var m = re.exec(value);
|
||
newItem.ISBN = m[0];
|
||
} else if(field == "title") {
|
||
var titleParts = value.split(" / ");
|
||
newItem.title = titleParts[0];
|
||
} else if(field == "publication info") {
|
||
var pubParts = value.split(" : ");
|
||
newItem.place = pubParts[0];
|
||
} else if(field == "personal author") {
|
||
newItem.creators.push(Scholar.Utilities.cleanAuthor(value, "author", true));
|
||
} else if(field == "added author") {
|
||
newItem.creators.push(Scholar.Utilities.cleanAuthor(value, "contributor", true));
|
||
} else if(field == "corporate author") {
|
||
newItem.creators.push({lastName:author});
|
||
} else if(field == "subject term" || field == "corporate subject" || field == "geographic term") {
|
||
var subjects = value.split("--");
|
||
newItem.tags = newItem.tags.concat(subjects);
|
||
} else if(field == "personal subject") {
|
||
var subjects = value.split(", ");
|
||
newItem.tags = newItem.tags.push(value[0]+", "+value[1]);
|
||
} else if(value && field != "http") {
|
||
newItem.extra += casedField+": "+value+"\n";
|
||
}
|
||
}
|
||
} catch (e) {}
|
||
|
||
elmt = elmts.iterateNext();
|
||
}
|
||
|
||
if(newItem.extra) {
|
||
newItem.extra = newItem.extra.substr(0, newItem.extra.length-1);
|
||
}
|
||
|
||
var callNumber = doc.evaluate(''//tr/td[1][@class="holdingslist"]/text()'', doc, nsResolver, XPathResult.ANY_TYPE, null).iterateNext();
|
||
if(callNumber && callNumber.nodeValue) {
|
||
newItem.callNumber = callNumber.nodeValue;
|
||
}
|
||
|
||
newItem.complete();
|
||
return true;
|
||
}
|
||
|
||
function doWeb(doc, url) {
|
||
var namespace = doc.documentElement.namespaceURI;
|
||
var nsResolver = namespace ? function(prefix) {
|
||
if (prefix == ''x'') return namespace; else return null;
|
||
} : null;
|
||
|
||
if(!scrape(doc)) {
|
||
var checkboxes = new Array();
|
||
var urls = new Array();
|
||
var availableItems = new Array();
|
||
|
||
var tableRows = doc.evaluate(''//td[@class="searchsum"]/table[//input[@value="Details"]]'', doc, nsResolver, XPathResult.ANY_TYPE, null);
|
||
var tableRow = tableRows.iterateNext(); // skip first row
|
||
// Go through table rows
|
||
while(tableRow = tableRows.iterateNext()) {
|
||
var input = doc.evaluate(''.//input[@value="Details"]'', tableRow, nsResolver, XPathResult.ANY_TYPE, null).iterateNext();
|
||
var text = Scholar.Utilities.getNodeString(doc, tableRow, ''.//label/strong//text()'', nsResolver);
|
||
if(text) {
|
||
availableItems[input.name] = text;
|
||
}
|
||
}
|
||
|
||
var items = Scholar.selectItems(availableItems);
|
||
|
||
if(!items) {
|
||
return true;
|
||
}
|
||
|
||
var hostRe = new RegExp("^http://[^/]+");
|
||
var m = hostRe.exec(doc.location.href);
|
||
var hitlist = doc.forms.namedItem("hitlist");
|
||
var baseUrl = m[0]+hitlist.getAttribute("action")+"?first_hit="+hitlist.elements.namedItem("first_hit").value+"&last_hit="+hitlist.elements.namedItem("last_hit").value;
|
||
Scholar.Utilities.debug(baseUrl);
|
||
|
||
var uris = new Array();
|
||
for(var i in items) {
|
||
uris.push(baseUrl+"&"+i+"=Details");
|
||
}
|
||
|
||
Scholar.Utilities.processDocuments(uris, function(doc) { scrape(doc) },
|
||
function() { Scholar.done() }, null);
|
||
|
||
Scholar.wait();
|
||
}
|
||
}');
|
||
|
||
REPLACE INTO "translators" VALUES ('a77690cf-c5d1-8fc4-110f-d1fc765dcf88', '2006-06-26 16:01:00', 4, 'ProQuest', 'Simon Kornblith', '^http://proquest\.umi\.com/pqdweb\?((?:.*\&)?did=.*&Fmt=[0-9]|(?:.*\&)Fmt=[0-9].*&did=|(?:.*\&)searchInterface=)',
|
||
'function detectWeb(doc, url) {
|
||
if(doc.title == "Results") {
|
||
return "multiple";
|
||
} else {
|
||
return "magazineArticle";
|
||
}
|
||
}',
|
||
'function scrape(doc) {
|
||
Scholar.Utilities.debug("hello");
|
||
|
||
var namespace = doc.documentElement.namespaceURI;
|
||
var nsResolver = namespace ? function(prefix) {
|
||
if (prefix == ''x'') return namespace; else return null;
|
||
} : null;
|
||
|
||
var newItem = new Scholar.Item();
|
||
var elmt;
|
||
|
||
// Title
|
||
var xpath = ''/html/body/span[@class="textMedium"]/table/tbody/tr/td[@class="headerBlack"]/strong//text()'';
|
||
newItem.title = Scholar.Utilities.getNodeString(doc, doc, xpath, nsResolver);
|
||
|
||
// Authors
|
||
var xpath = ''/html/body/span[@class="textMedium"]/table/tbody/tr/td[@class="textMedium"]/a/em'';
|
||
var elmts = doc.evaluate(xpath, doc, nsResolver, XPathResult.ANY_TYPE, null);
|
||
while(elmt = elmts.iterateNext()) {
|
||
// there are sometimes additional tags representing higlighting
|
||
var author = Scholar.Utilities.getNodeString(doc, elmt, ''.//text()'', nsResolver);
|
||
if(author) {
|
||
newItem.creators.push(Scholar.Utilities.cleanAuthor(author, "author", true));
|
||
}
|
||
}
|
||
|
||
// Other info
|
||
var xpath = ''/html/body/span[@class="textMedium"]/font/table/tbody/tr'';
|
||
var elmts = doc.evaluate(xpath, doc, nsResolver, XPathResult.ANY_TYPE, null);
|
||
while(elmt = elmts.iterateNext()) {
|
||
var field = Scholar.Utilities.superCleanString(doc.evaluate(''./TD[1]/text()[1]'', elmt, nsResolver, XPathResult.ANY_TYPE, null).iterateNext().nodeValue).toLowerCase();
|
||
if(field == "publication title") {
|
||
var publication = doc.evaluate(''./TD[2]/A[1]/text()[1]'', elmt, nsResolver, XPathResult.ANY_TYPE, null).iterateNext();
|
||
if(publication.nodeValue) {
|
||
newItem.publicationTitle = Scholar.Utilities.superCleanString(publication.nodeValue);
|
||
}
|
||
|
||
var place = doc.evaluate(''./TD[2]/text()[1]'', elmt, nsResolver, XPathResult.ANY_TYPE, null).iterateNext();
|
||
if(place.nodeValue) {
|
||
newItem.place = Scholar.Utilities.superCleanString(place.nodeValue);
|
||
}
|
||
|
||
var date = doc.evaluate(''./TD[2]/A[2]/text()[1]'', elmt, nsResolver, XPathResult.ANY_TYPE, null).iterateNext();
|
||
if(date.nodeValue) {
|
||
date = date.nodeValue;
|
||
var jsDate = new Date(Scholar.Utilities.superCleanString(date));
|
||
if(!isNaN(jsDate.valueOf())) {
|
||
date = Scholar.Utilities.dateToSQL(jsDate);
|
||
}
|
||
newItem.date = date;
|
||
}
|
||
|
||
var moreInfo = doc.evaluate(''./TD[2]/text()[2]'', elmt, nsResolver, XPathResult.ANY_TYPE, null).iterateNext();
|
||
if(moreInfo.nodeValue) {
|
||
moreInfo = Scholar.Utilities.superCleanString(moreInfo.nodeValue);
|
||
var parts = moreInfo.split(";\xA0");
|
||
|
||
var issueRegexp = /^(\w+)\.(?: |\xA0)?(.+)$/
|
||
var issueInfo = parts[0].split(",\xA0");
|
||
for(j in issueInfo) {
|
||
var m = issueRegexp.exec(issueInfo[j]);
|
||
if(m) {
|
||
var info = m[1].toLowerCase();
|
||
if(info == "vol") {
|
||
newItem.volume = Scholar.Utilities.superCleanString(m[2]);
|
||
} else if(info == "iss" || info == "no") {
|
||
newItem.issue = Scholar.Utilities.superCleanString(m[2]);
|
||
}
|
||
}
|
||
}
|
||
if(parts[1] && Scholar.Utilities.superCleanString(parts[1]).substring(0, 3).toLowerCase() == "pg.") {
|
||
var re = /[0-9\-]+/;
|
||
var m = re.exec(parts[1]);
|
||
|
||
if(m) {
|
||
newItem.pages = m[0];
|
||
}
|
||
}
|
||
}
|
||
} else if(field == "source type") {
|
||
var value = doc.evaluate(''./TD[2]/text()[1]'', elmt, nsResolver, XPathResult.ANY_TYPE, null).iterateNext();
|
||
if(value.nodeValue) {
|
||
value = Scholar.Utilities.superCleanString(value.nodeValue).toLowerCase();
|
||
Scholar.Utilities.debug(value);
|
||
|
||
if(value.indexOf("periodical") >= 0) {
|
||
newItem.itemType = "magazineArticle";
|
||
} else if(value.indexOf("newspaper") >= 0) {
|
||
newItem.itemType = "newspaperArticle";
|
||
} else { // TODO: support thesis
|
||
newItem.itemType = "book";
|
||
}
|
||
}
|
||
} else if(field == "isbn" || field == "issn" || field == "issn/isbn") {
|
||
var value = doc.evaluate(''./TD[2]/text()[1]'', elmt, nsResolver, XPathResult.ANY_TYPE, null).iterateNext();
|
||
if(value) {
|
||
var type;
|
||
value = Scholar.Utilities.superCleanString(value.nodeValue);
|
||
if(value.length == 10 || value.length == 13) {
|
||
newItem.ISBN = value;
|
||
} else if(value.length == 8) {
|
||
newItem.ISSN = value;
|
||
}
|
||
}
|
||
} else if(field == "document url") {
|
||
var value = doc.evaluate(''./TD[2]/text()[1]'', elmt, nsResolver, XPathResult.ANY_TYPE, null).iterateNext();
|
||
if(value) {
|
||
newItem.url = Scholar.Utilities.cleanString(value.nodeValue);
|
||
}
|
||
} else if(field == "proquest document id") {
|
||
var value = doc.evaluate(''./TD[2]/text()[1]'', elmt, nsResolver, XPathResult.ANY_TYPE, null).iterateNext();
|
||
if(value) {
|
||
newItem.accessionNumber = Scholar.Utilities.cleanString(value.nodeValue);
|
||
}
|
||
} else if(field == "subjects" || field == "people" || field == "locations") {
|
||
var subjects = doc.evaluate(".//a", elmt, nsResolver, XPathResult.ANY_TYPE, null);
|
||
var currentSubject;
|
||
while(currentSubject = subjects.iterateNext()) {
|
||
var subjectValue = Scholar.Utilities.getNodeString(doc, currentSubject, ".//text()", nsResolver);
|
||
subjectValue = Scholar.Utilities.superCleanString(subjectValue);
|
||
Scholar.Utilities.debug("tag: "+subjectValue);
|
||
if(subjectValue) {
|
||
newItem.tags.push(subjectValue);
|
||
}
|
||
}
|
||
}
|
||
}
|
||
|
||
// magazineArticle -> journalArticle if issue and volume exist
|
||
if(newItem.itemType == "magazineArticle" && (newItem.issue || newItem.volume)) {
|
||
newItem.itemType = "journalArticle";
|
||
}
|
||
|
||
// figure out what we can attach
|
||
var attachArray = {
|
||
''//td[@class="textSmall"]//img[@alt="Full Text - PDF"]'':"ProQuest Full Text (PDF)",
|
||
''//td[@class="textSmall"]//img[@alt="Text+Graphics"]'':"ProQuest Full Text (HTML with Graphics)",
|
||
''//td[@class="textSmall"]//img[@alt="Full Text"]'':"ProQuest Full Text (HTML)",
|
||
''//td[@class="textSmall"]//img[@alt="Abstract"]'':"ProQuest Abstract"
|
||
}
|
||
for(var xpath in attachArray) {
|
||
var item = doc.evaluate(xpath, doc, nsResolver, XPathResult.ANY_TYPE, null).iterateNext();
|
||
if(item) {
|
||
var title = attachArray[xpath];
|
||
Scholar.Utilities.debug(title);
|
||
|
||
if(item.parentNode.tagName.toLowerCase() == "a") {
|
||
// item is not this page
|
||
newItem.attachments.push({url:item.parentNode.href,
|
||
title:title, mimeType:(title == "ProQuest Full Text (PDF)" ? "application/pdf" : "text/html"),
|
||
downloadable:true});
|
||
} else {
|
||
// item is this page
|
||
newItem.attachments.push({document:doc, title:title, downloadable:true});
|
||
}
|
||
}
|
||
}
|
||
|
||
newItem.complete();
|
||
}
|
||
|
||
function doWeb(doc, url) {
|
||
var namespace = doc.documentElement.namespaceURI;
|
||
var nsResolver = namespace ? function(prefix) {
|
||
if (prefix == ''x'') return namespace; else return null;
|
||
} : null;
|
||
|
||
if(doc.title == "Results") {
|
||
var items = new Object();
|
||
|
||
// Require link to match this
|
||
var tagRegexp = new RegExp();
|
||
tagRegexp.compile(''^http://[^/]+/pqdweb\\?((?:.*&)?did=.*&Fmt=[12]|(?:.*&)Fmt=[12].*&did=)'');
|
||
|
||
var tableRows = doc.evaluate(''//tr[@class="rowUnMarked"]'',
|
||
doc, nsResolver, XPathResult.ANY_TYPE, null);
|
||
// Go through table rows
|
||
var tableRow;
|
||
while(tableRow = tableRows.iterateNext()) {
|
||
var links = tableRow.getElementsByTagName("a");
|
||
// Go through links
|
||
for(var j=0; j<links.length; j++) {
|
||
if(tagRegexp.test(links[j].href)) {
|
||
var text = doc.evaluate(''.//a[@class="bold"]/text()'', tableRow, nsResolver, XPathResult.ANY_TYPE, null).iterateNext();
|
||
if(text && text.nodeValue) {
|
||
text = Scholar.Utilities.cleanString(text.nodeValue);
|
||
items[links[j].href] = text;
|
||
}
|
||
break;
|
||
}
|
||
}
|
||
}
|
||
items = Scholar.selectItems(items);
|
||
|
||
if(!items) {
|
||
return true;
|
||
}
|
||
|
||
var uris = new Array();
|
||
for(var i in items) {
|
||
uris.push(i);
|
||
}
|
||
|
||
Scholar.Utilities.processDocuments(uris, function(doc) { scrape(doc) },
|
||
function() { Scholar.done(); }, null);
|
||
|
||
Scholar.wait();
|
||
} else {
|
||
var fmtCheck = /(?:\&|\?)Fmt=([0-9]+)/i
|
||
var m = fmtCheck.exec(doc.location.href);
|
||
if(m && (m[1] == "1" || m[1] == "2" || m[1] == "3")) {
|
||
scrape(doc);
|
||
} else if(m) {
|
||
Scholar.Utilities.loadDocument(doc.location.href.replace("Fmt="+m[1], "Fmt=1"), function(doc) { scrape(doc); Scholar.done(); }, null);
|
||
Scholar.wait();
|
||
}
|
||
}
|
||
}');
|
||
|
||
REPLACE INTO "translators" VALUES ('6773a9af-5375-3224-d148-d32793884dec', '2006-06-26 16:01:00', 4, 'InfoTrac College Edition', 'Simon Kornblith', '^http://infotrac-college\.thomsonlearning\.com/itw/infomark/',
|
||
'function detectWeb(doc, url) {
|
||
if(doc.title.substring(0, 8) == "Article ") {
|
||
return "magazineArticle";
|
||
} else if(doc.title.substring(0, 10) == "Citations ") {
|
||
return "multiple";
|
||
}
|
||
}',
|
||
'function extractCitation(url, elmts, title, doc) {
|
||
var newItem = new Scholar.Item();
|
||
newItem.url = url;
|
||
|
||
if(title) {
|
||
newItem.title = Scholar.Utilities.superCleanString(title);
|
||
}
|
||
while(elmt = elmts.iterateNext()) {
|
||
var colon = elmt.nodeValue.indexOf(":");
|
||
var field = elmt.nodeValue.substring(1, colon).toLowerCase();
|
||
var value = elmt.nodeValue.substring(colon+1, elmt.nodeValue.length-1);
|
||
if(field == "title") {
|
||
newItem.title = Scholar.Utilities.superCleanString(value);
|
||
} else if(field == "journal") {
|
||
newItem.publicationTitle = value;
|
||
} else if(field == "pi") {
|
||
parts = value.split(" ");
|
||
var date = "";
|
||
var field = null;
|
||
for(j in parts) {
|
||
firstChar = parts[j].substring(0, 1);
|
||
|
||
if(firstChar == "v") {
|
||
newItem.itemType = "journalArticle";
|
||
field = "volume";
|
||
} else if(firstChar == "i") {
|
||
field = "issue";
|
||
} else if(firstChar == "p") {
|
||
field = "pages";
|
||
|
||
var pagesRegexp = /p(\w+)\((\w+)\)/; // weird looking page range
|
||
var match = pagesRegexp.exec(parts[j]);
|
||
if(match) { // yup, it''s weird
|
||
var finalPage = parseInt(match[1])+parseInt(match[2])
|
||
parts[j] = "p"+match[1]+"-"+finalPage.toString();
|
||
} else if(!newItem.itemType) { // no, it''s normal
|
||
// check to see if it''s numeric, bc newspaper pages aren''t
|
||
var justPageNumber = parts[j].substr(1);
|
||
if(parseInt(justPageNumber).toString() != justPageNumber) {
|
||
newItem.itemType = "newspaperArticle";
|
||
}
|
||
}
|
||
} else if(!field) { // date parts at the beginning, before
|
||
// anything else
|
||
date += " "+parts[j];
|
||
}
|
||
|
||
if(field) {
|
||
isDate = false;
|
||
|
||
if(parts[j] != "pNA") { // make sure it''s not an invalid
|
||
// page number
|
||
// chop of letter
|
||
newItem[field] = parts[j].substring(1);
|
||
} else if(!newItem.itemType) { // only newspapers are missing
|
||
// page numbers on infotrac
|
||
newItem.itemType = "newspaperArticle";
|
||
}
|
||
}
|
||
}
|
||
|
||
// Set type
|
||
if(!newItem.itemType) {
|
||
newItem.itemType = "magazineArticle";
|
||
}
|
||
|
||
if(date != "") {
|
||
newItem.date = date.substring(1);
|
||
}
|
||
} else if(field == "author") {
|
||
newItem.creators.push(Scholar.Utilities.cleanAuthor(value, "author", true));
|
||
}
|
||
}
|
||
|
||
if(doc) {
|
||
newItem.attachments.push({document:doc, title:"InfoTrac Full Text",
|
||
downloadable:true});
|
||
} else {
|
||
newItem.attachments.push({url:url, title:"InfoTrac Full Text",
|
||
mimeType:"text/html", downloadable:true});
|
||
}
|
||
|
||
newItem.complete();
|
||
}
|
||
|
||
function doWeb(doc, url) {
|
||
var namespace = doc.documentElement.namespaceURI;
|
||
var nsResolver = namespace ? function(prefix) {
|
||
if (prefix == ''x'') return namespace; else return null;
|
||
} : null;
|
||
|
||
var uri = doc.location.href;
|
||
if(doc.title.substring(0, 8) == "Article ") { // article
|
||
var xpath = ''/html/body//comment()'';
|
||
var elmts = doc.evaluate(xpath, doc, nsResolver, XPathResult.ANY_TYPE, null);
|
||
extractCitation(uri, elmts);
|
||
} else { // search results
|
||
var items = new Array();
|
||
var uris = new Array();
|
||
var elmts = new Array();
|
||
|
||
var tableRows = doc.evaluate(''/html/body//table/tbody/tr/td[a/b]'', doc, nsResolver,
|
||
XPathResult.ANY_TYPE, null);
|
||
var tableRow;
|
||
var javaScriptRe = /''([^'']*)'' *, *''([^'']*)''/
|
||
var i = 0;
|
||
// Go through table rows
|
||
while(tableRow = tableRows.iterateNext()) {
|
||
var link = doc.evaluate(''./a'', tableRow, nsResolver, XPathResult.ANY_TYPE, null).iterateNext();
|
||
var m = javaScriptRe.exec(link.href);
|
||
if(m) {
|
||
uris[i] = "http://infotrac-college.thomsonlearning.com/itw/infomark/192/215/90714844w6"+m[1]+"?sw_aep=olr_wad"+m[2];
|
||
}
|
||
var article = doc.evaluate(''./b/text()'', link, nsResolver, XPathResult.ANY_TYPE, null).iterateNext();
|
||
items[i] = article.nodeValue;
|
||
// Chop off final period
|
||
if(items[i].substr(items[i].length-1) == ".") {
|
||
items[i] = items[i].substr(0, items[i].length-1);
|
||
}
|
||
elmts[i] = doc.evaluate(".//comment()", tableRow, nsResolver, XPathResult.ANY_TYPE, null);
|
||
i++;
|
||
}
|
||
|
||
items = Scholar.selectItems(items);
|
||
|
||
if(!items) {
|
||
return true;
|
||
}
|
||
|
||
for(var i in items) {
|
||
extractCitation(uris[i], elmts[i], items[i]);
|
||
}
|
||
}
|
||
}');
|
||
|
||
REPLACE INTO "translators" VALUES ('b047a13c-fe5c-6604-c997-bef15e502b09', '2006-06-26 16:01:00', 4, 'LexisNexis', 'Simon Kornblith', '^http://web\.lexis-?nexis\.com/universe/(?:document|doclist)',
|
||
'function detectWeb(doc, url) {
|
||
var detailRe = new RegExp("^http://[^/]+/universe/document");
|
||
if(detailRe.test(doc.location.href)) {
|
||
return "newspaperArticle";
|
||
} else {
|
||
return "multiple";
|
||
}
|
||
}',
|
||
'function scrape(doc) {
|
||
var newItem = new Scholar.Item();
|
||
newItem.attachments.push({document:doc, title:"LexisNexis Full Text",
|
||
downloadable:true});
|
||
|
||
var citationDataDiv;
|
||
var divs = doc.getElementsByTagName("div");
|
||
for(var i=0; i<divs.length; i++) {
|
||
if(divs[i].className == "bodytext") {
|
||
citationDataDiv = divs[i];
|
||
break;
|
||
}
|
||
}
|
||
|
||
centerElements = citationDataDiv.getElementsByTagName("center");
|
||
var elementParts = centerElements[0].innerHTML.split(/<br[^>]*>/gi);
|
||
newItem.publicationTitle = elementParts[elementParts.length-1];
|
||
|
||
var dateRegexp = /<br[^>]*>(?:<b>)?([A-Z][a-z]+)(?:<\/b>)? ([0-9]+, [0-9]{4})/;
|
||
var m = dateRegexp.exec(centerElements[centerElements.length-1].innerHTML);
|
||
if(m) {
|
||
var jsDate = new Date(m[1]+" "+m[2]);
|
||
newItem.date = Scholar.Utilities.dateToSQL(jsDate);
|
||
} else {
|
||
var elementParts = centerElements[centerElements.length-1].innerHTML.split(/<br[^>]*>/gi);
|
||
newItem.date = elementParts[1];
|
||
}
|
||
|
||
var cutIndex = citationDataDiv.innerHTML.indexOf("<b>BODY:</b>");
|
||
if(cutIndex < 0) {
|
||
cutIndex = citationDataDiv.innerHTML.indexOf("<b>TEXT:</b>");
|
||
}
|
||
if(cutIndex > 0) {
|
||
citationData = citationDataDiv.innerHTML.substring(0, cutIndex);
|
||
} else {
|
||
citationData = citationDataDiv.innerHTML;
|
||
}
|
||
|
||
citationData = Scholar.Utilities.cleanTags(citationData);
|
||
|
||
var headlineRegexp = /\n(?:HEADLINE|TITLE|ARTICLE): ([^\n]+)\n/;
|
||
var m = headlineRegexp.exec(citationData);
|
||
if(m) {
|
||
newItem.title = Scholar.Utilities.cleanTags(m[1]);
|
||
}
|
||
|
||
var bylineRegexp = /\nBYLINE: *(\w[\w\- ]+)/;
|
||
var m = bylineRegexp.exec(citationData);
|
||
if(m) { // there is a byline; use it as an author
|
||
if(m[1].substring(0, 3).toLowerCase() == "by ") {
|
||
m[1] = m[1].substring(3);
|
||
}
|
||
newItem.creators.push(Scholar.Utilities.cleanAuthor(m[1], "author"));
|
||
|
||
newItem.itemType = "newspaperArticle";
|
||
} else { // no byline; must be a journal
|
||
newItem.itemType = "journalArticle";
|
||
}
|
||
|
||
// other ways authors could be encoded
|
||
var authorRegexp = /\n(?:AUTHOR|NAME): ([^\n]+)\n/;
|
||
var m = authorRegexp.exec(citationData);
|
||
if(m) {
|
||
var authors = m[1].split(/, (?:and )?/);
|
||
for(var i in authors) {
|
||
newItem.creators.push(Scholar.Utilities.cleanAuthor(authors[i].replace(" *", ""), "author"));
|
||
}
|
||
}
|
||
|
||
newItem.complete();
|
||
}
|
||
|
||
function doWeb(doc, url) {
|
||
var detailRe = new RegExp("^http://[^/]+/universe/document");
|
||
if(detailRe.test(doc.location.href)) {
|
||
scrape(doc);
|
||
} else {
|
||
var items = Scholar.Utilities.getItemArray(doc, doc, "^http://[^/]+/universe/document");
|
||
items = Scholar.selectItems(items);
|
||
|
||
if(!items) {
|
||
return true;
|
||
}
|
||
|
||
var uris = new Array();
|
||
for(var i in items) {
|
||
uris.push(i);
|
||
}
|
||
|
||
Scholar.Utilities.processDocuments(uris, function(doc) { scrape(doc) },
|
||
function() { Scholar.done(); }, null);
|
||
|
||
Scholar.wait();
|
||
}
|
||
}');
|
||
|
||
REPLACE INTO "translators" VALUES ('cf87eca8-041d-b954-795a-2d86348999d5', '2006-06-26 16:01:00', 4, 'Aleph', 'Simon Kornblith', '^http://[^/]+/F(?:/[A-Z0-9\-]+(?:\?.*)?$|\?func=find)',
|
||
'function detectWeb(doc, url) {
|
||
var singleRe = new RegExp("^http://[^/]+/F/[A-Z0-9\-]+\?.*func=full-set-set.*\&format=[0-9]{3}");
|
||
|
||
if(singleRe.test(doc.location.href)) {
|
||
return "book";
|
||
} else {
|
||
var tags = doc.getElementsByTagName("a");
|
||
for(var i=0; i<tags.length; i++) {
|
||
if(singleRe.test(tags[i].href)) {
|
||
return "multiple";
|
||
}
|
||
}
|
||
}
|
||
}',
|
||
'function doWeb(doc, url) {
|
||
var detailRe = new RegExp("^http://[^/]+/F/[A-Z0-9\-]+\?.*func=full-set-set.*\&format=[0-9]{3}");
|
||
var uri = doc.location.href;
|
||
var newUris = new Array();
|
||
|
||
if(detailRe.test(uri)) {
|
||
newUris.push(uri.replace(/\&format=[0-9]{3}/, "&format=001"))
|
||
} else {
|
||
var items = Scholar.Utilities.getItemArray(doc, doc, ''^http://[^/]+/F/[A-Z0-9\-]+\?.*func=full-set-set.*\&format=999'', ''^[0-9]+$'');
|
||
|
||
// ugly hack to see if we have any items
|
||
var haveItems = false;
|
||
for(var i in items) {
|
||
haveItems = true;
|
||
break;
|
||
}
|
||
|
||
// If we don''t have any items otherwise, let us use the numbers
|
||
if(!haveItems) {
|
||
var items = Scholar.Utilities.getItemArray(doc, doc, ''^http://[^/]+/F/[A-Z0-9\-]+\?.*func=full-set-set.*\&format=999'');
|
||
}
|
||
|
||
items = Scholar.selectItems(items);
|
||
|
||
if(!items) {
|
||
return true;
|
||
}
|
||
|
||
for(var i in items) {
|
||
newUris.push(i.replace("&format=999", "&format=001"));
|
||
}
|
||
}
|
||
|
||
var marc = Scholar.loadTranslator("import", "a6ee60df-1ddc-4aae-bb25-45e0537be973");
|
||
Scholar.Utilities.processDocuments(newUris, function(newDoc) {
|
||
var uri = newDoc.location.href;
|
||
|
||
var namespace = newDoc.documentElement.namespaceURI;
|
||
var nsResolver = namespace ? function(prefix) {
|
||
if (prefix == ''x'') return namespace; else return null;
|
||
} : null;
|
||
|
||
var xpath = ''/html/body/table/tbody/tr[td[1][@id="bold"]][td[2]]'';
|
||
var elmts = Scholar.Utilities.gatherElementsOnXPath(newDoc, newDoc, xpath, nsResolver);
|
||
|
||
var record = new marc.MARC_Record();
|
||
for(var i=0; i<elmts.length; i++) {
|
||
var elmt = elmts[i];
|
||
var field = Scholar.Utilities.superCleanString(doc.evaluate(''./TD[1]/text()[1]'', elmt, nsResolver, XPathResult.ANY_TYPE, null).iterateNext().nodeValue);
|
||
var value = Scholar.Utilities.getNodeString(doc, elmt, ''./TD[2]//text()'', nsResolver);
|
||
var value = value.replace(/\|([a-z]) /g, record.subfield_delimiter+"$1");
|
||
|
||
if(field != "FMT" && field != "LDR") {
|
||
var ind1 = "";
|
||
var ind2 = "";
|
||
var code = field.substring(0, 3);
|
||
if(field.length > 3) {
|
||
var ind1 = field.charAt(3);
|
||
if(field.length > 4) {
|
||
var ind2 = field.charAt(4);
|
||
}
|
||
}
|
||
record.add_field(code, ind1, ind2, value);
|
||
}
|
||
}
|
||
|
||
var newItem = new Scholar.Item();
|
||
record.translate(newItem);
|
||
newItem.complete();
|
||
}, function() { Scholar.done(); }, null);
|
||
|
||
Scholar.wait();
|
||
}');
|
||
|
||
REPLACE INTO "translators" VALUES ('774d7dc2-3474-2684-392c-f787789ec63d', '2006-06-26 16:01:00', 4, 'Dynix', 'Simon Kornblith', 'ipac\.jsp\?.*(?:uri=full=[0-9]|menu=search)',
|
||
'function detectWeb(doc, url) {
|
||
var detailsRe = new RegExp(''ipac\.jsp\?.*uri=full=[0-9]'');
|
||
if(detailsRe.test(doc.location.href)) {
|
||
return "book";
|
||
} else {
|
||
return "multiple";
|
||
}
|
||
}',
|
||
'function scrape(doc, url) {
|
||
var namespace = doc.documentElement.namespaceURI;
|
||
var nsResolver = namespace ? function(prefix) {
|
||
if (prefix == ''x'') return namespace; else return null;
|
||
} : null;
|
||
|
||
var uri = doc.location.href;
|
||
var detailsRe = new RegExp(''ipac\.jsp\?.*uri=full=[0-9]'');
|
||
|
||
var uris = new Array();
|
||
if(detailsRe.test(uri)) {
|
||
uris.push(uri+''&fullmarc=true'');
|
||
} else {
|
||
var items = Scholar.Utilities.getItemArray(doc, doc, "ipac\.jsp\?.*uri=full=[0-9]|^javascript:buildNewList\\(''.*uri%3Dfull%3D[0-9]");
|
||
items = Scholar.selectItems(items);
|
||
|
||
if(!items) {
|
||
return true;
|
||
}
|
||
|
||
var buildNewList = new RegExp("^javascript:buildNewList\\(''([^'']+)");
|
||
|
||
var uris = new Array();
|
||
for(var i in items) {
|
||
var m = buildNewList.exec(i);
|
||
if(m) {
|
||
uris.push(unescape(m[1]+''&fullmarc=true''));
|
||
} else {
|
||
uris.push(i+''&fullmarc=true'');
|
||
}
|
||
}
|
||
}
|
||
|
||
var marc = Scholar.loadTranslator("import", "a6ee60df-1ddc-4aae-bb25-45e0537be973");
|
||
|
||
Scholar.Utilities.processDocuments(uris, function(newDoc) {
|
||
var uri = newDoc.location.href;
|
||
|
||
var namespace = newDoc.documentElement.namespaceURI;
|
||
var nsResolver = namespace ? function(prefix) {
|
||
if (prefix == ''x'') return namespace; else return null;
|
||
} : null;
|
||
|
||
var xpath = ''//form/table[@class="tableBackground"]/tbody/tr/td/table[@class="tableBackground"]/tbody/tr[td[1]/a[@class="normalBlackFont1"]]'';
|
||
var elmts = Scholar.Utilities.gatherElementsOnXPath(newDoc, newDoc, xpath, nsResolver);
|
||
|
||
var record = new marc.MARC_Record();
|
||
for(var i=0; i<elmts.length; i++) {
|
||
var elmt = elmts[i];
|
||
var field = Scholar.Utilities.superCleanString(newDoc.evaluate(''./TD[1]/A[1]/text()[1]'', elmt, nsResolver, XPathResult.ANY_TYPE, null).iterateNext().nodeValue);
|
||
var value = Scholar.Utilities.getNodeString(newDoc, elmt, ''./TD[2]/TABLE[1]/TBODY[1]/TR[1]/TD[1]/A[1]//text()'', nsResolver);
|
||
value = value.replace(/\$([a-z]) /g, record.subfield_delimiter+"$1");
|
||
|
||
if(field != "FMT" && field != "LDR") {
|
||
var ind1 = "";
|
||
var ind2 = "";
|
||
var valRegexp = /^([0-9])([0-9])? (.*)$/;
|
||
var m = valRegexp.exec(value);
|
||
if(m) {
|
||
ind1 = m[1];
|
||
if(ind2) {
|
||
ind2 = m[2]
|
||
}
|
||
value = m[3];
|
||
}
|
||
marc.add_field(field, ind1, ind2, value);
|
||
}
|
||
}
|
||
|
||
var newItem = new Scholar.Item();
|
||
record.translate(newItem);
|
||
newItem.complete();
|
||
}, function() { Scholar.done() }, null);
|
||
|
||
Scholar.wait();
|
||
}');
|
||
|
||
REPLACE INTO "translators" VALUES ('63a0a351-3131-18f4-21aa-f46b9ac51d87', '2006-06-26 16:01:00', 4, 'VTLS', 'Simon Kornblith', '/chameleon(?:\?|$)',
|
||
'function detectWeb(doc, url) {
|
||
var node = doc.evaluate(''//tr[@class="intrRow"]/td/table/tbody/tr[th]'', doc, null, XPathResult.ANY_TYPE, null).iterateNext();
|
||
if(node) {
|
||
return "multiple";
|
||
}
|
||
var node = doc.evaluate(''//a[text()="marc"]'', doc, null, XPathResult.ANY_TYPE, null).iterateNext();
|
||
if(node) {
|
||
return "book";
|
||
}
|
||
}',
|
||
'function doWeb(doc, url) {
|
||
var namespace = doc.documentElement.namespaceURI;
|
||
var nsResolver = namespace ? function(prefix) {
|
||
if (prefix == ''x'') return namespace; else return null;
|
||
} : null;
|
||
|
||
var uri = doc.location.href;
|
||
var newUris = new Array();
|
||
|
||
var marcs = Scholar.Utilities.gatherElementsOnXPath(doc, doc, ''//a[text()="marc"]'', nsResolver);
|
||
|
||
if(marcs.length == 1) {
|
||
newUris.push(marcs[0].href)
|
||
} else {
|
||
// Require link to match this
|
||
var tagRegexp = new RegExp();
|
||
tagRegexp.compile("/chameleon\?.*function=CARDSCR");
|
||
|
||
var items = new Array();
|
||
|
||
var tableRows = Scholar.Utilities.gatherElementsOnXPath(doc, doc, ''//tr[@class="intrRow"]'', nsResolver);
|
||
// Go through table rows
|
||
for(var i=0; i<tableRows.length; i++) {
|
||
var links = Scholar.Utilities.gatherElementsOnXPath(doc, tableRows[i], ''.//a'', nsResolver);
|
||
// Go through links
|
||
var url;
|
||
for(var j=0; j<links.length; j++) {
|
||
if(tagRegexp.test(links[j].href)) {
|
||
url = links[j].href;
|
||
break;
|
||
}
|
||
}
|
||
if(url) {
|
||
// Collect title information
|
||
var fields = Scholar.Utilities.gatherElementsOnXPath(doc, tableRows[i], ''./td/table/tbody/tr[th]'', nsResolver);
|
||
for(var j=0; j<fields.length; j++) {
|
||
var field = doc.evaluate(''./th/text()'', fields[j], nsResolver, XPathResult.ANY_TYPE, null).iterateNext();
|
||
if(field.nodeValue == "Title") {
|
||
var value = Scholar.Utilities.getNodeString(doc, fields[j], ''./td//text()'', nsResolver);
|
||
if(value) {
|
||
items[url] = Scholar.Utilities.cleanString(value);
|
||
}
|
||
}
|
||
}
|
||
}
|
||
}
|
||
|
||
items = Scholar.selectItems(items);
|
||
|
||
if(!items) {
|
||
return true;
|
||
}
|
||
|
||
for(var i in items) {
|
||
Scholar.Utilities.debug(i.replace(/function=[A-Z]{7}/, "function=MARCSCR"));
|
||
newUris.push(i.replace(/function=[A-Z]{7}/, "function=MARCSCR"));
|
||
}
|
||
}
|
||
|
||
var marc = Scholar.loadTranslator("import", "a6ee60df-1ddc-4aae-bb25-45e0537be973");
|
||
|
||
Scholar.Utilities.processDocuments(newUris, function(newDoc) {
|
||
var uri = newDoc.location.href
|
||
|
||
var namespace = newDoc.documentElement.namespaceURI;
|
||
var nsResolver = namespace ? function(prefix) {
|
||
if (prefix == ''x'') return namespace; else return null;
|
||
} : null;
|
||
|
||
var xpath = ''//table[@class="outertable"]/tbody/tr[td[4]]'';
|
||
var elmts = Scholar.Utilities.gatherElementsOnXPath(newDoc, newDoc, xpath, nsResolver);
|
||
var record = new marc.MARC_Record();
|
||
for(var i=0; i<elmts.length; i++) {
|
||
var elmt = elmts[i];
|
||
var field = doc.evaluate(''./TD[1]/text()[1]'', elmt, nsResolver, XPathResult.ANY_TYPE, null).iterateNext().nodeValue;
|
||
var ind1 = doc.evaluate(''./TD[2]/text()[1]'', elmt, nsResolver, XPathResult.ANY_TYPE, null).iterateNext().nodeValue;
|
||
var ind2 = doc.evaluate(''./TD[3]/text()[1]'', elmt, nsResolver, XPathResult.ANY_TYPE, null).iterateNext().nodeValue;
|
||
var value = doc.evaluate(''./TD[4]/text()[1]'', elmt, nsResolver, XPathResult.ANY_TYPE, null).iterateNext().nodeValue;
|
||
value = value.replace(/\\([a-z]) /g, record.subfield_delimiter+"$1");
|
||
|
||
record.add_field(field, ind1, ind2, value);
|
||
}
|
||
|
||
var newItem = new Scholar.Item();
|
||
record.translate(newItem);
|
||
newItem.complete();
|
||
}, function(){ Scholar.done(); }, null);
|
||
|
||
Scholar.wait();
|
||
}');
|
||
|
||
REPLACE INTO "translators" VALUES ('fb12ae9e-f473-cab4-0546-27ab88c64101', '2006-06-26 16:01:00', 4, 'DRA', 'Simon Kornblith', '/web2/tramp2\.exe/(?:see\_record/|authority\_hits/|goto/.*\?.*screen=Record\.html)',
|
||
'function detectWeb(doc, url) {
|
||
if(doc.location.href.indexOf("/authority_hits") > 0) {
|
||
return "multiple";
|
||
} else {
|
||
return "book";
|
||
}
|
||
}',
|
||
'function doWeb(doc, url) {
|
||
var checkItems = false;
|
||
|
||
if(doc.location.href.indexOf("/authority_hits") > 0) {
|
||
var namespace = doc.documentElement.namespaceURI;
|
||
var nsResolver = namespace ? function(prefix) {
|
||
if (prefix == ''x'') return namespace; else return null;
|
||
} : null;
|
||
|
||
checkItems = Scholar.Utilities.gatherElementsOnXPath(doc, doc, "/html/body//ol/li", nsResolver);
|
||
}
|
||
|
||
if(checkItems && checkItems.length) {
|
||
var items = Scholar.Utilities.getItemArray(doc, checkItems, ''https?://.*/web2/tramp2\.exe/see_record'');
|
||
items = Scholar.selectItems(items);
|
||
|
||
if(!items) {
|
||
return true;
|
||
}
|
||
|
||
var uris = new Array();
|
||
for(var i in items) {
|
||
uris.push(i);
|
||
}
|
||
} else {
|
||
var uris = new Array(doc.location.href);
|
||
}
|
||
|
||
for(var i in uris) {
|
||
var uri = uris[i];
|
||
var uriRegexp = /^(https?:\/\/.*\/web2\/tramp2\.exe\/)(?:goto|see\_record|authority\_hits)(\/.*)\?(?:screen=Record\.html\&)?(.*)$/i;
|
||
var m = uriRegexp.exec(uri);
|
||
if(uri.indexOf("/authority_hits") < 0) {
|
||
var newUri = m[1]+"download_record"+m[2]+"/RECORD.MRC?format=marc&"+m[3];
|
||
} else {
|
||
var newUri = m[1]+"download_record"+m[2]+"/RECORD.MRC?format=marc";
|
||
}
|
||
|
||
// Keep track of how many requests have been completed
|
||
var j = 0;
|
||
|
||
var marc = Scholar.loadTranslator("import", "a6ee60df-1ddc-4aae-bb25-45e0537be973");
|
||
|
||
Scholar.Utilities.HTTP.doGet(newUri, function(text) {
|
||
var record = new marc.MARC_Record();
|
||
record.load(text, "binary");
|
||
|
||
var newItem = new Scholar.Item();
|
||
record.translate(record, newItem);
|
||
newItem.complete();
|
||
|
||
j++;
|
||
if(j == uris.length) {
|
||
Scholar.done();
|
||
}
|
||
});
|
||
}
|
||
Scholar.wait();
|
||
}');
|
||
|
||
REPLACE INTO "translators" VALUES ('c0e6fda6-0ecd-e4f4-39ca-37a4de436e15', '2006-06-26 16:01:00', 4, 'GEAC', 'Simon Kornblith', '/(?:GeacQUERY|GeacFETCH[\:\?].*[&:]next=html/(?:record\.html|geacnffull\.html))',
|
||
'function detectWeb(doc, url) {
|
||
if(doc.location.href.indexOf("/GeacQUERY") > 0) {
|
||
return "multiple";
|
||
} else {
|
||
return "book";
|
||
}
|
||
}',
|
||
'function doWeb(doc, url) {
|
||
var uri = doc.location.href;
|
||
|
||
var uris = new Array();
|
||
|
||
if(uri.indexOf("/GeacQUERY") > 0) {
|
||
var items = Scholar.Utilities.getItemArray(doc, doc, "(?:Geac)?FETCH[\:\?].*[&:]next=html/(?:record\.html|geacnffull\.html)");
|
||
items = Scholar.selectItems(items);
|
||
|
||
if(!items) {
|
||
return true;
|
||
}
|
||
|
||
var uris = new Array();
|
||
for(var i in items) {
|
||
var newUri = i.replace(/([:&])next=html\/geacnffull.html/, "$1next=html/marc.html");
|
||
newUri = newUri.replace(/([:&])next=html\/record.html/, "$1next=html/marc.html");
|
||
uris.push(newUri);
|
||
}
|
||
} else {
|
||
var newUri = uri.replace(/([:&])next=html\/geacnffull.html/, "$1next=html/marc.html");
|
||
newUri = newUri.replace(/([:&])next=html\/record.html/, "$1next=html/marc.html");
|
||
uris.push(newUri);
|
||
}
|
||
|
||
var marc = Scholar.loadTranslator("import", "a6ee60df-1ddc-4aae-bb25-45e0537be973");
|
||
|
||
Scholar.Utilities.processDocuments(uris, function(newDoc) {
|
||
var uri = newDoc.location.href;
|
||
|
||
var namespace = newDoc.documentElement.namespaceURI;
|
||
var nsResolver = namespace ? function(prefix) {
|
||
if (prefix == ''x'') return namespace; else return null;
|
||
} : null;
|
||
|
||
var record = new marc.MARC_Record();
|
||
|
||
var elmts = Scholar.Utilities.gatherElementsOnXPath(newDoc, newDoc, ''//pre/text()'', nsResolver);
|
||
var tag, ind1, ind2, content;
|
||
|
||
for(var i=0; i<elmts.length; i++) {
|
||
var line = elmts[i].nodeValue;
|
||
|
||
if(line.substring(0, 6) == " ") {
|
||
content += " "+line.substring(6);
|
||
continue;
|
||
} else {
|
||
if(tag) {
|
||
record.add_field(tag, ind1, ind2, content);
|
||
}
|
||
}
|
||
|
||
line = line.replace(/\xA0/g," "); // nbsp
|
||
line = line.replace(/_/g," ");
|
||
line = line.replace(/\t/g,"");
|
||
|
||
tag = line.substring(0, 3);
|
||
if(parseInt(tag) > 10) {
|
||
ind1 = line.substring(4, 5);
|
||
ind2 = line.substring(5, 6);
|
||
content = line.substring(7);
|
||
content = content.replace(/\$([a-z])(?: |$)/g, record.subfield_delimiter+"$1");
|
||
} else {
|
||
ind1 = "";
|
||
ind2 = "";
|
||
content = line.substring(4);
|
||
}
|
||
|
||
}
|
||
|
||
var newItem = new Scholar.Item();
|
||
record.translate(newItem);
|
||
newItem.complete();
|
||
}, function() { Scholar.done(); }, null);
|
||
|
||
Scholar.wait();
|
||
}');
|
||
|
||
REPLACE INTO "translators" VALUES ('5287d20c-8a13-6004-4dcb-5bb2b66a9cc9', '2006-06-26 16:01:00', 4, 'SIRSI -2003', 'Simon Kornblith', '/uhtbin/cgisirsi',
|
||
'function detectWeb(doc, url) {
|
||
var namespace = doc.documentElement.namespaceURI;
|
||
var nsResolver = namespace ? function(prefix) {
|
||
if (prefix == ''x'') return namespace; else return null;
|
||
} : null;
|
||
|
||
var elmts = Scholar.Utilities.gatherElementsOnXPath(doc, doc, ''/html/body/form/p/text()[1]'', nsResolver);
|
||
for(var i=0; i<elmts.length; i++) {
|
||
if(Scholar.Utilities.superCleanString(elmts[i].nodeValue) == "Viewing record") {
|
||
return "book";
|
||
}
|
||
}
|
||
var xpath = ''//form[@name="hitlist"]/table/tbody/tr'';
|
||
var elmts = Scholar.Utilities.gatherElementsOnXPath(doc, doc, xpath, nsResolver);
|
||
if(elmts.length) {
|
||
return "multiple";
|
||
}
|
||
}',
|
||
'function doWeb(doc, url) {
|
||
var namespace = doc.documentElement.namespaceURI;
|
||
var nsResolver = namespace ? function(prefix) {
|
||
if (prefix == ''x'') return namespace; else return null;
|
||
} : null;
|
||
|
||
// Cheap hack to convert HTML entities
|
||
function unescapeHTML(text) {
|
||
var div = doc.createElement("div");
|
||
div.innerHTML = Scholar.Utilities.cleanTags(text);
|
||
var text = div.childNodes[0] ? div.childNodes[0].nodeValue : null;
|
||
delete div;
|
||
return text;
|
||
}
|
||
|
||
var uri = doc.location.href;
|
||
var recNumbers = new Array();
|
||
|
||
var xpath = ''//form[@name="hitlist"]/table/tbody/tr'';
|
||
var elmts = Scholar.Utilities.gatherElementsOnXPath(doc, doc, xpath, nsResolver);
|
||
if(elmts.length) { // Search results page
|
||
var uriRegexp = /^http:\/\/[^\/]+/;
|
||
var m = uriRegexp.exec(uri);
|
||
var postAction = doc.forms.namedItem("hitlist").getAttribute("action");
|
||
var newUri = m[0]+postAction.substr(0, postAction.length-1)+"40"
|
||
|
||
var titleRe = /<br>\s*(.*[^\s])\s*<br>/i;
|
||
|
||
var items = new Array();
|
||
|
||
for(var i=0; i<elmts.length; i++) {
|
||
var links = Scholar.Utilities.gatherElementsOnXPath(doc, elmts[i], ''.//a'', nsResolver);
|
||
|
||
// Collect title
|
||
var myTd = doc.evaluate("./td[2]", elmts[i], nsResolver, XPathResult.ANY_TYPE, null).iterateNext();
|
||
var m = titleRe.exec(myTd.innerHTML);
|
||
var title = unescapeHTML(m[1]);
|
||
|
||
items[i] = title;
|
||
}
|
||
|
||
|
||
items = Scholar.selectItems(items);
|
||
|
||
if(!items) {
|
||
return true;
|
||
}
|
||
|
||
for(var i in items) {
|
||
recNumbers.push(parseInt(i)+1);
|
||
}
|
||
} else { // Normal page
|
||
var uriRegexp = /^(.*)(\/[0-9]+)$/;
|
||
var m = uriRegexp.exec(uri);
|
||
var newUri = m[1]+"/40"
|
||
|
||
var elmts = Scholar.Utilities.gatherElementsOnXPath(doc, doc, ''/html/body/form/p'', nsResolver);
|
||
for(var i=0; i<elmts.length; i++) {
|
||
var elmt = elmts[i];
|
||
var initialText = doc.evaluate(''./text()[1]'', elmt, nsResolver, XPathResult.ANY_TYPE, null).iterateNext();
|
||
if(initialText && initialText.nodeValue && Scholar.Utilities.superCleanString(initialText.nodeValue) == "Viewing record") {
|
||
recNumbers.push(doc.evaluate(''./b[1]/text()[1]'', elmt, nsResolver, XPathResult.ANY_TYPE, null).iterateNext().nodeValue);
|
||
break;
|
||
}
|
||
}
|
||
}
|
||
|
||
var marc = Scholar.loadTranslator("import", "a6ee60df-1ddc-4aae-bb25-45e0537be973");
|
||
|
||
Scholar.Utilities.HTTP.doGet(newUri+''?marks=''+recNumbers.join(",")+''&shadow=NO&format=FLAT+ASCII&sort=TITLE&vopt_elst=ALL&library=ALL&display_rule=ASCENDING&duedate_code=l&holdcount_code=t&DOWNLOAD_x=22&DOWNLOAD_y=12&address=&form_type='', function(text) {
|
||
var texts = text.split("<PRE>");
|
||
texts = texts[1].split("</PRE>");
|
||
text = unescapeHTML(texts[0]);
|
||
var documents = text.split("*** DOCUMENT BOUNDARY ***");
|
||
|
||
for(var j=1; j<documents.length; j++) {
|
||
var uri = newUri+"?marks="+recNumbers[j]+"&shadow=NO&format=FLAT+ASCII&sort=TITLE&vopt_elst=ALL&library=ALL&display_rule=ASCENDING&duedate_code=l&holdcount_code=t&DOWNLOAD_x=22&DOWNLOAD_y=12&address=&form_type=";
|
||
var lines = documents[j].split("\n");
|
||
var record = new marc.MARC_Record();
|
||
var tag, ind1, ind2, content;
|
||
for(var i=0; i<lines.length; i++) {
|
||
var line = lines[i];
|
||
|
||
if(line.substr(0, 1) == "." && line.substr(4,2) == ". ") {
|
||
if(tag) {
|
||
content = content.replace(/\|([a-z])/g, record.subfield_delimiter+"$1");
|
||
record.add_field(tag, ind1, ind2, content);
|
||
}
|
||
} else {
|
||
content += " "+line.substring(6);
|
||
continue;
|
||
}
|
||
|
||
tag = line.substr(1, 3);
|
||
|
||
if(parseInt(tag) > 10) {
|
||
ind1 = line.substr(6, 1);
|
||
ind2 = line.substr(7, 1);
|
||
content = line.substr(8);
|
||
} else {
|
||
ind1 = "";
|
||
ind2 = "";
|
||
content = line.substring(6);
|
||
}
|
||
}
|
||
|
||
var newItem = new Scholar.Item();
|
||
record.translate(newItem);
|
||
newItem.complete();
|
||
}
|
||
Scholar.done();
|
||
});
|
||
|
||
Scholar.wait();
|
||
}');
|
||
|
||
REPLACE INTO "translators" VALUES ('0f9fc2fc-306e-5204-1117-25bca009dffc', '2006-06-26 16:01:00', 4, 'TLC/YouSeeMore', 'Simon Kornblith', 'TLCScripts/interpac\.dll\?(?:.*LabelDisplay.*RecordNumber=[0-9]|Search|ItemTitles)',
|
||
'function detectWeb(doc, url) {
|
||
var detailRe = new RegExp("TLCScripts/interpac\.dll\?.*LabelDisplay.*RecordNumber=[0-9]");
|
||
if(detailRe.test(doc.location.href)) {
|
||
return "book";
|
||
} else {
|
||
return "multiple";
|
||
}
|
||
}',
|
||
'function doWeb(doc, url) {
|
||
var namespace = doc.documentElement.namespaceURI;
|
||
var nsResolver = namespace ? function(prefix) {
|
||
if (prefix == ''x'') return namespace; else return null;
|
||
} : null;
|
||
|
||
var detailRe = new RegExp("TLCScripts/interpac\.dll\?.*LabelDisplay.*RecordNumber=[0-9]");
|
||
var uri = doc.location.href;
|
||
var newUris = new Array();
|
||
|
||
if(detailRe.test(uri)) {
|
||
newUris.push(uri.replace("LabelDisplay", "MARCDisplay"));
|
||
} else {
|
||
var items = Scholar.Utilities.getItemArray(doc, doc, ''TLCScripts/interpac\.dll\?.*LabelDisplay.*RecordNumber=[0-9]'');
|
||
items = Scholar.selectItems(items);
|
||
|
||
if(!items) {
|
||
return true;
|
||
}
|
||
|
||
for(var i in items) {
|
||
newUris.push(i.replace("LabelDisplay", "MARCDisplay"));
|
||
}
|
||
}
|
||
|
||
var marc = Scholar.loadTranslator("import", "a6ee60df-1ddc-4aae-bb25-45e0537be973");
|
||
|
||
Scholar.Utilities.processDocuments(newUris, function(newDoc) {
|
||
var uri = newDoc.location.href;
|
||
|
||
var namespace = newDoc.documentElement.namespaceURI;
|
||
var nsResolver = namespace ? function(prefix) {
|
||
if (prefix == ''x'') return namespace; else return null;
|
||
} : null;
|
||
|
||
var record = new marc.MARC_Record();
|
||
|
||
var elmts = Scholar.Utilities.gatherElementsOnXPath(newDoc, newDoc, ''/html/body/table/tbody/tr[td[4]]'', nsResolver);
|
||
var tag, ind1, ind2, content;
|
||
|
||
for(var i=0; i<elmts.length; i++) {
|
||
var elmt = elmts[i];
|
||
|
||
tag = newDoc.evaluate(''./td[2]/tt[1]/text()[1]'', elmt, nsResolver, XPathResult.ANY_TYPE, null).iterateNext().nodeValue;
|
||
var inds = newDoc.evaluate(''./td[3]/tt[1]/text()[1]'', elmt, nsResolver, XPathResult.ANY_TYPE, null).iterateNext().nodeValue;
|
||
|
||
tag = tag.replace(/[\r\n]/g, "");
|
||
if(tag.length == 1) {
|
||
tag = "00"+tag;
|
||
} else if(tag.length == 2) {
|
||
tag = "0"+tag;
|
||
}
|
||
inds = inds.replace(/[\r\n]/g, "");
|
||
|
||
// Get indicators, fix possible problems with s
|
||
ind1 = inds.substr(0, 1);
|
||
ind2 = inds.substr(1, 1);
|
||
if(ind1 == "\xA0") {
|
||
ind1 = "";
|
||
}
|
||
if(ind2 == "\xA0") {
|
||
ind2 = "";
|
||
}
|
||
|
||
var children = Scholar.Utilities.gatherElementsOnXPath(newDoc, elmt, ''./td[4]/tt[1]//text()'', nsResolver);
|
||
content = "";
|
||
if(children.length == 1) {
|
||
content = children[0].nodeValue;
|
||
} else {
|
||
for(var j=0; j<children.length; j+=2) {
|
||
var subfield = children[j].nodeValue.substr(1, 1);
|
||
var fieldContent = children[j+1].nodeValue;
|
||
content += record.subfield_delimiter+subfield+fieldContent;
|
||
}
|
||
}
|
||
|
||
record.add_field(tag, ind1, ind2, content);
|
||
}
|
||
|
||
var newItem = new Scholar.Item();
|
||
record.translate(newItem);
|
||
newItem.complete();
|
||
}, function() {Scholar.done(); }, null);
|
||
|
||
Scholar.wait();
|
||
}');
|
||
|
||
REPLACE INTO "translators" VALUES ('c54d1932-73ce-dfd4-a943-109380e06574', '2006-06-26 16:01:00', 4, 'Project MUSE', 'Simon Kornblith', '^http://muse\.jhu\.edu/(?:journals/[^/]+/[^/]+/[^/]+\.html|search/pia.cgi)',
|
||
'function detectWeb(doc, url) {
|
||
var searchRe = new RegExp("^http://[^/]+/search/pia\.cgi");
|
||
if(searchRe.test(url)) {
|
||
return "multiple";
|
||
} else {
|
||
return "journalArticle";
|
||
}
|
||
}',
|
||
'function doWeb(doc, url) {
|
||
var namespace = doc.documentElement.namespaceURI;
|
||
var nsResolver = namespace ? function(prefix) {
|
||
if (prefix == ''x'') return namespace; else return null;
|
||
} : null;
|
||
|
||
var searchRe = new RegExp("^http://[^/]+/search/pia\.cgi");
|
||
if(searchRe.test(doc.location.href)) {
|
||
var items = new Array();
|
||
var attachments = new Array();
|
||
var pdfRe = /\.pdf$/i;
|
||
var htmlRe = /\.html$/i;
|
||
|
||
var tableRows = doc.evaluate(''/html/body/table[@class="navbar"]/tbody/tr/td/form/table'',
|
||
doc, nsResolver, XPathResult.ANY_TYPE, null);
|
||
var tableRow;
|
||
// Go through table rows
|
||
while(tableRow = tableRows.iterateNext()) {
|
||
// article_id is what we need to get it all as one file
|
||
var input = doc.evaluate(''./tbody/tr/td/input[@name="article_id"]'', tableRow, nsResolver, XPathResult.ANY_TYPE, null).iterateNext();
|
||
var link = doc.evaluate(''.//b/i/a/text()'', tableRow, nsResolver, XPathResult.ANY_TYPE, null).iterateNext();
|
||
if(input && input.value && link && link.nodeValue) {
|
||
items[input.value] = link.nodeValue;
|
||
|
||
var aTags = tableRow.getElementsByTagName("a");
|
||
|
||
// get attachments
|
||
attachments[input.value] = new Array();
|
||
for(var i=0; i<aTags.length; i++) {
|
||
if(pdfRe.test(aTags[i].href)) {
|
||
attachments[input.value].push({url:aTags[i].href,
|
||
title:"Project MUSE Full Text (PDF)",
|
||
mimeType:"application/pdf",
|
||
downloadable:true});
|
||
} else if(htmlRe.test(aTags[i].href)) {
|
||
attachments[input.value].push({url:aTags[i].href,
|
||
title:"Project MUSE Full Text (HTML)",
|
||
mimeType:"text/html",
|
||
downloadable:true});
|
||
}
|
||
}
|
||
}
|
||
}
|
||
|
||
items = Scholar.selectItems(items);
|
||
if(!items) {
|
||
return true;
|
||
}
|
||
|
||
try {
|
||
var search_id = doc.forms.namedItem("results").elements.namedItem("search_id").value;
|
||
} catch(e) {
|
||
var search_id = "";
|
||
}
|
||
var articleString = "";
|
||
var newAttachments = new Array();
|
||
for(var i in items) {
|
||
articleString += "&article_id="+i;
|
||
newAttachments.push(attachments[i]);
|
||
}
|
||
var savePostString = "actiontype=save&search_id="+search_id+articleString;
|
||
|
||
Scholar.Utilities.HTTP.doGet("http://muse.jhu.edu/search/save.cgi?"+savePostString, function() {
|
||
Scholar.Utilities.HTTP.doGet("http://muse.jhu.edu/search/export.cgi?exporttype=endnote"+articleString, function(text) {
|
||
Scholar.Utilities.debug(text);
|
||
// load translator for RIS
|
||
var translator = Scholar.loadTranslator("import", "32d59d2d-b65a-4da4-b0a3-bdd3cfb979e7");
|
||
// feed in data
|
||
translator.Scholar.write(text);
|
||
translator.Scholar.eof();
|
||
// translate
|
||
translator.doImport(newAttachments);
|
||
Scholar.done();
|
||
}, function() {});
|
||
}, function() {});
|
||
|
||
Scholar.wait();
|
||
} else {
|
||
var newItem = new Scholar.Item("journalArticle");
|
||
newItem.url = url;
|
||
newItem.attachments.push({title:"Project MUSE Full Text (HTML)", mimeType:"text/html",
|
||
url:url, downloadable:true});
|
||
|
||
var getPDF = doc.evaluate(''//a[text() = "[Access article in PDF]"]'', doc,
|
||
nsResolver, XPathResult.ANY_TYPE, null).iterateNext();
|
||
if(getPDF) {
|
||
newItem.attachments.push({title:"Project MUSE Full Text (PDF)", mimeType:"application/pdf",
|
||
url:getPDF.href, downloadable:true});
|
||
}
|
||
|
||
var elmts = doc.evaluate(''//comment()'', doc, nsResolver,
|
||
XPathResult.ANY_TYPE, null);
|
||
|
||
var headerRegexp = /HeaderData((?:.|\n)*)\#\#EndHeaders/i
|
||
while(elmt = elmts.iterateNext()) {
|
||
if(elmt.nodeValue.substr(0, 10) == "HeaderData") {
|
||
var m = headerRegexp.exec(elmt.nodeValue);
|
||
var headerData = m[1];
|
||
}
|
||
}
|
||
|
||
// Use E4X rather than DOM/XPath, because the Mozilla gods have decided not to
|
||
// expose DOM/XPath to sandboxed scripts
|
||
var newDOM = new XML(headerData);
|
||
|
||
newItem.publicationTitle = newDOM.journal.text();
|
||
newItem.volume = newDOM.volume.text();
|
||
newItem.issue = newDOM.issue.text();
|
||
newItem.date = newDOM.pubdate.text().toString();
|
||
if(!newItem.date) {
|
||
newItem.date = newDOM.year.text();
|
||
}
|
||
newItem.title = newDOM.doctitle.text();
|
||
newItem.ISSN = newDOM.issn.text();
|
||
|
||
// Do pages
|
||
var fpage = newDOM.fpage.text();
|
||
var lpage = newDOM.lpage.text();
|
||
if(fpage != "") {
|
||
newItem.pages = fpage;
|
||
if(lpage) {
|
||
newItem.pages += "-"+lpage;
|
||
}
|
||
}
|
||
|
||
// Do authors
|
||
var elmts = newDOM.docauthor;
|
||
for(var i in elmts) {
|
||
var fname = elmts[i].fname.text();
|
||
var surname = elmts[i].surname.text();
|
||
newItem.creators.push({firstName:fname, lastName:surname, creatorType:"author"});
|
||
}
|
||
|
||
newItem.complete();
|
||
}
|
||
}');
|
||
|
||
REPLACE INTO "translators" VALUES ('fcf41bed-0cbc-3704-85c7-8062a0068a7a', '2006-08-07 21:55:00', 12, 'PubMed', 'Simon Kornblith', '^http://www\.ncbi\.nlm\.nih\.gov/entrez/query\.fcgi\?(?:.*db=PubMed.*list_uids=[0-9]|.*list_uids=[0-9].*db=PubMed|.*db=PubMed.*CMD=search|.*CMD=search.*db=PubMed)',
|
||
'function detectWeb(doc, url) {
|
||
if(doc.location.href.indexOf("list_uids=") >= 0) {
|
||
return "journalArticle";
|
||
} else {
|
||
return "multiple";
|
||
}
|
||
}
|
||
|
||
function getPMID(co) {
|
||
var coParts = co.split("&");
|
||
for each(part in coParts) {
|
||
if(part.substr(0, 7) == "rft_id=") {
|
||
var value = unescape(part.substr(7));
|
||
if(value.substr(0, 10) == "info:pmid/") {
|
||
return value.substr(10);
|
||
}
|
||
}
|
||
}
|
||
}
|
||
|
||
function detectSearch(item) {
|
||
if(item.contextObject) {
|
||
if(getPMID(item.contextObject)) {
|
||
return "journalArticle";
|
||
}
|
||
}
|
||
return false;
|
||
}',
|
||
'function lookupPMIDs(ids, doc) {
|
||
Scholar.wait();
|
||
|
||
var newUri = "http://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=PubMed&retmode=xml&rettype=citation&id="+ids.join(",");
|
||
Scholar.Utilities.HTTP.doGet(newUri, function(text) {
|
||
// Remove xml parse instruction and doctype
|
||
text = text.replace(/<!DOCTYPE[^>]*>/, "").replace(/<\?xml[^>]*\?>/, "");
|
||
|
||
var xml = new XML(text);
|
||
|
||
for(var i=0; i<xml.PubmedArticle.length(); i++) {
|
||
var newItem = new Scholar.Item("journalArticle");
|
||
|
||
var citation = xml.PubmedArticle[i].MedlineCitation;
|
||
|
||
var PMID = citation.PMID.text().toString();
|
||
newItem.accessionNumber = "PMID "+PMID;
|
||
|
||
// add attachments
|
||
if(doc) {
|
||
newItem.attachments.push({document:doc, title:"PubMed Abstract",
|
||
downloadable:true});
|
||
} else {
|
||
var url = "http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=pubmed&cmd=Retrieve&dopt=AbstractPlus&list_uids="+PMID;
|
||
newItem.attachments.push({url:url, title:"PubMed Abstract (HTML)",
|
||
mimeType:"text/html", downloadable:true});
|
||
}
|
||
|
||
var article = citation.Article;
|
||
if(article.ArticleTitle.length()) {
|
||
var title = article.ArticleTitle.text().toString();
|
||
if(title.substr(-1) == ".") {
|
||
title = title.substring(0, title.length-1);
|
||
}
|
||
newItem.title = title;
|
||
}
|
||
|
||
if(article.Journal.length()) {
|
||
var issn = article.Journal.ISSN.text();
|
||
if(issn) {
|
||
newItem.ISSN = issn.replace(/[^0-9]/g, "");
|
||
}
|
||
|
||
if(article.Journal.Title.length()) {
|
||
newItem.publicationTitle = Scholar.Utilities.superCleanString(article.Journal.Title.text().toString());
|
||
} else if(citation.MedlineJournalInfo.MedlineTA.length()) {
|
||
newItem.publicationTitle = Scholar.Utilities.superCleanString(citation.MedlineJournalInfo.MedlineTA.text().toString());
|
||
}
|
||
|
||
if(article.Journal.JournalIssue.length()) {
|
||
newItem.volume = article.Journal.JournalIssue.Volume.text();
|
||
newItem.issue = article.Journal.JournalIssue.Issue.text();
|
||
if(article.Journal.JournalIssue.PubDate.length()) { // try to get the date
|
||
if(article.Journal.JournalIssue.PubDate.Day.text().toString() != "") {
|
||
var date = article.Journal.JournalIssue.PubDate.Month.text()+" "+article.Journal.JournalIssue.PubDate.Day.text()+", "+article.Journal.JournalIssue.PubDate.Year.text();
|
||
var jsDate = new Date(date);
|
||
if(!isNaN(jsDate.valueOf())) {
|
||
date = Scholar.Utilities.dateToSQL(jsDate);
|
||
}
|
||
} else if(article.Journal.JournalIssue.PubDate.Month.text().toString() != "") {
|
||
var date = article.Journal.JournalIssue.PubDate.Month.text()+" "+article.Journal.JournalIssue.PubDate.Year.text();
|
||
} else if(article.Journal.JournalIssue.PubDate.Year.text().toString() != "") {
|
||
var date = article.Journal.JournalIssue.PubDate.Year.text();
|
||
}
|
||
|
||
if(date) {
|
||
newItem.date = date;
|
||
}
|
||
}
|
||
}
|
||
}
|
||
|
||
if(article.AuthorList.length() && article.AuthorList.Author.length()) {
|
||
var authors = article.AuthorList.Author;
|
||
for(var j=0; j<authors.length(); j++) {
|
||
var lastName = authors[j].LastName.text().toString();
|
||
var firstName = authors[j].FirstName.text().toString();
|
||
if(firstName == "") {
|
||
var firstName = authors[j].ForeName.text().toString();
|
||
}
|
||
if(firstName || lastName) {
|
||
newItem.creators.push({lastName:lastName, firstName:firstName});
|
||
}
|
||
}
|
||
}
|
||
|
||
newItem.complete();
|
||
}
|
||
|
||
Scholar.done();
|
||
});
|
||
}
|
||
|
||
function doWeb(doc, url) {
|
||
var uri = doc.location.href;
|
||
var ids = new Array();
|
||
var idRegexp = /[\?\&]list_uids=([0-9\,]+)/;
|
||
|
||
var m = idRegexp.exec(uri);
|
||
if(m) {
|
||
ids.push(m[1]);
|
||
|
||
lookupPMIDs(ids, doc);
|
||
} else {
|
||
var namespace = doc.documentElement.namespaceURI;
|
||
var nsResolver = namespace ? function(prefix) {
|
||
if (prefix == ''x'') return namespace; else return null;
|
||
} : null;
|
||
|
||
var items = new Array();
|
||
var tableRows = doc.evaluate(''//div[@class="ResultSet"]/table/tbody'', doc,
|
||
nsResolver, XPathResult.ANY_TYPE, null);
|
||
var tableRow;
|
||
// Go through table rows
|
||
while(tableRow = tableRows.iterateNext()) {
|
||
var link = doc.evaluate(''.//a'', tableRow, nsResolver, XPathResult.ANY_TYPE, null).iterateNext();
|
||
var article = doc.evaluate(''./tr[2]/td[2]/text()[1]'', tableRow, nsResolver, XPathResult.ANY_TYPE, null).iterateNext();
|
||
items[link.href] = article.nodeValue;
|
||
}
|
||
|
||
items = Scholar.selectItems(items);
|
||
|
||
if(!items) {
|
||
return true;
|
||
}
|
||
|
||
for(var i in items) {
|
||
var m = idRegexp.exec(i);
|
||
ids.push(m[1]);
|
||
}
|
||
|
||
lookupPMIDs(ids);
|
||
}
|
||
}
|
||
|
||
function doSearch(item) {
|
||
// pmid was defined earlier in detectSearch
|
||
lookupPMIDs([getPMID(item.contextObject)]);
|
||
}');
|
||
|
||
REPLACE INTO "translators" VALUES ('951c027d-74ac-47d4-a107-9c3069ab7b48', '2006-06-26 16:41:00', 4, 'Embedded RDF', 'Simon Kornblith', NULL,
|
||
'function detectWeb(doc, url) {
|
||
var metaTags = doc.getElementsByTagName("meta");
|
||
|
||
for(var i=0; i<metaTags.length; i++) {
|
||
var tag = metaTags[i].getAttribute("name");
|
||
if(tag && tag.substr(0, 3).toLowerCase() == "dc.") {
|
||
return "website";
|
||
}
|
||
}
|
||
|
||
return false;
|
||
}',
|
||
'function doWeb(doc, url) {
|
||
var dc = "http://purl.org/dc/elements/1.1/";
|
||
|
||
// load RDF translator
|
||
var translator = Scholar.loadTranslator("import", "5e3ad958-ac79-463d-812b-a86a9235c28f");
|
||
|
||
var metaTags = doc.getElementsByTagName("meta");
|
||
var foundTitle = false; // We can use the page title if necessary
|
||
for(var i=0; i<metaTags.length; i++) {
|
||
var tag = metaTags[i].getAttribute("name");
|
||
var value = metaTags[i].getAttribute("content");
|
||
if(tag && value && tag.substr(0, 3).toLowerCase() == "dc.") {
|
||
if(tag == "dc.title") {
|
||
foundTitle = true;
|
||
}
|
||
translator.Scholar.RDF.addStatement(url, dc + tag.substr(3), value, true);
|
||
Scholar.Utilities.debug(tag.substr(3) + " = " + value);
|
||
} else if(tag && value && (tag == "author" || tag == "author-personal")) {
|
||
translator.Scholar.RDF.addStatement(url, dc + "creator", value, true);
|
||
} else if(tag && value && tag == "author-corporate") {
|
||
translator.Scholar.RDF.addStatement(url, dc + "creator", value, true);
|
||
}
|
||
}
|
||
|
||
if(!foundTitle) {
|
||
translator.Scholar.RDF.addStatement(url, dc + "title", doc.title, true);
|
||
}
|
||
|
||
translator.doImport();
|
||
}');
|
||
|
||
REPLACE INTO "translators" VALUES ('05d07af9-105a-4572-99f6-a8e231c0daef', '2006-08-07 01:09:00', 4, 'COinS', 'Simon Kornblith', NULL,
|
||
'function detectWeb(doc, url) {
|
||
var spanTags = doc.getElementsByTagName("span");
|
||
|
||
var encounteredType = false;
|
||
|
||
for(var i=0; i<spanTags.length; i++) {
|
||
var spanClass = spanTags[i].getAttribute("class");
|
||
if(spanClass) {
|
||
var spanClasses = spanClass.split(" ");
|
||
if(Scholar.Utilities.inArray("Z3988", spanClasses)) {
|
||
var spanTitle = spanTags[i].getAttribute("title");
|
||
|
||
// determine if it''s a valid type
|
||
var coParts = spanTitle.split("&");
|
||
var type = null
|
||
for(var j in coParts) {
|
||
if(coParts[j].substr(0, 12) == "rft_val_fmt=") {
|
||
var format = unescape(coParts[j].substr(12));
|
||
if(format == "info:ofi/fmt:kev:mtx:journal") {
|
||
var type = "journalArticle";
|
||
} else if(format == "info:ofi/fmt:kev:mtx:book") {
|
||
if(Scholar.Utilities.inArray("rft.genre=bookitem", coParts)) {
|
||
var type = "bookSection";
|
||
} else {
|
||
var type = "book";
|
||
}
|
||
break;
|
||
}
|
||
}
|
||
}
|
||
|
||
if(type) {
|
||
if(encounteredType) {
|
||
return "multiple";
|
||
} else {
|
||
encounteredType = type;
|
||
}
|
||
}
|
||
}
|
||
}
|
||
}
|
||
|
||
return encounteredType;
|
||
}',
|
||
'// used to retrieve next COinS object when asynchronously parsing COinS objects
|
||
// on a page
|
||
function retrieveNextCOinS(needFullItems, newItems, doc) {
|
||
if(needFullItems.length) {
|
||
var item = needFullItems.shift();
|
||
|
||
Scholar.Utilities.debug("looking up contextObject");
|
||
var search = Scholar.loadTranslator("search");
|
||
search.setHandler("itemDone", function(obj, item) {
|
||
newItems.push(item);
|
||
});
|
||
search.setHandler("done", function() {
|
||
retrieveNextCOinS(needFullItems, newItems, doc);
|
||
});
|
||
search.setSearch(item);
|
||
|
||
// look for translators
|
||
var translators = search.getTranslators();
|
||
if(translators) {
|
||
search.setTranslator(translators);
|
||
search.translate();
|
||
} else {
|
||
retrieveNextCOinS(needFullItems, newItems, doc);
|
||
}
|
||
} else {
|
||
completeCOinS(newItems, doc);
|
||
Scholar.done(true);
|
||
}
|
||
}
|
||
|
||
// saves all COinS objects
|
||
function completeCOinS(newItems, doc) {
|
||
if(newItems.length > 1) {
|
||
var selectArray = new Array();
|
||
|
||
for(var i in newItems) {
|
||
selectArray[i] = newItems[i].title;
|
||
}
|
||
selectArray = Scholar.selectItems(selectArray);
|
||
for(var i in selectArray) {
|
||
// add doc as attachment
|
||
newItems[i].attachments.push({document:doc});
|
||
|
||
newItems[i].complete();
|
||
}
|
||
} else if(newItems.length) {
|
||
newItems[0].attachments.push({document:doc});
|
||
newItems[0].complete();
|
||
}
|
||
}
|
||
|
||
function doWeb(doc, url) {
|
||
var newItems = new Array();
|
||
var needFullItems = new Array();
|
||
|
||
var spanTags = doc.getElementsByTagName("span");
|
||
|
||
for(var i=0; i<spanTags.length; i++) {
|
||
var spanClass = spanTags[i].getAttribute("class");
|
||
if(spanClass) {
|
||
var spanClasses = spanClass.split(" ");
|
||
if(Scholar.Utilities.inArray("Z3988", spanClasses)) {
|
||
var spanTitle = spanTags[i].getAttribute("title");
|
||
var newItem = new Scholar.Item();
|
||
if(Scholar.Utilities.parseContextObject(spanTitle, newItem)) {
|
||
if(newItem.title && newItem.creators.length) {
|
||
// title and creators are minimum data to avoid looking up
|
||
newItems.push(newItem);
|
||
} else {
|
||
// retrieve full item
|
||
newItem.contextObject = spanTitle;
|
||
needFullItems.push(newItem);
|
||
}
|
||
}
|
||
}
|
||
}
|
||
}
|
||
|
||
if(needFullItems.length) {
|
||
// retrieve full items asynchronously
|
||
Scholar.wait();
|
||
retrieveNextCOinS(needFullItems, newItems, doc);
|
||
} else {
|
||
completeCOinS(newItems, doc);
|
||
}
|
||
}');
|
||
|
||
REPLACE INTO "translators" VALUES ('3e684d82-73a3-9a34-095f-19b112d88bbf', '2006-06-26 16:01:00', 4, 'Google Books', 'Simon Kornblith', '^http://books\.google\.com/books\?(.*vid=.*\&id=.*|.*q=.*)',
|
||
'function detectWeb(doc, url) {
|
||
var re = new RegExp(''^http://books\\.google\\.com/books\\?vid=([^&]+).*\\&id=([^&]+)'', ''i'');
|
||
if(re.test(doc.location.href)) {
|
||
return "book";
|
||
} else {
|
||
return "multiple";
|
||
}
|
||
}',
|
||
'function doWeb(doc, url) {
|
||
var uri = doc.location.href;
|
||
var newUris = new Array();
|
||
|
||
var re = new RegExp(''^http://books\\.google\\.com/books\\?vid=([^&]+).*\\&id=([^&]+)'', ''i'');
|
||
var m = re.exec(uri);
|
||
if(m) {
|
||
newUris.push(''http://books.google.com/books?vid=''+m[1]+''&id=''+m[2]);
|
||
} else {
|
||
var items = Scholar.Utilities.getItemArray(doc, doc, ''http://books\\.google\\.com/books\\?vid=([^&]+).*\\&id=([^&]+)'', ''^(?:All matching pages|About this Book|Table of Contents|Index)'');
|
||
|
||
// Drop " - Page" thing
|
||
for(var i in items) {
|
||
items[i] = items[i].replace(/- Page [0-9]+\s*$/, "");
|
||
}
|
||
items = Scholar.selectItems(items);
|
||
|
||
if(!items) {
|
||
return true;
|
||
}
|
||
|
||
for(var i in items) {
|
||
var m = re.exec(i);
|
||
newUris.push(''http://books.google.com/books?vid=''+m[1]+''&id=''+m[2]);
|
||
}
|
||
}
|
||
|
||
Scholar.Utilities.processDocuments(newUris, function(newDoc) {
|
||
var newItem = new Scholar.Item("book");
|
||
newItem.extra = "";
|
||
newItem.attachments.push({title:"Google Books Information Page", document:newDoc});
|
||
|
||
var namespace = newDoc.documentElement.namespaceURI;
|
||
var nsResolver = namespace ? function(prefix) {
|
||
if (prefix == ''x'') return namespace; else return null;
|
||
} : null;
|
||
|
||
var xpath = ''//table[@id="bib"]/tbody/tr'';
|
||
var elmts = newDoc.evaluate(xpath, newDoc, nsResolver,
|
||
XPathResult.ANY_TYPE, null);
|
||
var elmt;
|
||
while(elmt = elmts.iterateNext()) {
|
||
var field = newDoc.evaluate(''./td[1]//text()'', elmt, nsResolver, XPathResult.ANY_TYPE, null).iterateNext();
|
||
var value = newDoc.evaluate(''./td[2]//text()'', elmt, nsResolver, XPathResult.ANY_TYPE, null).iterateNext();
|
||
|
||
if(field && value) {
|
||
field = Scholar.Utilities.superCleanString(field.nodeValue);
|
||
value = Scholar.Utilities.cleanString(value.nodeValue);
|
||
if(field == "Title") {
|
||
newItem.title = value;
|
||
} else if(field == "Author(s)") {
|
||
var authors = value.split(", ");
|
||
for(j in authors) {
|
||
newItem.creators.push(Scholar.Utilities.cleanAuthor(authors[j], "author"));
|
||
}
|
||
} else if(field == "Editor(s)") {
|
||
var authors = value.split(", ");
|
||
for(j in authors) {
|
||
newItem.creators.push(Scholar.Utilities.cleanAuthor(authors[j], "editor"));
|
||
}
|
||
} else if(field == "Publisher") {
|
||
newItem.publisher = value;
|
||
} else if(field == "Publication Date") {
|
||
var date = value;
|
||
|
||
jsDate = new Date(value);
|
||
if(!isNaN(jsDate.valueOf())) {
|
||
date = Scholar.Utilities.dateToSQL(jsDate);
|
||
}
|
||
|
||
newItem.date = date;
|
||
/*} else if(field == "Format") {
|
||
.addStatement(uri, prefixDC + ''medium'', value);*/
|
||
} else if(field == "ISBN") {
|
||
newItem.ISBN = value;
|
||
} else if(field == "Pages") {
|
||
newItem.pages = value;
|
||
} else {
|
||
newItem.extra += field+": "+value+"\n";
|
||
}
|
||
}
|
||
}
|
||
|
||
if(newItem.extra) {
|
||
newItem.extra = newItem.extra.substr(newItem.extra, newItem.extra.length-1);
|
||
}
|
||
|
||
newItem.complete();
|
||
}, function() { Scholar.done(); }, null);
|
||
|
||
Scholar.wait();
|
||
}');
|
||
|
||
REPLACE INTO "translators" VALUES ('9c335444-a562-4f88-b291-607e8f46a9bb', '2006-08-15 15:42:00', 4, 'Berkeley Library', 'Simon Kornblith', '^http://[^/]*berkeley.edu[^/]*/WebZ/(?:html/results.html|FETCH)\?.*sessionid=',
|
||
'function detectWeb(doc, url) {
|
||
var resultsRegexp = /\/WebZ\/html\/results.html/i
|
||
if(resultsRegexp.test(url)) {
|
||
return "multiple";
|
||
} else {
|
||
return "book";
|
||
}
|
||
}',
|
||
'function reformURL(url) {
|
||
return url.replace(/fmtclass=[^&]*/, "")+":fmtclass=marc";
|
||
}
|
||
|
||
function doWeb(doc, url) {
|
||
var resultsRegexp = /\/WebZ\/html\/results.html/i
|
||
|
||
if(resultsRegexp.test(url)) {
|
||
var items = Scholar.Utilities.getItemArray(doc, doc, "/WebZ/FETCH", "^[0-9]*$");
|
||
items = Scholar.selectItems(items);
|
||
|
||
if(!items) {
|
||
return true;
|
||
}
|
||
|
||
var urls = new Array();
|
||
for(var i in items) {
|
||
urls.push(reformURL(i));
|
||
}
|
||
} else {
|
||
var urls = [reformURL(url)];
|
||
}
|
||
|
||
var marc = Scholar.loadTranslator("import", "a6ee60df-1ddc-4aae-bb25-45e0537be973");
|
||
|
||
Scholar.Utilities.processDocuments(urls, function(newDoc) {
|
||
Scholar.Utilities.debug(newDoc.getElementsByTagName("body")[0].innerHTML);
|
||
var uri = newDoc.location.href;
|
||
|
||
var namespace = newDoc.documentElement.namespaceURI;
|
||
var nsResolver = namespace ? function(prefix) {
|
||
if (prefix == ''x'') return namespace; else return null;
|
||
} : null;
|
||
|
||
var elmts = newDoc.evaluate(''//table/tbody/tr[@valign="top"]'',
|
||
newDoc, nsResolver, XPathResult.ANY_TYPE, null);
|
||
|
||
var record = new marc.MARC_Record();
|
||
while(elmt = elmts.iterateNext()) {
|
||
var field = Scholar.Utilities.superCleanString(doc.evaluate(''./TD[1]/text()[1]'', elmt, nsResolver, XPathResult.ANY_TYPE, null).iterateNext().nodeValue);
|
||
var value = doc.evaluate(''./TD[2]/text()[1]'', elmt, nsResolver, XPathResult.ANY_TYPE, null).iterateNext().nodeValue;
|
||
var ind1 = value[4];
|
||
var ind2 = value[6];
|
||
value = Scholar.Utilities.cleanString(value.substr(6)).
|
||
replace(/\$([a-z0-9]) /g, record.subfield_delimiter+"$1");
|
||
if(value[0] != record.subfield_delimiter) {
|
||
value = record.subfield_delimiter+"a"+value;
|
||
}
|
||
|
||
if(field != 0) {
|
||
record.add_field(field, ind1, ind2, value);
|
||
}
|
||
}
|
||
|
||
var newItem = new Scholar.Item();
|
||
newItem.source = uri;
|
||
record.translate(newItem);
|
||
newItem.complete();
|
||
}, function() { Scholar.done(); }, null);
|
||
|
||
Scholar.wait();
|
||
}');
|
||
|
||
REPLACE INTO "translators" VALUES ('e07e9b8c-0e98-4915-bb5a-32a08cb2f365', '2006-08-07 11:36:00', 8, 'Open WorldCat', 'Simon Kornblith', 'http://partneraccess.oclc.org/',
|
||
'function detectSearch(item) {
|
||
if(item.itemType == "book" || item.itemType == "bookSection") {
|
||
return true;
|
||
}
|
||
return false;
|
||
}',
|
||
'// creates an item from an Open WorldCat document
|
||
function processOWC(doc) {
|
||
var spanTags = doc.getElementsByTagName("span");
|
||
for(var i=0; i<spanTags.length; i++) {
|
||
var spanClass = spanTags[i].getAttribute("class");
|
||
if(spanClass) {
|
||
var spanClasses = spanClass.split(" ");
|
||
if(Scholar.Utilities.inArray("Z3988", spanClasses)) {
|
||
var spanTitle = spanTags[i].getAttribute("title");
|
||
var item = new Scholar.Item();
|
||
if(Scholar.Utilities.parseContextObject(spanTitle, item)) {
|
||
item.complete();
|
||
return true;
|
||
} else {
|
||
return false;
|
||
}
|
||
}
|
||
}
|
||
}
|
||
|
||
return false;
|
||
}
|
||
|
||
function doSearch(item) {
|
||
if(item.contextObject) {
|
||
var co = item.contextObject;
|
||
} else {
|
||
var co = Scholar.Utilities.createContextObject(item);
|
||
}
|
||
|
||
Scholar.Utilities.loadDocument("http://partneraccess.oclc.org/wcpa/servlet/OpenUrl?"+co, function(doc) {
|
||
// find new COinS in the Open WorldCat page
|
||
if(processOWC(doc)) { // we got a single item page
|
||
Scholar.done();
|
||
} else { // assume we have a search results page
|
||
var items = new Array();
|
||
|
||
var namespace = doc.documentElement.namespaceURI;
|
||
var nsResolver = namespace ? function(prefix) {
|
||
if (prefix == ''x'') return namespace; else return null;
|
||
} : null;
|
||
|
||
// first try to get only books
|
||
var elmts = doc.evaluate(''//table[@class="tableLayout"]/tbody/tr/td[@class="content"]/table[@class="tableResults"]/tbody/tr[td/img[@alt="Book"]]/td/div[@class="title"]/a'', doc, nsResolver, Components.interfaces.nsIDOMXPathResult.ANY_TYPE,null);
|
||
var elmt = elmts.iterateNext();
|
||
if(!elmt) { // if that fails, look for other options
|
||
var elmts = doc.evaluate(''//table[@class="tableLayout"]/tbody/tr/td[@class="content"]/table[@class="tableResults"]/tbody/tr[td/img[@alt="Book"]]/td/div[@class="title"]/a'', doc, nsResolver, Components.interfaces.nsIDOMXPathResult.ANY_TYPE,null);
|
||
elmt = elmts.iterateNext()
|
||
}
|
||
|
||
var urlsToProcess = new Array();
|
||
do {
|
||
urlsToProcess.push(elmt.href);
|
||
} while(elmt = elmts.iterateNext());
|
||
|
||
Scholar.Utilities.processDocuments(urlsToProcess, function(doc) {
|
||
// per URL
|
||
processOWC(doc);
|
||
}, function() { // done
|
||
Scholar.done();
|
||
}, function() { // error
|
||
Scholar.done(false);
|
||
});
|
||
}
|
||
}, null);
|
||
|
||
Scholar.wait();
|
||
}');
|
||
|
||
REPLACE INTO "translators" VALUES ('11645bd1-0420-45c1-badb-53fb41eeb753', '2006-08-07 18:17:00', 8, 'CrossRef', 'Simon Kornblith', 'http://partneraccess.oclc.org/',
|
||
'function detectSearch(item) {
|
||
if(item.itemType == "journal") {
|
||
return true;
|
||
}
|
||
return false;
|
||
}',
|
||
'function processCrossRef(xmlOutput) {
|
||
xmlOutput = xmlOutput.replace(/<\?xml[^>]*\?>/, "");
|
||
|
||
// parse XML with E4X
|
||
var qr = new Namespace("http://www.crossref.org/qrschema/2.0");
|
||
try {
|
||
var xml = new XML(xmlOutput);
|
||
} catch(e) {
|
||
return false;
|
||
}
|
||
|
||
// ensure status is valid
|
||
var status = xml.qr::query_result.qr::body.qr::query.@status.toString();
|
||
if(status != "resolved" && status != "multiresolved") {
|
||
return false;
|
||
}
|
||
|
||
var query = xml.qr::query_result.qr::body.qr::query;
|
||
var item = new Scholar.Item("journalArticle");
|
||
|
||
// try to get a DOI
|
||
item.DOI = query.qr::doi.(@type=="journal_article").text().toString();
|
||
if(!item.DOI) {
|
||
item.DOI = query.qr::doi.(@type=="book_title").text().toString();
|
||
}
|
||
if(!item.DOI) {
|
||
item.DOI = query.qr::doi.(@type=="book_content").text().toString();
|
||
}
|
||
|
||
// try to get an ISSN (no print/electronic preferences)
|
||
item.ISSN = query.qr::issn[0].text().toString();
|
||
// get title
|
||
item.title = query.qr::article_title.text().toString();
|
||
// get publicationTitle
|
||
item.publicationTitle = query.qr::journal_title.text().toString();
|
||
// get author
|
||
item.creators.push(Scholar.Utilities.cleanAuthor(query.qr::author.text().toString(), "author", true));
|
||
// get volume
|
||
item.volume = query.qr::volume.text().toString();
|
||
// get issue
|
||
item.issue = query.qr::issue.text().toString();
|
||
// get year
|
||
item.date = query.qr::year.text().toString();
|
||
// get edition
|
||
item.edition = query.qr::edition_number.text().toString();
|
||
// get first page
|
||
item.pages = query.qr::first_page.text().toString();
|
||
item.complete();
|
||
return true;
|
||
}
|
||
|
||
function doSearch(item) {
|
||
if(item.contextObject) {
|
||
var co = item.contextObject;
|
||
if(co.indexOf("url_ver=") == -1) {
|
||
co = "url_ver=Z39.88-2004"+co;
|
||
}
|
||
} else {
|
||
var co = Scholar.Utilities.createContextObject(item);
|
||
}
|
||
|
||
Scholar.Utilities.HTTP.doGet("http://www.crossref.org/openurl/?"+co+"&noredirect=true", function(responseText) {
|
||
processCrossRef(responseText);
|
||
Scholar.done();
|
||
});
|
||
|
||
Scholar.wait();
|
||
}');
|
||
|
||
REPLACE INTO "translators" VALUES ('0e2235e7-babf-413c-9acf-f27cce5f059c', '2006-07-05 23:40:00', 3, 'MODS (XML)', 'Simon Kornblith', 'xml',
|
||
'Scholar.addOption("exportNotes", true);
|
||
|
||
function detectImport() {
|
||
var read = Scholar.read(512);
|
||
var modsTagRegexp = /<mods[^>]+>/
|
||
if(modsTagRegexp.test(read)) {
|
||
return true;
|
||
}
|
||
}',
|
||
'var partialItemTypes = ["bookSection", "journalArticle", "magazineArticle", "newspaperArticle"];
|
||
|
||
function doExport() {
|
||
var modsCollection = <modsCollection xmlns="http://www.loc.gov/mods/v3" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.loc.gov/mods/v3 http://www.loc.gov/standards/mods/v3/mods-3-2.xsd" />;
|
||
|
||
var item;
|
||
while(item = Scholar.nextItem()) {
|
||
var isPartialItem = Scholar.Utilities.inArray(item.itemType, partialItemTypes);
|
||
|
||
var mods = <mods />;
|
||
|
||
/** CORE FIELDS **/
|
||
|
||
// XML tag titleInfo; object field title
|
||
if(item.title) {
|
||
mods.titleInfo.title = item.title;
|
||
}
|
||
|
||
// XML tag typeOfResource/genre; object field type
|
||
var modsType, marcGenre;
|
||
if(item.itemType == "book" || item.itemType == "bookSection") {
|
||
modsType = "text";
|
||
marcGenre = "book";
|
||
} else if(item.itemType == "journalArticle" || item.itemType == "magazineArticle") {
|
||
modsType = "text";
|
||
marcGenre = "periodical";
|
||
} else if(item.itemType == "newspaperArticle") {
|
||
modsType = "text";
|
||
marcGenre = "newspaper";
|
||
} else if(item.itemType == "thesis") {
|
||
modsType = "text";
|
||
marcGenre = "theses";
|
||
} else if(item.itemType == "letter") {
|
||
modsType = "text";
|
||
marcGenre = "letter";
|
||
} else if(item.itemType == "manuscript") {
|
||
modsType = "text";
|
||
modsType.@manuscript = "yes";
|
||
} else if(item.itemType == "interview") {
|
||
modsType = "text";
|
||
marcGenre = "interview";
|
||
} else if(item.itemType == "film") {
|
||
modsType = "moving image";
|
||
marcGenre = "motion picture";
|
||
} else if(item.itemType == "artwork") {
|
||
modsType = "still image";
|
||
marcGenre = "art original";
|
||
} else if(item.itemType == "website") {
|
||
modsType = "multimedia";
|
||
marcGenre = "web site";
|
||
} else if(item.itemType == "note") {
|
||
continue;
|
||
}
|
||
mods.typeOfResource = modsType;
|
||
mods.genre += <genre authority="local">{item.itemType}</genre>;
|
||
if(marcGenre) {
|
||
mods.genre += <genre authority="marcgt">{marcGenre}</genre>;
|
||
}
|
||
|
||
// XML tag genre; object field thesisType, type
|
||
if(item.thesisType) {
|
||
mods.genre += <genre>{item.thesisType}</genre>;
|
||
}
|
||
if(item.type) {
|
||
mods.genre += <genre>{item.type}</genre>;
|
||
}
|
||
|
||
// XML tag name; object field creators
|
||
for(var j in item.creators) {
|
||
var roleTerm = "";
|
||
if(item.creators[j].creatorType == "author") {
|
||
roleTerm = "aut";
|
||
} else if(item.creators[j].creatorType == "editor") {
|
||
roleTerm = "edt";
|
||
} else if(item.creators[j].creatorType == "creator") {
|
||
roleTerm = "ctb";
|
||
}
|
||
|
||
// FIXME - currently all names are personal
|
||
mods.name += <name type="personal">
|
||
<namePart type="family">{item.creators[j].lastName}</namePart>
|
||
<namePart type="given">{item.creators[j].firstName}</namePart>
|
||
<role><roleTerm type="code" authority="marcrelator">{roleTerm}</roleTerm></role>
|
||
</name>;
|
||
}
|
||
|
||
// XML tag recordInfo.recordOrigin; used to store our generator note
|
||
//mods.recordInfo.recordOrigin = "Scholar for Firefox "+Scholar.Utilities.getVersion();
|
||
|
||
/** FIELDS ON NEARLY EVERYTHING BUT NOT A PART OF THE CORE **/
|
||
|
||
// XML tag recordInfo.recordContentSource; object field source
|
||
if(item.source) {
|
||
mods.recordInfo.recordContentSource = item.source;
|
||
}
|
||
// XML tag recordInfo.recordIdentifier; object field accessionNumber
|
||
if(item.accessionNumber) {
|
||
mods.recordInfo.recordIdentifier = item.accessionNumber;
|
||
}
|
||
|
||
// XML tag accessCondition; object field rights
|
||
if(item.rights) {
|
||
mods.accessCondition = item.rights;
|
||
}
|
||
|
||
/** SUPPLEMENTAL FIELDS **/
|
||
|
||
// XML tag relatedItem.titleInfo; object field series
|
||
if(item.seriesTitle) {
|
||
var series = <relatedItem type="series">
|
||
<titleInfo><title>{item.seriesTitle}</title></titleInfo>
|
||
</relatedItem>;
|
||
|
||
if(item.itemType == "bookSection") {
|
||
// For a book section, series info must go inside host tag
|
||
mods.relatedItem.relatedItem = series;
|
||
} else {
|
||
mods.relatedItem += series;
|
||
}
|
||
}
|
||
|
||
// Make part its own tag so we can figure out where it goes later
|
||
var part = new XML();
|
||
|
||
// XML tag detail; object field volume
|
||
if(item.volume) {
|
||
if(Scholar.Utilities.isInt(item.volume)) {
|
||
part += <detail type="volume"><number>{item.volume}</number></detail>;
|
||
} else {
|
||
part += <detail type="volume"><text>{item.volume}</text></detail>;
|
||
}
|
||
}
|
||
|
||
// XML tag detail; object field number
|
||
if(item.issue) {
|
||
if(Scholar.Utilities.isInt(item.issue)) {
|
||
part += <detail type="issue"><number>{item.issue}</number></detail>;
|
||
} else {
|
||
part += <detail type="issue"><text>{item.issue}</text></detail>;
|
||
}
|
||
}
|
||
|
||
// XML tag detail; object field section
|
||
if(item.section) {
|
||
if(Scholar.Utilities.isInt(item.section)) {
|
||
part += <detail type="section"><number>{item.section}</number></detail>;
|
||
} else {
|
||
part += <detail type="section"><text>{item.section}</text></detail>;
|
||
}
|
||
}
|
||
|
||
// XML tag detail; object field pages
|
||
if(item.pages) {
|
||
var range = Scholar.Utilities.getPageRange(item.pages);
|
||
part += <extent unit="pages"><start>{range[0]}</start><end>{range[1]}</end></extent>;
|
||
}
|
||
|
||
// Assign part if something was assigned
|
||
if(part.length() != 1) {
|
||
if(isPartialItem) {
|
||
// For a journal article, bookSection, etc., the part is the host
|
||
mods.relatedItem.part += <part>{part}</part>;
|
||
} else {
|
||
mods.part += <part>{part}</part>;
|
||
}
|
||
}
|
||
|
||
// XML tag originInfo; object fields edition, place, publisher, year, date
|
||
var originInfo = new XML();
|
||
if(item.edition) {
|
||
originInfo += <edition>{item.edition}</edition>;
|
||
}
|
||
if(item.place) {
|
||
originInfo += <place><placeTerm type="text">{item.place}</placeTerm></place>;
|
||
}
|
||
if(item.publisher) {
|
||
originInfo += <publisher>{item.publisher}</publisher>;
|
||
} else if(item.distributor) {
|
||
originInfo += <publisher>{item.distributor}</publisher>;
|
||
}
|
||
if(item.date) {
|
||
if(Scholar.Utilities.inArray(item.itemType, ["book", "bookSection"])) {
|
||
// Assume year is copyright date
|
||
var dateType = "copyrightDate";
|
||
} else if(Scholar.Utilities.inArray(item.itemType, ["journalArticle", "magazineArticle", "newspaperArticle"])) {
|
||
// Assume date is date issued
|
||
var dateType = "dateIssued";
|
||
} else {
|
||
// Assume date is date created
|
||
var dateType = "dateCreated";
|
||
}
|
||
var tag = <{dateType}>{item.date}</{dateType}>;
|
||
tag.@encoding = "iso8601";
|
||
originInfo += tag;
|
||
}
|
||
if(item.accessDate) {
|
||
originInfo += <dateCaptured encoding="iso8601">{item.accessDate}</dateCaptured>;
|
||
}
|
||
if(originInfo.length() != 1) {
|
||
if(isPartialItem) {
|
||
// For a journal article, bookSection, etc., this goes under the host
|
||
mods.relatedItem.originInfo += <originInfo>{originInfo}</originInfo>;
|
||
} else {
|
||
mods.originInfo += <originInfo>{originInfo}</originInfo>;
|
||
}
|
||
}
|
||
|
||
// XML tag identifier; object fields ISBN, ISSN
|
||
if(isPartialItem) {
|
||
var identifier = mods.relatedItem;
|
||
} else {
|
||
var identifier = mods;
|
||
}
|
||
if(item.ISBN) {
|
||
identifier.identifier += <identifier type="isbn">{item.ISBN}</identifier>;
|
||
}
|
||
if(item.ISSN) {
|
||
identifier.identifier += <identifier type="issn">{item.ISSN}</identifier>;
|
||
}
|
||
if(item.DOI) {
|
||
identifier.identifier += <identifier type="doi">{item.DOI}</identifier>;
|
||
}
|
||
|
||
// XML tag relatedItem.titleInfo; object field publication
|
||
if(item.publicationTitle) {
|
||
mods.relatedItem.titleInfo += <titleInfo><title>{item.publicationTitle}</title></titleInfo>;
|
||
}
|
||
|
||
// XML tag classification; object field callNumber
|
||
if(item.callNumber) {
|
||
mods.classification = item.callNumber;
|
||
}
|
||
|
||
// XML tag location.physicalLocation; object field archiveLocation
|
||
if(item.archiveLocation) {
|
||
mods.location.physicalLocation = item.archiveLocation;
|
||
}
|
||
|
||
// XML tag location.url; object field archiveLocation
|
||
if(item.url) {
|
||
mods.location.url = item.url;
|
||
}
|
||
|
||
// XML tag title.titleInfo; object field journalAbbreviation
|
||
if(item.journalAbbreviation) {
|
||
mods.relatedItem.titleInfo += <titleInfo type="abbreviated"><title>{item.journalAbbreviation}</title></titleInfo>;
|
||
}
|
||
|
||
if(mods.relatedItem.length() == 1 && isPartialItem) {
|
||
mods.relatedItem.@type = "host";
|
||
}
|
||
|
||
/** NOTES **/
|
||
|
||
if(Scholar.getOption("exportNotes")) {
|
||
for(var j in item.notes) {
|
||
// Add note tag
|
||
var note = <note type="content">{item.notes[j].note}</note>;
|
||
mods.note += note;
|
||
}
|
||
}
|
||
|
||
/** TAGS **/
|
||
|
||
for(var j in item.tags) {
|
||
mods.subject += <subject>{item.tags[j]}</subject>;
|
||
}
|
||
|
||
modsCollection.mods += mods;
|
||
}
|
||
|
||
Scholar.write(''<?xml version="1.0"?>''+"\n");
|
||
Scholar.write(modsCollection.toXMLString());
|
||
}
|
||
|
||
function doImport() {
|
||
var text = "";
|
||
var read;
|
||
|
||
// read in 16384 byte increments
|
||
while(read = Scholar.read(16384)) {
|
||
text += read;
|
||
}
|
||
Scholar.Utilities.debug("read in");
|
||
|
||
// eliminate <?xml ?> heading so we can parse as XML
|
||
text = text.replace(/<\?xml[^?]+\?>/, "");
|
||
|
||
// parse with E4X
|
||
var m = new Namespace("http://www.loc.gov/mods/v3");
|
||
// why does this default namespace declaration not work!?
|
||
default xml namespace = m;
|
||
var xml = new XML(text);
|
||
|
||
for each(var mods in xml.m::mods) {
|
||
Scholar.Utilities.debug("item is: ");
|
||
for(var i in mods) {
|
||
Scholar.Utilities.debug(i+" = "+mods[i].toString());
|
||
}
|
||
|
||
var newItem = new Scholar.Item();
|
||
|
||
// title
|
||
newItem.title = mods.m::titleInfo.(m::title.@type!="abbreviated").m::title;
|
||
|
||
// try to get genre from local genre
|
||
var localGenre = mods.m::genre.(@authority=="local").text().toString();
|
||
if(localGenre && Scholar.Utilities.itemTypeExists(localGenre)) {
|
||
newItem.itemType = localGenre;
|
||
} else {
|
||
// otherwise, look at the marc genre
|
||
var marcGenre = mods.m::genre.(@authority=="marcgt").text().toString();
|
||
if(marcGenre) {
|
||
if(marcGenre == "book") {
|
||
newItem.itemType = "book";
|
||
} else if(marcGenre == "periodical") {
|
||
newItem.itemType = "magazineArticle";
|
||
} else if(marcGenre == "newspaper") {
|
||
newItem.itemType = "newspaperArticle";
|
||
} else if(marcGenre == "theses") {
|
||
newItem.itemType = "thesis";
|
||
} else if(marcGenre == "letter") {
|
||
newItem.itemType = "letter";
|
||
} else if(marcGenre == "interview") {
|
||
newItem.itemType = "interview";
|
||
} else if(marcGenre == "motion picture") {
|
||
newItem.itemType = "film";
|
||
} else if(marcGenre == "art original") {
|
||
newItem.itemType = "artwork";
|
||
} else if(marcGenre == "web site") {
|
||
newItem.itemType = "website";
|
||
}
|
||
}
|
||
|
||
if(!newItem.itemType) {
|
||
newItem.itemType = "book";
|
||
}
|
||
}
|
||
|
||
var isPartialItem = Scholar.Utilities.inArray(newItem.itemType, partialItemTypes);
|
||
|
||
// TODO: thesisType, type
|
||
|
||
for each(var name in mods.m::name) {
|
||
// TODO: institutional authors
|
||
var creator = new Array();
|
||
creator.firstName = name.m::namePart.(@type=="given").text().toString();
|
||
creator.lastName = name.m::namePart.(@type=="family").text().toString();
|
||
|
||
// look for roles
|
||
var role = name.m::role.m::roleTerm.(@type=="code").(@authority=="marcrelator").text().toString();
|
||
if(role == "edt") {
|
||
creator.creatorType = "editor";
|
||
} else if(role == "ctb") {
|
||
creator.creatorType = "contributor";
|
||
} else {
|
||
creator.creatorType = "author";
|
||
}
|
||
|
||
newItem.creators.push(creator);
|
||
}
|
||
|
||
// source
|
||
newItem.source = mods.m::recordInfo.m::recordContentSource.text().toString();
|
||
// accessionNumber
|
||
newItem.accessionNumber = mods.m::recordInfo.m::recordIdentifier.text().toString();
|
||
// rights
|
||
newItem.rights = mods.m::accessCondition.text().toString();
|
||
|
||
/** SUPPLEMENTAL FIELDS **/
|
||
|
||
// series
|
||
if(newItem.itemType == "bookSection") {
|
||
newItem.seriesTitle = mods.m::relatedItem.(@type=="host").m::relatedItem.(@type=="series").m::titleInfo.m::title.text().toString();
|
||
} else {
|
||
newItem.seriesTitle = mods.m::relatedItem.(@type=="series").m::titleInfo.m::title.text().toString();
|
||
}
|
||
|
||
// get part
|
||
if(isPartialItem) {
|
||
var part = mods.m::relatedItem.m::part;
|
||
var originInfo = mods.m::relatedItem.m::originInfo;
|
||
var identifier = mods.m::relatedItem.m::identifier;
|
||
} else {
|
||
var part = mods.m::part;
|
||
var originInfo = mods.m::originInfo;
|
||
var identifier = mods.m::identifier;
|
||
}
|
||
|
||
// volume
|
||
newItem.volume = part.m::detail.(@type=="volume").m::number.text().toString();
|
||
if(!newItem.volume) {
|
||
newItem.volume = part.m::detail.(@type=="volume").m::text.text().toString();
|
||
}
|
||
|
||
// number
|
||
newItem.issue = part.m::detail.(@type=="issue").m::number.text().toString();
|
||
if(!newItem.issue) {
|
||
newItem.issue = part.m::detail.(@type=="issue").m::text.text().toString();
|
||
}
|
||
|
||
// section
|
||
newItem.section = part.m::detail.(@type=="section").m::number.text().toString();
|
||
if(!newItem.section) {
|
||
newItem.section = part.m::detail.(@type=="section").m::text.text().toString();
|
||
}
|
||
|
||
// pages
|
||
var pagesStart = part.m::extent.(@unit=="pages").m::start.text().toString();
|
||
var pagesEnd = part.m::extent.(@unit=="pages").m::end.text().toString();
|
||
if(pagesStart || pagesEnd) {
|
||
if(pagesStart && pagesEnd && pagesStart != pagesEnd) {
|
||
newItem.pages = pagesStart+"-"+pagesEnd;
|
||
} else {
|
||
newItem.pages = pagesStart+pagesEnd;
|
||
}
|
||
}
|
||
|
||
// edition
|
||
newItem.edition = originInfo.m::edition.text().toString();
|
||
// place
|
||
newItem.place = originInfo.m::place.m::placeTerm.text().toString();
|
||
// publisher/distributor
|
||
newItem.publisher = newItem.distributor = originInfo.m::publisher.text().toString();
|
||
// date
|
||
newItem.date = originInfo.m::copyrightDate.text().toString();
|
||
if(!newItem.date) {
|
||
newItem.date = originInfo.m::dateIssued.text().toString();
|
||
if(!newItem.date) {
|
||
newItem.date = originInfo.dateCreated.text().toString();
|
||
}
|
||
}
|
||
// lastModified
|
||
newItem.lastModified = originInfo.m::dateModified.text().toString();
|
||
// accessDate
|
||
newItem.accessDate = originInfo.m::dateCaptured.text().toString();
|
||
// ISBN
|
||
newItem.ISBN = identifier.(@type=="isbn").text().toString()
|
||
// ISSN
|
||
newItem.ISSN = identifier.(@type=="issn").text().toString()
|
||
// DOI
|
||
newItem.DOI = identifier.(@type=="doi").text().toString()
|
||
// publication
|
||
newItem.publicationTitle = mods.m::relatedItem.m::publication.text().toString();
|
||
// call number
|
||
newItem.callNumber = mods.m::classification.text().toString();
|
||
// archiveLocation
|
||
newItem.archiveLocation = mods.m::location.m::physicalLocation.text().toString();
|
||
// url
|
||
newItem.url = mods.m::location.m::url.text().toString();
|
||
// journalAbbreviation
|
||
newItem.journalAbbreviation = mods.m::relatedItem.(m::titleInfo.@type=="abbreviated").m::titleInfo.m::title.text().toString();
|
||
|
||
/** NOTES **/
|
||
for each(var note in mods.m::note) {
|
||
newItem.notes.push({note:note.text().toString()});
|
||
}
|
||
|
||
/** TAGS **/
|
||
for each(var subject in mods.m::subject) {
|
||
newItem.tags.push(subject.text().toString());
|
||
}
|
||
|
||
newItem.complete();
|
||
}
|
||
}');
|
||
|
||
REPLACE INTO "translators" VALUES ('14763d24-8ba0-45df-8f52-b8d1108e7ac9', '2006-07-07 12:44:00', 2, 'Biblio/DC/FOAF/PRISM/VCard (RDF/XML)', 'Simon Kornblith', 'rdf',
|
||
'Scholar.configure("getCollections", true);
|
||
Scholar.configure("dataMode", "rdf");
|
||
Scholar.addOption("exportNotes", true);
|
||
Scholar.addOption("exportFileData", true);',
|
||
'function generateSeeAlso(resource, seeAlso) {
|
||
for(var i in seeAlso) {
|
||
Scholar.RDF.addStatement(resource, n.dc+"relation", itemResources[seeAlso[i]], false);
|
||
}
|
||
}
|
||
|
||
function generateCollection(collection) {
|
||
var collectionResource = "#collection:"+collection.id;
|
||
Scholar.RDF.addStatement(collectionResource, rdf+"type", n.bib+"Collection", false);
|
||
Scholar.RDF.addStatement(collectionResource, n.dc+"title", collection.name, true);
|
||
|
||
for each(var child in collection.children) {
|
||
// add child list items
|
||
if(child.type == "collection") {
|
||
Scholar.RDF.addStatement(collectionResource, n.dcterms+"hasPart", "#collection:"+child.id, false);
|
||
// do recursive processing of collections
|
||
generateCollection(child);
|
||
} else if(itemResources[child.id]) {
|
||
Scholar.RDF.addStatement(collectionResource, n.dcterms+"hasPart", itemResources[child.id], false);
|
||
}
|
||
}
|
||
}
|
||
|
||
function handleAttachment(attachmentResource, attachment) {
|
||
Scholar.RDF.addStatement(attachmentResource, rdf+"type", n.fs+"File", false);
|
||
|
||
if(attachment.url) {
|
||
// add url as identifier
|
||
var term = Scholar.RDF.newResource();
|
||
// set term type
|
||
Scholar.RDF.addStatement(term, rdf+"type", n.dcterms+"URI", false);
|
||
// set url value
|
||
Scholar.RDF.addStatement(term, rdf+"value", attachment.url, true);
|
||
// add relationship to resource
|
||
Scholar.RDF.addStatement(attachmentResource, n.dc+"identifier", term, false);
|
||
}
|
||
|
||
// add mime type
|
||
var term = Scholar.RDF.newResource();
|
||
// set term type
|
||
Scholar.RDF.addStatement(term, rdf+"type", n.dcterms+"IMT", false);
|
||
// set mime type value
|
||
Scholar.RDF.addStatement(term, rdf+"value", attachment.mimeType, true);
|
||
// add relationship to resource
|
||
Scholar.RDF.addStatement(attachmentResource, n.dc+"format", term, false);
|
||
|
||
// add title
|
||
Scholar.RDF.addStatement(attachmentResource, n.dc+"title", attachment.title, true);
|
||
}
|
||
|
||
function doExport() {
|
||
rdf = "http://www.w3.org/1999/02/22-rdf-syntax-ns#";
|
||
|
||
n = {
|
||
bib:"http://purl.org/net/biblio#",
|
||
dc:"http://purl.org/dc/elements/1.1/",
|
||
dcterms:"http://purl.org/dc/terms/",
|
||
prism:"http://prismstandard.org/namespaces/1.2/basic/",
|
||
foaf:"http://xmlns.com/foaf/0.1/",
|
||
vcard:"http://nwalsh.com/rdf/vCard#",
|
||
fs:"http://chnm.gmu.edu/firefoxscholar/rdf#"
|
||
};
|
||
|
||
// add namespaces
|
||
for(var i in n) {
|
||
Scholar.RDF.addNamespace(i, n[i]);
|
||
}
|
||
|
||
// leave as global
|
||
itemResources = new Array();
|
||
|
||
// keep track of resources already assigned (in case two book items have the
|
||
// same ISBN, or something like that)
|
||
var usedResources = new Array();
|
||
|
||
var items = new Array();
|
||
|
||
// first, map each ID to a resource
|
||
while(item = Scholar.nextItem()) {
|
||
items.push(item);
|
||
|
||
if(item.itemType == "attachment" && item.path) {
|
||
// file is stored locally (paths are always unique)
|
||
itemResources[item.itemID] = item.path+item.filename;
|
||
} else if(item.ISBN && !usedResources["urn:isbn:"+item.ISBN]) {
|
||
itemResources[item.itemID] = "urn:isbn:"+item.ISBN;
|
||
usedResources[itemResources[item.itemID]] = true;
|
||
} else if(item.url && !usedResources[item.url]) {
|
||
itemResources[item.itemID] = item.url;
|
||
usedResources[itemResources[item.itemID]] = true;
|
||
} else {
|
||
// just specify a node ID
|
||
itemResources[item.itemID] = "#item:"+item.itemID;
|
||
}
|
||
|
||
for(var j in item.notes) {
|
||
itemResources[item.notes[j].itemID] = "#item:"+item.notes[j].itemID;
|
||
}
|
||
|
||
for each(var attachment in item.attachments) {
|
||
if(attachment.path) {
|
||
// file is stored locally (paths are always unique)
|
||
itemResources[attachment.itemID] = attachment.path+attachment.filename;
|
||
} else if(!usedResources[attachment.url]) {
|
||
// file is referenced via url, and no other item has this url
|
||
itemResources[attachment.itemID] = attachment.url;
|
||
usedResources[attachment.url] = true;
|
||
} else {
|
||
// just specify a node ID
|
||
itemResources[attachment.itemID] = "#item:"+attachment.itemID;
|
||
}
|
||
}
|
||
}
|
||
|
||
for each(item in items) {
|
||
// these items are global
|
||
resource = itemResources[item.itemID];
|
||
|
||
container = null;
|
||
containerElement = null;
|
||
section = null;
|
||
|
||
/** CORE FIELDS **/
|
||
|
||
// title
|
||
if(item.title) {
|
||
Scholar.RDF.addStatement(resource, n.dc+"title", item.title, true);
|
||
}
|
||
|
||
// type
|
||
var type = null;
|
||
if(item.itemType == "book") {
|
||
type = "Book";
|
||
} else if (item.itemType == "bookSection") {
|
||
type = "BookSection";
|
||
container = "Book";
|
||
} else if(item.itemType == "journalArticle") {
|
||
type = "Article";
|
||
container = "Journal";
|
||
} else if(item.itemType == "magazineArticle") {
|
||
type = "Article";
|
||
container = "Periodical";
|
||
} else if(item.itemType == "newspaperArticle") {
|
||
type = "Article";
|
||
container = "Newspaper";
|
||
} else if(item.itemType == "thesis") {
|
||
type = "Thesis";
|
||
} else if(item.itemType == "letter") {
|
||
type = "Letter";
|
||
} else if(item.itemType == "manuscript") {
|
||
type = "Manuscript";
|
||
} else if(item.itemType == "interview") {
|
||
type = "Interview";
|
||
} else if(item.itemType == "film") {
|
||
type = "MotionPicture";
|
||
} else if(item.itemType == "artwork") {
|
||
type = "Illustration";
|
||
} else if(item.itemType == "website") {
|
||
type = "Document";
|
||
} else if(item.itemType == "note") {
|
||
type = "Memo";
|
||
if(!Scholar.getOption("exportNotes")) {
|
||
continue;
|
||
}
|
||
} else if(item.itemType == "attachment") {
|
||
handleAttachment(resource, item);
|
||
continue;
|
||
}
|
||
if(type) {
|
||
Scholar.RDF.addStatement(resource, rdf+"type", n.bib+type, false);
|
||
}
|
||
|
||
// authors/editors/contributors
|
||
var creatorContainers = new Object();
|
||
for(var j in item.creators) {
|
||
var creator = Scholar.RDF.newResource();
|
||
Scholar.RDF.addStatement(creator, rdf+"type", n.foaf+"Person", false);
|
||
// gee. an entire vocabulary for describing people, and these aren''t even
|
||
// standardized in it. oh well. using them anyway.
|
||
Scholar.RDF.addStatement(creator, n.foaf+"surname", item.creators[j].lastName, true);
|
||
Scholar.RDF.addStatement(creator, n.foaf+"givenname", item.creators[j].firstName, true);
|
||
|
||
// in addition, these tags are not yet in Biblio, but Bruce D''Arcus
|
||
// says they will be.
|
||
if(item.creators[j].creatorType == "author") {
|
||
var cTag = "authors";
|
||
} else if(item.creators[j].creatorType == "editor") {
|
||
var cTag = "editors";
|
||
} else {
|
||
var cTag = "contributors";
|
||
}
|
||
|
||
if(!creatorContainers[cTag]) {
|
||
var creatorResource = Scholar.RDF.newResource();
|
||
// create new seq for author type
|
||
creatorContainers[cTag] = Scholar.RDF.newContainer("seq", creatorResource);
|
||
// attach container to resource
|
||
Scholar.RDF.addStatement(resource, n.bib+cTag, creatorResource, false);
|
||
}
|
||
Scholar.RDF.addContainerElement(creatorContainers[cTag], creator, false);
|
||
}
|
||
|
||
/** FIELDS ON NEARLY EVERYTHING BUT NOT A PART OF THE CORE **/
|
||
|
||
// source
|
||
if(item.source) {
|
||
Scholar.RDF.addStatement(resource, n.dc+"source", item.source, true);
|
||
}
|
||
|
||
// url
|
||
if(item.url) {
|
||
// add url as identifier
|
||
var term = Scholar.RDF.newResource();
|
||
// set term type
|
||
Scholar.RDF.addStatement(term, rdf+"type", n.dcterms+"URI", false);
|
||
// set url value
|
||
Scholar.RDF.addStatement(term, rdf+"value", attachment.url, true);
|
||
// add relationship to resource
|
||
Scholar.RDF.addStatement(resource, n.dc+"identifier", term, false);
|
||
}
|
||
|
||
// accessionNumber as generic ID
|
||
if(item.accessionNumber) {
|
||
Scholar.RDF.addStatement(resource, n.dc+"identifier", item.accessionNumber, true);
|
||
}
|
||
|
||
// rights
|
||
if(item.rights) {
|
||
Scholar.RDF.addStatement(resource, n.dc+"rights", item.rights, true);
|
||
}
|
||
|
||
/** SUPPLEMENTAL FIELDS **/
|
||
|
||
// use section to set up another container element
|
||
if(item.section) {
|
||
section = Scholar.RDF.newResource(); // leave as global
|
||
// set section type
|
||
Scholar.RDF.addStatement(section, rdf+"type", n.bib+"Part", false);
|
||
// set section title
|
||
Scholar.RDF.addStatement(section, n.dc+"title", item.section, true);
|
||
// add relationship to resource
|
||
Scholar.RDF.addStatement(resource, n.dc+"isPartOf", section, false);
|
||
}
|
||
|
||
// generate container
|
||
if(container) {
|
||
if(item.ISSN && !Scholar.RDF.getArcsIn("urn:issn:"+item.ISSN)) {
|
||
// use ISSN as container URI if no other item is
|
||
containerElement = "urn:issn:"+item.ISSN
|
||
} else {
|
||
containerElement = Scholar.RDF.newResource();
|
||
}
|
||
// attach container to section (if exists) or resource
|
||
Scholar.RDF.addStatement((section ? section : resource), n.dcterms+"isPartOf", containerElement, false);
|
||
// add container type
|
||
Scholar.RDF.addStatement(containerElement, rdf+"type", n.bib+container, false);
|
||
}
|
||
|
||
// ISSN
|
||
if(item.ISSN) {
|
||
Scholar.RDF.addStatement((containerElement ? containerElement : resource), n.dc+"identifier", "ISSN "+item.ISSN, true);
|
||
}
|
||
|
||
// ISBN
|
||
if(item.ISBN) {
|
||
Scholar.RDF.addStatement((containerElement ? containerElement : resource), n.dc+"identifier", "ISBN "+item.ISBN, true);
|
||
}
|
||
|
||
// DOI
|
||
if(item.DOI) {
|
||
Scholar.RDF.addStatement((containerElement ? containerElement : resource), n.dc+"identifier", "DOI "+item.DOI, true);
|
||
}
|
||
|
||
// publication gets linked to container via isPartOf
|
||
if(item.publicationTitle) {
|
||
Scholar.RDF.addStatement((containerElement ? containerElement : resource), n.dc+"title", item.publicationTitle, true);
|
||
}
|
||
|
||
// series also linked in
|
||
if(item.seriesTitle) {
|
||
var series = Scholar.RDF.newResource();
|
||
// set series type
|
||
Scholar.RDF.addStatement(series, rdf+"type", n.bib+"Series", false);
|
||
// set series title
|
||
Scholar.RDF.addStatement(series, n.dc+"title", item.seriesTitle, true);
|
||
// add relationship to resource
|
||
Scholar.RDF.addStatement((containerElement ? containerElement : resource), n.dcterms+"isPartOf", series, false);
|
||
}
|
||
|
||
// volume
|
||
if(item.volume) {
|
||
Scholar.RDF.addStatement((containerElement ? containerElement : resource), n.prism+"volume", item.volume, true);
|
||
}
|
||
// number
|
||
if(item.issue) {
|
||
Scholar.RDF.addStatement((containerElement ? containerElement : resource), n.prism+"number", item.issue, true);
|
||
}
|
||
// edition
|
||
if(item.edition) {
|
||
Scholar.RDF.addStatement(resource, n.prism+"edition", item.edition, true);
|
||
}
|
||
// publisher/distributor and place
|
||
if(item.publisher || item.distributor || item.place) {
|
||
var organization = Scholar.RDF.newResource();
|
||
// set organization type
|
||
Scholar.RDF.addStatement(organization, rdf+"type", n.foaf+"Organization", false);
|
||
// add relationship to resource
|
||
Scholar.RDF.addStatement(resource, n.dc+"publisher", organization, false);
|
||
// add publisher/distributor
|
||
if(item.publisher) {
|
||
Scholar.RDF.addStatement(organization, n.foaf+"name", item.publisher, true);
|
||
} else if(item.distributor) {
|
||
Scholar.RDF.addStatement(organization, n.foaf+"name", item.distributor, true);
|
||
}
|
||
// add place
|
||
if(item.place) {
|
||
var address = Scholar.RDF.newResource();
|
||
// set address type
|
||
Scholar.RDF.addStatement(address, rdf+"type", n.vcard+"Address", false);
|
||
// set address locality
|
||
Scholar.RDF.addStatement(address, n.vcard+"locality", item.place, true);
|
||
// add relationship to organization
|
||
Scholar.RDF.addStatement(organization, n.vcard+"adr", address, false);
|
||
}
|
||
}
|
||
// date/year
|
||
if(item.date) {
|
||
Scholar.RDF.addStatement(resource, n.dc+"date", item.date, true);
|
||
}
|
||
if(item.accessDate) { // use date submitted for access date?
|
||
Scholar.RDF.addStatement(resource, n.dcterms+"dateSubmitted", item.accessDate, true);
|
||
}
|
||
|
||
// callNumber
|
||
if(item.callNumber) {
|
||
var term = Scholar.RDF.newResource();
|
||
// set term type
|
||
Scholar.RDF.addStatement(term, rdf+"type", n.dcterms+"LCC", false);
|
||
// set callNumber value
|
||
Scholar.RDF.addStatement(term, rdf+"value", item.callNumber, true);
|
||
// add relationship to resource
|
||
Scholar.RDF.addStatement(resource, n.dc+"subject", term, false);
|
||
}
|
||
|
||
// archiveLocation
|
||
if(item.archiveLocation) {
|
||
Scholar.RDF.addStatement(resource, n.dc+"coverage", item.archiveLocation, true);
|
||
}
|
||
|
||
// type (not itemType)
|
||
if(item.type) {
|
||
Scholar.RDF.addStatement(resource, n.dc+"type", item.type, true);
|
||
} else if(item.thesisType) {
|
||
Scholar.RDF.addStatement(resource, n.dc+"type", item.thesisType, true);
|
||
}
|
||
|
||
// THIS IS NOT YET IN THE BIBLIO NAMESPACE, BUT BRUCE D''ARCUS HAS SAID
|
||
// IT WILL BE SOON
|
||
if(item.pages) {
|
||
Scholar.RDF.addStatement(resource, n.bib+"pages", item.pages, true);
|
||
}
|
||
|
||
// journalAbbreviation
|
||
if(item.journalAbbreviation) {
|
||
Scholar.RDF.addStatement((containerElement ? containerElement : resource), n.dcterms+"alternative", item.journalAbbreviation, true);
|
||
}
|
||
|
||
/** NOTES **/
|
||
|
||
if(Scholar.getOption("exportNotes")) {
|
||
for(var j in item.notes) {
|
||
var noteResource = itemResources[item.notes[j].itemID];
|
||
|
||
// add note tag
|
||
Scholar.RDF.addStatement(noteResource, rdf+"type", n.bib+"Memo", false);
|
||
// add note value
|
||
Scholar.RDF.addStatement(noteResource, rdf+"value", item.notes[j].note, true);
|
||
// add relationship between resource and note
|
||
Scholar.RDF.addStatement(resource, n.dcterms+"isReferencedBy", noteResource, false);
|
||
|
||
// Add see also info to RDF
|
||
generateSeeAlso(resource, item.notes[j].seeAlso);
|
||
}
|
||
|
||
if(item.note) {
|
||
Scholar.RDF.addStatement(resource, rdf+"value", item.note, true);
|
||
}
|
||
}
|
||
|
||
/** FILES **/
|
||
|
||
for each(var attachment in item.attachments) {
|
||
var attachmentResource = itemResources[attachment.itemID];
|
||
Scholar.RDF.addStatement(resource, n.dc+"relation", attachmentResource, false);
|
||
handleAttachment(attachmentResource, attachment);
|
||
}
|
||
|
||
/** TAGS **/
|
||
|
||
for(var j in item.tags) {
|
||
Scholar.RDF.addStatement(resource, n.dc+"subject", item.tags[j], true);
|
||
}
|
||
|
||
// Add see also info to RDF
|
||
generateSeeAlso(resource, item.seeAlso);
|
||
}
|
||
|
||
/** RDF COLLECTION STRUCTURE **/
|
||
var collection;
|
||
while(collection = Scholar.nextCollection()) {
|
||
generateCollection(collection);
|
||
}
|
||
}');
|
||
|
||
REPLACE INTO "translators" VALUES ('6e372642-ed9d-4934-b5d1-c11ac758ebb7', '2006-07-05 23:40:00', 2, 'Unqualified Dublin Core (RDF/XML)', 'Simon Kornblith', 'rdf',
|
||
'Scholar.configure("dataMode", "rdf");',
|
||
'function doExport() {
|
||
var dc = "http://purl.org/dc/elements/1.1/";
|
||
Scholar.RDF.addNamespace("dc", dc);
|
||
|
||
var item;
|
||
while(item = Scholar.nextItem()) {
|
||
if(item.itemType == "note") {
|
||
continue;
|
||
}
|
||
|
||
var resource;
|
||
if(item.ISBN) {
|
||
resource = "urn:isbn:"+item.ISBN;
|
||
} else if(item.url) {
|
||
resource = item.url;
|
||
} else {
|
||
// just specify a node ID
|
||
resource = Scholar.RDF.newResource();
|
||
}
|
||
|
||
/** CORE FIELDS **/
|
||
|
||
// title
|
||
if(item.title) {
|
||
Scholar.RDF.addStatement(resource, dc+"title", item.title, true);
|
||
}
|
||
|
||
// type
|
||
Scholar.RDF.addStatement(resource, dc+"type", item.itemType, true);
|
||
|
||
// creators
|
||
for(var j in item.creators) {
|
||
// put creators in lastName, firstName format (although DC doesn''t specify)
|
||
var creator = item.creators[j].lastName;
|
||
if(item.creators[j].firstName) {
|
||
creator += ", "+item.creators[j].firstName;
|
||
}
|
||
|
||
if(item.creators[j].creatorType == "author") {
|
||
Scholar.RDF.addStatement(resource, dc+"creator", creator, true);
|
||
} else {
|
||
Scholar.RDF.addStatement(resource, dc+"contributor", creator, true);
|
||
}
|
||
}
|
||
|
||
/** FIELDS ON NEARLY EVERYTHING BUT NOT A PART OF THE CORE **/
|
||
|
||
// source
|
||
if(item.source) {
|
||
Scholar.RDF.addStatement(resource, dc+"source", item.source, true);
|
||
}
|
||
|
||
// accessionNumber as generic ID
|
||
if(item.accessionNumber) {
|
||
Scholar.RDF.addStatement(resource, dc+"identifier", item.accessionNumber, true);
|
||
}
|
||
|
||
// rights
|
||
if(item.rights) {
|
||
Scholar.RDF.addStatement(resource, dc+"rights", item.rights, true);
|
||
}
|
||
|
||
/** SUPPLEMENTAL FIELDS **/
|
||
|
||
// TODO - create text citation and OpenURL citation to handle volume, number, pages, issue, place
|
||
|
||
// publisher/distributor
|
||
if(item.publisher) {
|
||
Scholar.RDF.addStatement(resource, dc+"publisher", item.publisher, true);
|
||
} else if(item.distributor) {
|
||
Scholar.RDF.addStatement(resource, dc+"publisher", item.distributor, true);
|
||
}
|
||
// date/year
|
||
if(item.date) {
|
||
Scholar.RDF.addStatement(resource, dc+"date", item.date, true);
|
||
}
|
||
|
||
// ISBN/ISSN/DOI
|
||
if(item.ISBN) {
|
||
Scholar.RDF.addStatement(resource, dc+"identifier", "ISBN "+item.ISBN, true);
|
||
}
|
||
if(item.ISSN) {
|
||
Scholar.RDF.addStatement(resource, dc+"identifier", "ISSN "+item.ISSN, true);
|
||
}
|
||
if(item.DOI) {
|
||
Scholar.RDF.addStatement(resource, dc+"identifier", "DOI "+item.DOI, true);
|
||
}
|
||
|
||
// callNumber
|
||
if(item.callNumber) {
|
||
Scholar.RDF.addStatement(resource, dc+"identifier", item.callNumber, true);
|
||
}
|
||
|
||
// archiveLocation
|
||
if(item.archiveLocation) {
|
||
Scholar.RDF.addStatement(resource, dc+"coverage", item.archiveLocation, true);
|
||
}
|
||
}
|
||
}');
|
||
|
||
REPLACE INTO "translators" VALUES ('5e3ad958-ac79-463d-812b-a86a9235c28f', '2006-07-15 17:09:00', 1, 'RDF', 'Simon Kornblith', 'rdf',
|
||
'Scholar.configure("dataMode", "rdf");
|
||
|
||
function detectImport() {
|
||
// unfortunately, Mozilla will let you create a data source from any type
|
||
// of XML, so we need to make sure there are actually nodes
|
||
|
||
var nodes = Scholar.RDF.getAllResources();
|
||
if(nodes) {
|
||
return true;
|
||
}
|
||
}',
|
||
'// gets the first result set for a property that can be encoded in multiple
|
||
// ontologies
|
||
function getFirstResults(node, properties, onlyOneString) {
|
||
for(var i=0; i<properties.length; i++) {
|
||
var result = Scholar.RDF.getTargets(node, properties[i]);
|
||
if(result) {
|
||
if(onlyOneString) {
|
||
// onlyOneString means we won''t return nsIRDFResources, only
|
||
// actual literals
|
||
if(typeof(result[0]) != "object") {
|
||
return result[0];
|
||
}
|
||
} else {
|
||
return result;
|
||
}
|
||
}
|
||
}
|
||
return; // return undefined on failure
|
||
}
|
||
|
||
// adds creators to an item given a list of creator nodes
|
||
function handleCreators(newItem, creators, creatorType) {
|
||
if(!creators) {
|
||
return;
|
||
}
|
||
|
||
if(typeof(creators[0]) != "string") { // see if creators are in a container
|
||
try {
|
||
var creators = Scholar.RDF.getContainerElements(creators[0]);
|
||
} catch(e) {}
|
||
}
|
||
|
||
if(typeof(creators[0]) == "string") { // support creators encoded as strings
|
||
for(var i in creators) {
|
||
if(typeof(creators[i]) != "object") {
|
||
newItem.creators.push(Scholar.Utilities.cleanAuthor(creators[i], creatorType, true));
|
||
}
|
||
}
|
||
} else { // also support foaf
|
||
for(var i in creators) {
|
||
var type = Scholar.RDF.getTargets(creators[i], rdf+"type");
|
||
if(type) {
|
||
type = Scholar.RDF.getResourceURI(type[0]);
|
||
if(type == n.foaf+"Person") { // author is FOAF type person
|
||
var creator = new Array();
|
||
creator.lastName = getFirstResults(creators[i],
|
||
[n.foaf+"surname", n.foaf+"family_name"], true);
|
||
creator.firstName = getFirstResults(creators[i],
|
||
[n.foaf+"givenname", n.foaf+"firstName"], true);
|
||
creator.creatorType = creatorType;
|
||
newItem.creators.push(creator);
|
||
}
|
||
}
|
||
}
|
||
}
|
||
}
|
||
|
||
// gets attachment info
|
||
function handleAttachment(node, attachment) {
|
||
if(!attachment) {
|
||
attachment = new Array();
|
||
}
|
||
|
||
attachment.title = getFirstResults(node, [n.dc+"title"], true);
|
||
|
||
var identifiers = getFirstResults(node, [n.dc+"identifier"]);
|
||
for each(var identifier in identifiers) {
|
||
if(typeof(identifier) != "string") {
|
||
var identifierType = Scholar.RDF.getTargets(identifier, rdf+"type");
|
||
if(identifierType) {
|
||
identifierType = Scholar.RDF.getResourceURI(identifierType[0]);
|
||
|
||
if(identifierType == n.dcterms+"URI") { // uri is url
|
||
attachment.url = getFirstResults(identifier, [rdf+"value"], true);
|
||
}
|
||
}
|
||
}
|
||
}
|
||
|
||
var formats = getFirstResults(node, [n.dc+"format"]);
|
||
for each(var format in formats) {
|
||
if(typeof(format) != "string") {
|
||
var formatType = Scholar.RDF.getTargets(format, rdf+"type");
|
||
if(formatType) {
|
||
formatType = Scholar.RDF.getResourceURI(formatType[0]);
|
||
|
||
if(formatType == n.dcterms+"IMT") { // uri is url
|
||
attachment.mimeType = getFirstResults(format, [rdf+"value"], true);
|
||
}
|
||
}
|
||
}
|
||
}
|
||
|
||
var stringNode = node;
|
||
if(typeof(stringNode) != "string") {
|
||
stringNode = Scholar.RDF.getResourceURI(stringNode);
|
||
}
|
||
if(stringNode.substr(0, 8) == "file:///") {
|
||
// not a protocol specifier; we have a path name
|
||
attachment.path = stringNode;
|
||
}
|
||
|
||
return attachment;
|
||
}
|
||
|
||
// processes collections recursively
|
||
function processCollection(node, collection) {
|
||
if(!collection) {
|
||
collection = new Array();
|
||
}
|
||
collection.type = "collection";
|
||
collection.name = getFirstResults(node, [n.dc+"title"], true);
|
||
collection.children = new Array();
|
||
|
||
// check for children
|
||
var children = getFirstResults(node, [n.dcterms+"hasPart"]);
|
||
for each(var child in children) {
|
||
var type = Scholar.RDF.getTargets(child, rdf+"type");
|
||
if(type) {
|
||
type = Scholar.RDF.getResourceURI(type[0]);
|
||
}
|
||
|
||
if(type == n.bib+"Collection") {
|
||
// for collections, process recursively
|
||
collection.children.push(processCollection(child));
|
||
} else {
|
||
// all other items are added by ID
|
||
collection.children.push({id:Scholar.RDF.getResourceURI(child), type:"item"});
|
||
}
|
||
}
|
||
|
||
return collection;
|
||
}
|
||
|
||
// gets the node with a given type from an array
|
||
function getNodeByType(nodes, type) {
|
||
if(!nodes) {
|
||
return false;
|
||
}
|
||
|
||
for each(node in nodes) {
|
||
var nodeType = Scholar.RDF.getTargets(node, rdf+"type");
|
||
if(nodeType) {
|
||
nodeType = Scholar.RDF.getResourceURI(nodeType[0]);
|
||
if(nodeType == type) { // we have a node of the correct type
|
||
return node;
|
||
}
|
||
}
|
||
}
|
||
return false;
|
||
}
|
||
|
||
function doImport() {
|
||
rdf = "http://www.w3.org/1999/02/22-rdf-syntax-ns#";
|
||
|
||
n = {
|
||
bib:"http://purl.org/net/biblio#",
|
||
dc:"http://purl.org/dc/elements/1.1/",
|
||
dcterms:"http://purl.org/dc/terms/",
|
||
prism:"http://prismstandard.org/namespaces/1.2/basic/",
|
||
foaf:"http://xmlns.com/foaf/0.1/",
|
||
vcard:"http://nwalsh.com/rdf/vCard#",
|
||
fs:"http://chnm.gmu.edu/firefoxscholar/rdf#"
|
||
};
|
||
|
||
callNumberTypes = [
|
||
n.dcterms+"LCC", n.dcterms+"DDC", n.dcterms+"UDC"
|
||
];
|
||
|
||
var nodes = Scholar.RDF.getAllResources();
|
||
if(!nodes) {
|
||
return false;
|
||
}
|
||
|
||
// keep track of collections while we''re looping through
|
||
var collections = new Array();
|
||
|
||
for each(var node in nodes) {
|
||
var newItem = new Scholar.Item();
|
||
newItem.itemID = Scholar.RDF.getResourceURI(node);
|
||
var container = undefined;
|
||
|
||
// type
|
||
var type = Scholar.RDF.getTargets(node, rdf+"type");
|
||
// also deal with type detection based on parts, so we can differentiate
|
||
// magazine and journal articles, and find container elements
|
||
var isPartOf = getFirstResults(node, [n.dcterms+"isPartOf"]);
|
||
|
||
if(type) {
|
||
type = Scholar.RDF.getResourceURI(type[0]);
|
||
|
||
if(type == n.bib+"Book") {
|
||
newItem.itemType = "book";
|
||
} else if(type == n.bib+"BookSection") {
|
||
newItem.itemType = "bookSection";
|
||
container = getNodeByType(isPartOf, n.bib+"Book");
|
||
} else if(type == n.bib+"Article") { // choose between journal,
|
||
// newspaper, and magazine
|
||
// articles
|
||
if(container = getNodeByType(isPartOf, n.bib+"Journal")) {
|
||
newItem.itemType = "journalArticle";
|
||
} else if(container = getNodeByType(isPartOf, n.bib+"Periodical")) {
|
||
newItem.itemType = "magazineArticle";
|
||
} else if(container = getNodeByType(isPartOf, n.bib+"Newspaper")) {
|
||
newItem.itemType = "newspaperArticle";
|
||
}
|
||
} else if(type == n.bib+"Thesis") {
|
||
newItem.itemType = "thesis";
|
||
} else if(type == n.bib+"Letter") {
|
||
newItem.itemType = "letter";
|
||
} else if(type == n.bib+"Manuscript") {
|
||
newItem.itemType = "manuscript";
|
||
} else if(type == n.bib+"Interview") {
|
||
newItem.itemType = "interview";
|
||
} else if(type == n.bib+"MotionPicture") {
|
||
newItem.itemType = "film";
|
||
} else if(type == n.bib+"Illustration") {
|
||
newItem.itemType = "illustration";
|
||
} else if(type == n.bib+"Document") {
|
||
newItem.itemType = "website";
|
||
} else if(type == n.bib+"Memo") {
|
||
// check to see if this note is independent
|
||
var arcs = Scholar.RDF.getArcsIn(node);
|
||
var skip = false;
|
||
for each(var arc in arcs) {
|
||
arc = Scholar.RDF.getResourceURI(arc);
|
||
if(arc != n.dc+"relation" && arc != n.dcterms+"hasPart") {
|
||
// related to another item by some arc besides see also
|
||
skip = true;
|
||
}
|
||
}
|
||
if(skip) {
|
||
continue;
|
||
}
|
||
|
||
newItem.itemType = "note";
|
||
} else if(type == n.bib+"Collection") {
|
||
// skip collections until all the items are done
|
||
collections.push(node);
|
||
continue;
|
||
} else if(type == n.fs+"File") {
|
||
// check to see if file is independent
|
||
var arcs = Scholar.RDF.getArcsIn(node);
|
||
if(arcs.length) {
|
||
continue;
|
||
}
|
||
|
||
// process as file
|
||
newItem.itemType = "attachment";
|
||
handleAttachment(node, newItem);
|
||
Scholar.Utilities.debug(newItem);
|
||
newItem.complete();
|
||
continue;
|
||
} else { // default to book
|
||
newItem.itemType = "book";
|
||
}
|
||
}
|
||
|
||
// title
|
||
newItem.title = getFirstResults(node, [n.dc+"title"], true);
|
||
if(newItem.itemType != "note" && !newItem.title) { // require the title
|
||
// (if not a note)
|
||
continue;
|
||
}
|
||
|
||
// regular author-type creators
|
||
var creators = getFirstResults(node, [n.bib+"authors", n.dc+"creator"]);
|
||
handleCreators(newItem, creators, "author");
|
||
// editors
|
||
var creators = getFirstResults(node, [n.bib+"editors"]);
|
||
handleCreators(newItem, creators, "editor");
|
||
// contributors
|
||
var creators = getFirstResults(node, [n.bib+"contributors"]);
|
||
handleCreators(newItem, creators, "contributor");
|
||
|
||
// source
|
||
newItem.source = getFirstResults(node, [n.dc+"source"], true);
|
||
|
||
// rights
|
||
newItem.rights = getFirstResults(node, [n.dc+"rights"], true);
|
||
|
||
// section
|
||
var section = getNodeByType(isPartOf, n.bib+"Part");
|
||
if(section) {
|
||
newItem.section = getFirstResults(section, [n.dc+"title"], true);
|
||
}
|
||
|
||
// publication
|
||
if(container) {
|
||
newItem.publicationTitle = getFirstResults(container, [n.dc+"title"], true);
|
||
}
|
||
|
||
// series
|
||
var series = getNodeByType(isPartOf, n.bib+"Series");
|
||
if(series) {
|
||
newItem.seriesTitle = getFirstResults(container, [n.dc+"title"], true);
|
||
}
|
||
|
||
// volume
|
||
newItem.volume = getFirstResults((container ? container : node), [n.prism+"volume"], true);
|
||
|
||
// number
|
||
newItem.issue = getFirstResults((container ? container : node), [n.prism+"number"], true);
|
||
|
||
// edition
|
||
newItem.edition = getFirstResults(node, [n.prism+"edition"], true);
|
||
|
||
// publisher
|
||
var publisher = getFirstResults(node, [n.dc+"publisher"]);
|
||
if(publisher) {
|
||
if(typeof(publisher[0]) == "string") {
|
||
newItem.publisher = publisher[0];
|
||
} else {
|
||
var type = Scholar.RDF.getTargets(publisher[0], rdf+"type");
|
||
if(type) {
|
||
type = Scholar.RDF.getResourceURI(type[0]);
|
||
if(type == n.foaf+"Organization") { // handle foaf organizational publishers
|
||
newItem.publisher = getFirstResults(publisher[0], [n.foaf+"name"], true);
|
||
var place = getFirstResults(publisher[0], [n.vcard+"adr"]);
|
||
if(place) {
|
||
newItem.place = getFirstResults(place[0], [n.vcard+"locality"]);
|
||
}
|
||
}
|
||
}
|
||
}
|
||
}
|
||
|
||
// (this will get ignored except for films, where we encode distributor as publisher)
|
||
newItem.distributor = newItem.publisher;
|
||
|
||
// date
|
||
newItem.date = getFirstResults(node, [n.dc+"date"], true);
|
||
// accessDate
|
||
newItem.accessDate = getFirstResults(node, [n.dcterms+"dateSubmitted"], true);
|
||
// lastModified
|
||
newItem.lastModified = getFirstResults(node, [n.dcterms+"modified"], true);
|
||
|
||
// identifier
|
||
var identifiers = getFirstResults(node, [n.dc+"identifier"]);
|
||
if(container) {
|
||
var containerIdentifiers = getFirstResults(container, [n.dc+"identifier"]);
|
||
// concatenate sets of identifiers
|
||
if(containerIdentifiers) {
|
||
if(identifiers) {
|
||
identifiers = identifiers.concat(containerIdentifiers);
|
||
} else {
|
||
identifiers = containerIdentifiers;
|
||
}
|
||
}
|
||
}
|
||
|
||
if(identifiers) {
|
||
for(var i in identifiers) {
|
||
var beforeSpace = identifiers[i].substr(0, identifiers[i].indexOf(" ")).toUpperCase();
|
||
|
||
if(beforeSpace == "ISBN") {
|
||
newItem.ISBN = identifiers[i].substr(5).toUpperCase();
|
||
} else if(beforeSpace == "ISSN") {
|
||
newItem.ISSN = identifiers[i].substr(5).toUpperCase();
|
||
} else if(beforeSpace == "DOI") {
|
||
newItem.DOI = identifiers[i].substr(4);
|
||
} else if(!newItem.accessionNumber) {
|
||
newItem.accessionNumber = identifiers[i];
|
||
}
|
||
}
|
||
}
|
||
|
||
// archiveLocation
|
||
newItem.archiveLocation = getFirstResults(node, [n.dc+"coverage"], true);
|
||
|
||
// type
|
||
newItem.type = newItem.thesisType = getFirstResults(node, [n.dc+"type"], true);
|
||
|
||
// journalAbbreviation
|
||
newItem.journalAbbreviation = getFirstResults((container ? container : node), [n.dcterms+"alternative"], true);
|
||
|
||
// see also
|
||
var relations;
|
||
if(relations = getFirstResults(node, [n.dc+"relation"])) {
|
||
for each(var relation in relations) {
|
||
newItem.seeAlso.push(Scholar.RDF.getResourceURI(relation));
|
||
}
|
||
}
|
||
|
||
/** NOTES **/
|
||
|
||
var referencedBy = Scholar.RDF.getTargets(node, n.dcterms+"isReferencedBy");
|
||
for each(var referentNode in referencedBy) {
|
||
var type = Scholar.RDF.getTargets(referentNode, rdf+"type");
|
||
if(type && Scholar.RDF.getResourceURI(type[0]) == n.bib+"Memo") {
|
||
// if this is a memo
|
||
var note = new Array();
|
||
note.note = getFirstResults(referentNode, [rdf+"value", n.dc+"description"], true);
|
||
if(note.note != undefined) {
|
||
// handle see also
|
||
var relations;
|
||
if(relations = getFirstResults(referentNode, [n.dc+"relation"])) {
|
||
note.seeAlso = new Array();
|
||
for each(var relation in relations) {
|
||
note.seeAlso.push(Scholar.RDF.getResourceURI(relation));
|
||
}
|
||
}
|
||
|
||
// add note
|
||
newItem.notes.push(note);
|
||
}
|
||
}
|
||
}
|
||
|
||
if(newItem.itemType == "note") {
|
||
// add note for standalone
|
||
newItem.note = getFirstResults(node, [rdf+"value", n.dc+"description"], true);
|
||
}
|
||
|
||
/** TAGS **/
|
||
|
||
var subjects = getFirstResults(node, [n.dc+"subject"]);
|
||
for each(var subject in subjects) {
|
||
if(typeof(subject) == "string") { // a regular tag
|
||
newItem.tags.push(subject);
|
||
} else { // a call number
|
||
var type = Scholar.RDF.getTargets(subject, rdf+"type");
|
||
if(type) {
|
||
type = Scholar.RDF.getResourceURI(type[0]);
|
||
if(Scholar.Utilities.inArray(type, callNumberTypes)) {
|
||
newItem.callNumber = getFirstResults(subject, [rdf+"value"], true);
|
||
}
|
||
}
|
||
}
|
||
}
|
||
|
||
/* ATTACHMENTS */
|
||
var relations = getFirstResults(node, [n.dc+"relation"]);
|
||
for each(var relation in relations) {
|
||
var type = Scholar.RDF.getTargets(relation, rdf+"type");
|
||
if(type) {
|
||
type = Scholar.RDF.getResourceURI(type[0]);
|
||
if(type == n.fs+"File") {
|
||
newItem.attachments.push(handleAttachment(relation));
|
||
}
|
||
}
|
||
}
|
||
|
||
newItem.complete();
|
||
}
|
||
|
||
/* COLLECTIONS */
|
||
|
||
for each(var collection in collections) {
|
||
if(!Scholar.RDF.getArcsIn(collection)) {
|
||
var newCollection = new Scholar.Collection();
|
||
processCollection(collection, newCollection);
|
||
newCollection.complete();
|
||
}
|
||
}
|
||
}');
|
||
|
||
REPLACE INTO "translators" VALUES ('32d59d2d-b65a-4da4-b0a3-bdd3cfb979e7', '2006-08-08 17:12:00', 3, 'RIS', 'Simon Kornblith', 'ris',
|
||
'Scholar.configure("dataMode", "line");
|
||
Scholar.addOption("exportNotes", true);
|
||
|
||
function detectImport() {
|
||
var line;
|
||
while(line = Scholar.read()) {
|
||
if(line.replace(/\s/g, "") != "") {
|
||
if(line.substr(0, 6) == "TY - ") {
|
||
return true;
|
||
} else {
|
||
return false;
|
||
}
|
||
}
|
||
}
|
||
}',
|
||
'var itemsWithYears = ["book", "bookSection", "thesis", "film"];
|
||
|
||
var fieldMap = {
|
||
ID:"itemID",
|
||
T1:"title",
|
||
T3:"seriesTitle",
|
||
JF:"publicationTitle",
|
||
VL:"volume",
|
||
IS:"issue",
|
||
CP:"place",
|
||
PB:"publisher"
|
||
};
|
||
|
||
var inputFieldMap = {
|
||
TI:"title",
|
||
CT:"title",
|
||
JO:"publicationTitle",
|
||
CY:"place"
|
||
};
|
||
|
||
// TODO: figure out if these are the best types for letter, interview, website, manuscript
|
||
var typeMap = {
|
||
book:"BOOK",
|
||
bookSection:"CHAP",
|
||
journalArticle:"JOUR",
|
||
magazineArticle:"MGZN",
|
||
newspaperArticle:"NEWS",
|
||
thesis:"THES",
|
||
letter:"PCOMM",
|
||
manuscript:"UNPB",
|
||
interview:"PCOMM",
|
||
film:"MPCT",
|
||
artwork:"ART",
|
||
website:"ELEC"
|
||
};
|
||
|
||
// supplements outputTypeMap for importing
|
||
// TODO: BILL, CASE, COMP, CONF, DATA, HEAR, MUSIC, PAT, SOUND, STAT
|
||
var inputTypeMap = {
|
||
ABST:"journalArticle",
|
||
ADVS:"film",
|
||
CTLG:"magazineArticle",
|
||
GEN:"book",
|
||
INPR:"manuscript",
|
||
JFULL:"journalArticle",
|
||
MAP:"artwork",
|
||
PAMP:"book",
|
||
RPRT:"book",
|
||
SER:"book",
|
||
SLIDE:"artwork",
|
||
UNBILL:"manuscript",
|
||
VIDEO:"film"
|
||
};
|
||
|
||
function processTag(item, tag, value) {
|
||
if(fieldMap[tag]) {
|
||
item[fieldMap[tag]] = value;
|
||
} else if(inputFieldMap[tag]) {
|
||
item[inputFieldMap[tag]] = value;
|
||
} else if(tag == "TY") {
|
||
// look for type
|
||
|
||
// first check typeMap
|
||
for(var i in typeMap) {
|
||
if(value == typeMap[i]) {
|
||
item.itemType = i;
|
||
}
|
||
}
|
||
// then check inputTypeMap
|
||
if(!item.itemType) {
|
||
if(inputTypeMap[value]) {
|
||
item.itemType = inputTypeMap[value];
|
||
} else {
|
||
// default to generic from inputTypeMap
|
||
item.itemType = inputTypeMap["GEN"];
|
||
}
|
||
}
|
||
} else if(tag == "BT") {
|
||
// ignore, unless this is a book or unpublished work, as per spec
|
||
if(item.itemType == "book" || item.itemType == "manuscript") {
|
||
item.title = value;
|
||
}
|
||
} else if(tag == "A1" || tag == "AU") {
|
||
// primary author
|
||
var names = value.split(",");
|
||
item.creators.push({lastName:names[0], firstName:names[1], creatorType:"author"});
|
||
} else if(tag == "A2" || tag == "ED") {
|
||
// contributing author
|
||
var names = value.split(",");
|
||
item.creators.push({lastName:names[0], firstName:names[1], creatorType:"contributor"});
|
||
} else if(tag == "Y1" || tag == "PY") {
|
||
// year or date
|
||
var dateParts = value.split("/");
|
||
|
||
if(dateParts.length == 1) {
|
||
// technically, if there''s only one date part, the file isn''t valid
|
||
// RIS, but EndNote accepts this, so we have to too
|
||
item.date = value+"-00-00";
|
||
} else if(dateParts[1].length == 0 && dateParts[2].length == 0 && dateParts[3] && dateParts[3].length != 0) {
|
||
// in the case that we have a year and other data, format that way
|
||
item.date = dateParts[3]+(dateParts[0] ? " "+dateParts[0] : "");
|
||
} else {
|
||
// standard YMD data
|
||
item.date = Scholar.Utilities.lpad(dateParts[0], "0", 4)+"-"+Scholar.Utilities.lpad(dateParts[1], "0", 2)+"-"+Scholar.Utilities.lpad(dateParts[2], "0", 2);
|
||
}
|
||
} else if(tag == "N1" || tag == "AB") {
|
||
// notes
|
||
item.notes.push({note:value});
|
||
} else if(tag == "KW") {
|
||
// keywords/tags
|
||
item.tags.push(value);
|
||
} else if(tag == "SP") {
|
||
// start page
|
||
if(!item.pages) {
|
||
item.pages = value;
|
||
} else if(item.pages[0] == "-") { // already have ending page
|
||
item.pages = value + item.pages;
|
||
} else { // multiple ranges? hey, it''s a possibility
|
||
item.pages += ", "+value;
|
||
}
|
||
} else if(tag == "EP") {
|
||
// end page
|
||
if(value) {
|
||
if(!item.pages || value != item.pages) {
|
||
if(!item.pages) {
|
||
item.pages = "";
|
||
}
|
||
item.pages += "-"+value;
|
||
}
|
||
}
|
||
} else if(tag == "SN") {
|
||
// ISSN/ISBN - just add both
|
||
if(!item.ISBN) {
|
||
item.ISBN = value;
|
||
}
|
||
if(!item.ISSN) {
|
||
item.ISSN = value;
|
||
}
|
||
} else if(tag == "UR") {
|
||
// URL
|
||
item.url = value;
|
||
}
|
||
}
|
||
|
||
function doImport(attachments) {
|
||
var line = true;
|
||
var tag = data = false;
|
||
do { // first valid line is type
|
||
line = Scholar.read();
|
||
Scholar.Utilities.debug(line);
|
||
} while(line !== false && line.substr(0, 6) != "TY - ");
|
||
|
||
var item = new Scholar.Item();
|
||
var i = 0;
|
||
if(attachments && attachments[i]) {
|
||
item.attachments = attachments[i];
|
||
}
|
||
|
||
var tag = "TY";
|
||
var data = line.substr(6);
|
||
|
||
while((line = Scholar.read()) !== false) { // until EOF
|
||
if(line.substr(2, 4) == " - ") {
|
||
// if this line is a tag, take a look at the previous line to map
|
||
// its tag
|
||
if(tag) {
|
||
processTag(item, tag, data);
|
||
}
|
||
|
||
// then fetch the tag and data from this line
|
||
tag = line.substr(0,2);
|
||
data = line.substr(6);
|
||
|
||
Scholar.Utilities.debug("tag: ''"+tag+"''; data: ''"+data+"''");
|
||
|
||
if(tag == "ER") { // ER signals end of reference
|
||
// unset info
|
||
tag = data = false;
|
||
// new item
|
||
item.complete();
|
||
item = new Scholar.Item();
|
||
i++;
|
||
if(attachments && attachments[i]) {
|
||
item.attachments = attachments[i];
|
||
}
|
||
}
|
||
} else {
|
||
// otherwise, assume this is data from the previous line continued
|
||
if(tag) {
|
||
data += line;
|
||
}
|
||
}
|
||
}
|
||
|
||
if(tag) { // save any unprocessed tags
|
||
processTag(item, tag, data);
|
||
item.complete();
|
||
}
|
||
}
|
||
|
||
function addTag(tag, value) {
|
||
if(value) {
|
||
Scholar.write(tag+" - "+value+"\r\n");
|
||
}
|
||
}
|
||
|
||
function doExport() {
|
||
var item;
|
||
|
||
while(item = Scholar.nextItem()) {
|
||
// can''t store independent notes in RIS
|
||
if(item.itemType == "note") {
|
||
continue;
|
||
}
|
||
|
||
// type
|
||
addTag("TY", typeMap[item.itemType]);
|
||
|
||
// use field map
|
||
for(var j in fieldMap) {
|
||
addTag(j, item[fieldMap[j]]);
|
||
}
|
||
|
||
// creators
|
||
for(var j in item.creators) {
|
||
// only two types, primary and secondary
|
||
var risTag = "A1"
|
||
if(item.creators[j].creatorType != "author") {
|
||
risTag = "A2";
|
||
}
|
||
|
||
addTag(risTag, item.creators[j].lastName+","+item.creators[j].firstName);
|
||
}
|
||
|
||
// date
|
||
if(item.date) {
|
||
var isoDate = /^[0-9]{4}(-[0-9]{2}-[0-9]{2})?$/;
|
||
if(isoDate.test(item.date)) { // can directly accept ISO format with minor mods
|
||
addTag("Y1", item.date.replace("-", "/")+"/");
|
||
} else { // otherwise, extract year and attach other data
|
||
var year = /^(.*?) *([0-9]{4})/;
|
||
var m = year.exec(item.date);
|
||
if(m) {
|
||
addTag("Y1", m[2]+"///"+m[1]);
|
||
}
|
||
}
|
||
}
|
||
|
||
// notes
|
||
if(Scholar.getOption("exportNotes")) {
|
||
for(var j in item.notes) {
|
||
addTag("N1", item.notes[j].note.replace(/[\r\n]/g, " "));
|
||
}
|
||
}
|
||
|
||
// tags
|
||
for(var j in item.tags) {
|
||
addTag("KY", item.tags[j]);
|
||
}
|
||
|
||
// pages
|
||
if(item.pages) {
|
||
var range = Scholar.Utilities.getPageRange(item.pages);
|
||
addTag("SP", range[0]);
|
||
addTag("EP", range[1]);
|
||
}
|
||
|
||
// ISBN/ISSN
|
||
addTag("SN", item.ISBN);
|
||
addTag("SN", item.ISSN);
|
||
|
||
// URL
|
||
if(item.url) {
|
||
addTag("UR", item.url);
|
||
} else if(item.source && item.source.substr(0, 7) == "http://") {
|
||
addTag("UR", item.source);
|
||
}
|
||
|
||
Scholar.write("ER - \r\n\r\n");
|
||
}
|
||
}');
|
||
|
||
REPLACE INTO "translators" VALUES ('a6ee60df-1ddc-4aae-bb25-45e0537be973', '2006-07-16 17:18:00', 1, 'MARC', 'Simon Kornblith', 'marc',
|
||
'function detectImport() {
|
||
var marcRecordRegexp = /^[0-9]{5}[a-z ]{3}$/
|
||
var read = Scholar.read(8);
|
||
if(marcRecordRegexp.test(read)) {
|
||
return true;
|
||
}
|
||
}',
|
||
'/*
|
||
* Original version of MARC record library copyright (C) 2005 Stefano Bargioni,
|
||
* licensed under the LGPL
|
||
*
|
||
* (Available at http://www.pusc.it/bib/mel/Scholar.Ingester.MARC_Record.js)
|
||
*
|
||
* This library is free software; you can redistribute it 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.
|
||
*
|
||
* This library 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.
|
||
*/
|
||
|
||
var MARC_Record = function() { // new MARC record
|
||
this.leader = {
|
||
record_length:''00000'',
|
||
record_status:''n'', // acdnp
|
||
type_of_record:'' '',
|
||
bibliographic_level:'' '',
|
||
type_of_control:'' '',
|
||
character_coding_scheme:'' '',
|
||
indicator_count:''2'',
|
||
subfield_code_length:''2'',
|
||
base_address_of_data:''00000'',
|
||
encoding_level:'' '',
|
||
descriptive_cataloging_form:'' '',
|
||
linked_record_requirement:'' '',
|
||
entry_map:''4500''
|
||
}; // 24 chars
|
||
|
||
this.field_terminator = ''\x1E'';
|
||
this.record_terminator = ''\x1D'';
|
||
this.subfield_delimiter = ''\x1F'';
|
||
this.directory = '''';
|
||
this.directory_terminator = this.field_terminator;
|
||
this.variable_fields = new Array();
|
||
};
|
||
|
||
MARC_Record.prototype.load = function(s,f) { // loads record s passed in format f
|
||
if (f == ''binary'') {
|
||
this.leader.record_length = ''00000'';
|
||
this.leader.record_status = s.substr(5,1);
|
||
this.leader.type_of_record = s.substr(6,1);
|
||
this.leader.bibliographic_level = s.substr(7,1);
|
||
this.leader.type_of_control = s.substr(8,1);
|
||
this.leader.character_coding_scheme = s.substr(9,1);
|
||
this.leader.indicator_count = ''2'';
|
||
this.leader.subfield_code_length = ''2'';
|
||
this.leader.base_address_of_data = ''00000'';
|
||
this.leader.encoding_level = s.substr(17,1);
|
||
this.leader.descriptive_cataloging_form = s.substr(18,1);
|
||
this.leader.linked_record_requirement = s.substr(19,1);
|
||
this.leader.entry_map = ''4500'';
|
||
|
||
this.directory = '''';
|
||
this.directory_terminator = this.field_terminator;
|
||
this.variable_fields = new Array();
|
||
|
||
// loads fields
|
||
var campi = s.split(this.field_terminator);
|
||
var k;
|
||
for (k=1; k<-1+campi.length; k++) { // the first and the last are unuseful
|
||
// the first is the header + directory, the last is the this.record_terminator
|
||
var tag = campi[0].substr(24+(k-1)*12,3);
|
||
var ind1 = ''''; var ind2 = ''''; var value = campi[k];
|
||
if (tag.substr(0,2) != ''00'') {
|
||
ind1 = campi[k].substr(0,1);
|
||
ind2 = campi[k].substr(1,1);
|
||
value = campi[k].substr(2);
|
||
}
|
||
this.add_field(tag,ind1,ind2,value);
|
||
}
|
||
}
|
||
|
||
this.update_record_length();
|
||
this.update_base_address_of_data();
|
||
return this;
|
||
}
|
||
|
||
MARC_Record.prototype.update_base_address_of_data = function() { // updates the base_address
|
||
this.leader.base_address_of_data = this._zero_fill(24+this.variable_fields.length*12+1,5);
|
||
return this.leader.base_address_of_data;
|
||
}
|
||
|
||
MARC_Record.prototype.update_displacements = function() { // rebuilds the directory
|
||
var displ = 0;
|
||
this.directory = '''';
|
||
for (var i=0; i<this.variable_fields.length; i++) {
|
||
var len = this.variable_fields[i].value.length + 1 +
|
||
this.variable_fields[i].ind1.length +
|
||
this.variable_fields[i].ind2.length;
|
||
this.directory += this.variable_fields[i].tag +
|
||
this._zero_fill(len,4) + this._zero_fill(displ,5);
|
||
displ += len;
|
||
}
|
||
return true;
|
||
}
|
||
MARC_Record.prototype.update_record_length = function() { // updates total record length
|
||
var fields_total_length = 0; var f;
|
||
for (f=0; f<this.variable_fields.length;f++) {
|
||
fields_total_length += this.variable_fields[f].ind1.length+this.variable_fields[f].ind2.length+this.variable_fields[f].value.length + 1;
|
||
}
|
||
var rl = 24+this.directory.length+1+fields_total_length+1;
|
||
this.leader.record_length = this._zero_fill(rl,5);
|
||
}
|
||
|
||
MARC_Record.prototype.sort_directory = function() { // sorts directory and array variable_fields by tag and occ
|
||
// ordinamento della directory
|
||
if (this.directory.length <= 12) { return true; } // already sorted
|
||
var directory_entries = new Array();
|
||
var i;
|
||
for (i=0; i<this.directory.length; i=i+12) {
|
||
directory_entries[directory_entries.length] = this.directory.substr(i,12);
|
||
}
|
||
directory_entries.sort();
|
||
this.directory = directory_entries.join('''');
|
||
// sorts array variable_fields
|
||
this.variable_fields.sort(function(a,b) { return a.tag - b.tag + a.occ - b.occ; });
|
||
return true;
|
||
}
|
||
|
||
MARC_Record.prototype.show_leader = function() {
|
||
var leader = ''''; var f;
|
||
for (f in this.leader) { leader += this.leader[f]; }
|
||
return leader;
|
||
}
|
||
|
||
MARC_Record.prototype.show_fields = function() {
|
||
var fields = ''''; var f;
|
||
for (f=0; f<this.variable_fields.length;f++) {
|
||
fields += this.variable_fields[f].ind1 +
|
||
this.variable_fields[f].ind2 +
|
||
this.variable_fields[f].value +
|
||
this.field_terminator;
|
||
}
|
||
return fields;
|
||
}
|
||
|
||
MARC_Record.prototype.show_directory = function() {
|
||
var d = '''';
|
||
for (var i = 0; i<this.directory.length; i+=12) {
|
||
d += this.directory.substr(i,3) + '' '' +
|
||
this.directory.substr(i+3,4) + '' '' +
|
||
this.directory.substr(i+7,5) + ''\n'';
|
||
}
|
||
return d;
|
||
}
|
||
|
||
MARC_Record.prototype.add_field_005 = function() {
|
||
var now = new Date();
|
||
now = now.getFullYear() +
|
||
this._zero_fill(now.getMonth()+1,2) +
|
||
this._zero_fill(now.getDate(),2) +
|
||
this._zero_fill(now.getHours(),2) +
|
||
this._zero_fill(now.getMinutes(),2) +
|
||
this._zero_fill(now.getSeconds(),2) + ''.0'';
|
||
this.add_field(''005'','''','''',now);
|
||
return now;
|
||
}
|
||
|
||
MARC_Record.prototype.count_occ = function(tag) { // counts occ of tag
|
||
var n = 0;
|
||
for (var i=0; i<this.variable_fields.length; i++) {
|
||
if (this.variable_fields[i].tag == tag) { n++; }
|
||
}
|
||
return n;
|
||
}
|
||
|
||
MARC_Record.prototype.exists = function(tag) { // field existence
|
||
if (this.count_occ(tag) > 0) return true;
|
||
return false;
|
||
}
|
||
|
||
MARC_Record.prototype.MARC_field = function(rec,tag,ind1,ind2,value) { // new MARC field
|
||
this.tag = tag;
|
||
this.occ = rec.count_occ(tag)+1; // occurrence order no.
|
||
this.ind1 = ind1; if (this.ind1 == '''') this.ind1 = '' '';
|
||
this.ind2 = ind2; if (this.ind2 == '''') this.ind2 = '' '';
|
||
if (tag.substr(0,2) == ''00'') {
|
||
this.ind1 = ''''; this.ind2 = '''';
|
||
}
|
||
this.value = value;
|
||
return this;
|
||
}
|
||
|
||
MARC_Record.prototype.display = function(type) { // displays record in format type
|
||
type = type.toLowerCase();
|
||
if (type == ''binary'') return this.show_leader() +
|
||
this.directory +
|
||
this.field_terminator +
|
||
this.show_fields() +
|
||
this.record_terminator;
|
||
if (type == ''xml'') {
|
||
s = '''';
|
||
s += ''<?xml version="1.0" encoding="iso-8859-1"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record>'';
|
||
s += ''<leader>''+this.show_leader()+''</leader>'';
|
||
// var i;
|
||
for (i=0; i<this.variable_fields.length; i++) {
|
||
ind1 = this.variable_fields[i].ind1; if (ind1 != '''') ind1 = '' ind1="''+ind1+''"'';
|
||
ind2 = this.variable_fields[i].ind2; if (ind2 != '''') ind2 = '' ind2="''+ind2+''"'';
|
||
if (this.variable_fields[i].tag.substr(0,2) == ''00'') s += ''<controlfield tag="''+this.variable_fields[i].tag+''">''+this.variable_fields[i].value+''</controlfield>'';
|
||
else {
|
||
var subfields = this.variable_fields[i].value.split(this.subfield_delimiter);
|
||
// alert(this.variable_fields[i].value+'' ''+subfields.length); // test
|
||
if (subfields.length == 1) subfields[1] = ''?''+this.variable_fields[i].value;
|
||
var sf = '''';
|
||
for (var j=1; j<subfields.length; j++) {
|
||
sf += ''<subfield code="''+subfields[j].substr(0,1)+''">''+subfields[j].substr(1)+''</subfield>'';
|
||
}
|
||
s += ''<datafield tag="'' + this.variable_fields[i].tag + ''"'' + ind1 + ind2 + ''>'' + sf + ''</datafield>'';
|
||
}
|
||
}
|
||
s += ''</record></collection>'';
|
||
return s;
|
||
}
|
||
return false;
|
||
}
|
||
|
||
MARC_Record.prototype.get_field = function(tag) { // returns an array of values, one for each occurrence
|
||
var v = new Array(); var i;
|
||
for (i=0; i<this.variable_fields.length; i++) {
|
||
if (this.variable_fields[i].tag == tag) {
|
||
v[v.length] = this.variable_fields[i].ind1 +
|
||
this.variable_fields[i].ind2 +
|
||
this.variable_fields[i].value;
|
||
}
|
||
}
|
||
return v;
|
||
}
|
||
|
||
// This function added by Simon Kornblith
|
||
MARC_Record.prototype.get_field_subfields = function(tag) { // returns a two-dimensional array of values
|
||
var field = this.get_field(tag);
|
||
var return_me = new Array();
|
||
for(var i in field) {
|
||
return_me[i] = new Object();
|
||
var subfields = field[i].split(this.subfield_delimiter);
|
||
if (subfields.length == 1) {
|
||
return_me[i][''?''] = field[i];
|
||
} else {
|
||
for (var j=1; j<subfields.length; j++) {
|
||
return_me[i][subfields[j].substr(0,1)] = subfields[j].substr(1);
|
||
}
|
||
}
|
||
}
|
||
return return_me;
|
||
}
|
||
|
||
MARC_Record.prototype.add_field = function(tag,ind1,ind2,value) { // adds a field to the record
|
||
/*if(tag.length != 3) {
|
||
return false;
|
||
}*/
|
||
|
||
if (tag.length < 3) {
|
||
tag = Scholar.Utilities.lpad(tag.toString(),"0",3);
|
||
} else if(tag.length > 3) {
|
||
return false;
|
||
}
|
||
|
||
var F = new this.MARC_field(this,tag,ind1,ind2,value);
|
||
// adds pointer to list of fields
|
||
this.variable_fields[this.variable_fields.length] = F;
|
||
// adds the entry to the directory
|
||
this.directory += F.tag+this._zero_fill(F.ind1.length+F.ind2.length+F.value.length+1,4)+''00000'';
|
||
// sorts the directory
|
||
this.sort_directory();
|
||
// updates lengths
|
||
this.update_base_address_of_data();
|
||
this.update_displacements();
|
||
this.update_record_length();
|
||
return F;
|
||
}
|
||
|
||
MARC_Record.prototype.delete_field = function(tag,occurrence) {
|
||
// lookup and delete the occurrence from array variable_fields
|
||
var i;
|
||
for (i=0; i<this.variable_fields.length; i++) {
|
||
if (this.variable_fields[i].tag == tag && this.variable_fields[i].occ == occurrence) break;
|
||
}
|
||
if (i==this.variable_fields.length) return false; // campo non trovato
|
||
// deletes the occ. i from array variable_fields scaling next values
|
||
var j;
|
||
for (j=i+1; j<this.variable_fields.length; j++) {
|
||
this.variable_fields[i++]=this.variable_fields[j];
|
||
}
|
||
this.variable_fields.length--; // deletes last element
|
||
// lookup and delete the occurrence from directory (must exist; no sort is needed)
|
||
var nocc = 0;
|
||
// var i;
|
||
for (i=0; i<this.directory.length;i=i+12) {
|
||
if (this.directory.substr(i,3) == tag) nocc++;
|
||
if (occurrence == nocc) { // occ found
|
||
break;
|
||
}
|
||
}
|
||
if (i >= this.directory.length) alert(''Internal error!'');
|
||
this.directory = this.directory.substr(0,i) + this.directory.substr(i+12);
|
||
// updates lengths
|
||
this.update_base_address_of_data();
|
||
this.update_displacements();
|
||
this.update_record_length();
|
||
return true;
|
||
}
|
||
|
||
MARC_Record.prototype._clean = function(value) {
|
||
value = value.replace(/^[\s\.\,\/\:]+/, '''');
|
||
value = value.replace(/[\s\.\,\/\:]+$/, '''');
|
||
value = value.replace(/ +/g, '' '');
|
||
|
||
var char1 = value[1];
|
||
var char2 = value[value.length-1];
|
||
if((char1 == "[" && char2 == "]") || (char1 == "(" && char2 == ")")) {
|
||
// chop of extraneous characters
|
||
return value.substr(1, value.length-2);
|
||
}
|
||
|
||
return value;
|
||
}
|
||
|
||
MARC_Record.prototype._associateDBField = function(item, fieldNo, part, fieldName, execMe, arg1, arg2) {
|
||
|
||
if(!part) {
|
||
part = ''a'';
|
||
}
|
||
|
||
var field = this.get_field_subfields(fieldNo);
|
||
Scholar.Utilities.debug(''Found ''+field.length+'' matches for ''+fieldNo+part);
|
||
if(field) {
|
||
for(var i in field) {
|
||
var value = false;
|
||
for(var j=0; j<part.length; j++) {
|
||
var myPart = part[j];
|
||
if(field[i][myPart]) {
|
||
if(value) {
|
||
value += " "+field[i][myPart];
|
||
} else {
|
||
value = field[i][myPart];
|
||
}
|
||
}
|
||
}
|
||
if(value) {
|
||
this._gotField = true;
|
||
value = this._clean(value);
|
||
|
||
if(execMe) {
|
||
value = execMe(value, arg1, arg2);
|
||
}
|
||
|
||
if(fieldName == "creator") {
|
||
item.creators.push(value);
|
||
} else {
|
||
item[fieldName] = value;
|
||
}
|
||
}
|
||
}
|
||
}
|
||
}
|
||
|
||
MARC_Record.prototype._associateTags = function(item, fieldNo, part) {
|
||
var field = this.get_field_subfields(fieldNo);
|
||
|
||
for(var i in field) {
|
||
for(var j=0; j<part.length; j++) {
|
||
var myPart = part[j];
|
||
if(field[i][myPart]) {
|
||
item.tags.push(this._clean(field[i][myPart]));
|
||
}
|
||
}
|
||
}
|
||
}
|
||
|
||
// this function loads a MARC record into our database
|
||
MARC_Record.prototype.translate = function(item) {
|
||
// cleaning functions - use a closure to improve readability because they''ll
|
||
// only be called once per record anyway
|
||
function _pullNumber(text) {
|
||
var pullRe = /[0-9]+/;
|
||
var m = pullRe.exec(text);
|
||
if(m) {
|
||
return m[0];
|
||
}
|
||
}
|
||
|
||
function _corpAuthor(author) {
|
||
return {lastName:author};
|
||
}
|
||
|
||
// not sure why this is necessary, but without it, this code is inaccessible
|
||
// from other translators
|
||
function _author(author, type, useComma) {
|
||
return Scholar.Utilities.cleanAuthor(author, type, useComma);
|
||
}
|
||
|
||
// Extract ISBNs
|
||
this._associateDBField(item, ''020'', ''a'', ''ISBN'', _pullNumber);
|
||
// Extract ISSNs
|
||
this._associateDBField(item, ''022'', ''a'', ''ISSN'', _pullNumber);
|
||
// Extract creators
|
||
this._associateDBField(item, ''100'', ''a'', ''creator'', _author, ''author'', true);
|
||
this._associateDBField(item, ''110'', ''a'', ''creator'', _corpAuthor, ''author'');
|
||
this._associateDBField(item, ''111'', ''a'', ''creator'', _corpAuthor, ''author'');
|
||
this._associateDBField(item, ''700'', ''a'', ''creator'', _author, ''contributor'', true);
|
||
this._associateDBField(item, ''710'', ''a'', ''creator'', _corpAuthor, ''contributor'');
|
||
this._associateDBField(item, ''711'', ''a'', ''creator'', _corpAuthor, ''contributor'');
|
||
if(!item.creators.length) {
|
||
// some LOC entries have no listed author, but have the author in the person subject field as the first entry
|
||
var field = this.get_field_subfields(''600'');
|
||
if(field[0]) {
|
||
item.creators.push(this.cleanAuthor(field[0][''a''], true));
|
||
}
|
||
}
|
||
|
||
// Extract tags
|
||
// personal
|
||
this._associateTags(item, "600", "aqtxyz");
|
||
// corporate
|
||
this._associateTags(item, "611", "abtxyz");
|
||
// meeting
|
||
this._associateTags(item, "630", "acetxyz");
|
||
// uniform title
|
||
this._associateTags(item, "648", "atxyz");
|
||
// chronological
|
||
this._associateTags(item, "650", "axyz");
|
||
// topical
|
||
this._associateTags(item, "651", "abcxyz");
|
||
// geographic
|
||
this._associateTags(item, "653", "axyz");
|
||
// uncontrolled
|
||
this._associateTags(item, "653", "a");
|
||
// faceted topical term (whatever that means)
|
||
this._associateTags(item, "654", "abcyz");
|
||
// genre/form
|
||
this._associateTags(item, "655", "abcxyz");
|
||
// occupation
|
||
this._associateTags(item, "656", "axyz");
|
||
// function
|
||
this._associateTags(item, "657", "axyz");
|
||
// curriculum objective
|
||
this._associateTags(item, "658", "ab");
|
||
// hierarchical geographic place name
|
||
this._associateTags(item, "662", "abcdfgh");
|
||
|
||
// Extract title
|
||
this._associateDBField(item, ''245'', ''ab'', ''title'');
|
||
// Extract edition
|
||
this._associateDBField(item, ''250'', ''a'', ''edition'');
|
||
// Extract place info
|
||
this._associateDBField(item, ''260'', ''a'', ''place'');
|
||
// Extract publisher info
|
||
this._associateDBField(item, ''260'', ''b'', ''publisher'');
|
||
// Extract year
|
||
this._associateDBField(item, ''260'', ''c'', ''date'', _pullNumber);
|
||
// Extract pages
|
||
this._associateDBField(item, ''300'', ''a'', ''pages'', _pullNumber);
|
||
// Extract series
|
||
this._associateDBField(item, ''440'', ''a'', ''seriesTitle'');
|
||
// Extract call number
|
||
this._associateDBField(item, ''084'', ''ab'', ''callNumber'');
|
||
this._associateDBField(item, ''082'', ''a'', ''callNumber'');
|
||
this._associateDBField(item, ''080'', ''ab'', ''callNumber'');
|
||
this._associateDBField(item, ''070'', ''ab'', ''callNumber'');
|
||
this._associateDBField(item, ''060'', ''ab'', ''callNumber'');
|
||
this._associateDBField(item, ''050'', ''ab'', ''callNumber'');
|
||
|
||
// Set type
|
||
item.itemType = "book";
|
||
|
||
if(!this._gotField) {
|
||
throw("tried to create a marc record with no fields!");
|
||
}
|
||
}
|
||
|
||
MARC_Record.prototype._trim = function(s) { // eliminates blanks from both sides
|
||
s = s.replace(/\s+$/,'''');
|
||
return s.replace(/^\s+/,'''');
|
||
}
|
||
|
||
MARC_Record.prototype._zero_fill = function(s,l) { // left ''0'' padding of s, up to l (l<=15)
|
||
var t = ''000000000000000'';
|
||
t = t+s;
|
||
return t.substr(t.length-l,l);
|
||
}
|
||
|
||
function doImport(url) { // the URL is actually here for other translators
|
||
var text;
|
||
var holdOver = ""; // part of the text held over from the last loop
|
||
|
||
while(text = Scholar.read(4096)) { // read in 4096 byte increments
|
||
var records = text.split("\x1D");
|
||
|
||
if(records.length > 1) {
|
||
records[0] = holdOver + records[0];
|
||
holdOver = records.pop(); // skip last record, since it''s not done
|
||
|
||
for(var i in records) {
|
||
var newItem = new Scholar.Item();
|
||
newItem.source = url;
|
||
|
||
// create new record
|
||
var record = new MARC_Record();
|
||
record.load(records[i], "binary");
|
||
record.translate(newItem);
|
||
|
||
newItem.complete();
|
||
}
|
||
} else {
|
||
holdOver += text;
|
||
}
|
||
}
|
||
}');
|
||
|
||
REPLACE INTO "csl" VALUES('http://purl.org/net/xbiblio/csl/styles/apa.csl', '2006-08-12 19:22:00', 'APA',
|
||
'<?xml version="1.0" encoding="UTF-8"?>
|
||
<?oxygen RNGSchema="file:/Users/darcusb/xbiblio/csl/schema/trunk/csl-alt.rnc" type="compact"?>
|
||
<style xmlns="http://purl.org/net/xbiblio/csl" class="author-date" xml:lang="en">
|
||
<info>
|
||
<title>American Psychological Association</title>
|
||
<id>http://purl.org/net/xbiblio/csl/styles/apa.csl</id>
|
||
<link>http://purl.org/net/xbiblio/csl/styles/apa.csl</link>
|
||
<author>
|
||
<name>Bruce D’Arcus</name>
|
||
<email>bdarcus@sourceforge.net</email>
|
||
</author>
|
||
<author>
|
||
<name>Simon Kornblith</name>
|
||
<email>simon@simonster.com</email>
|
||
</author>
|
||
<updated>2006-08-13T23:28:00-05:00</updated>
|
||
</info>
|
||
<defaults>
|
||
<contributors name-as-sort-order="no">
|
||
<name and="symbol" initialize-with="."/>
|
||
<label prefix=", " text-transform="capitalize"/>
|
||
</contributors>
|
||
<author name-as-sort-order="all">
|
||
<name and="symbol" sort-separator=", " initialize-with="."/>
|
||
<label prefix=" (" suffix=")" text-transform="capitalize"/>
|
||
<substitute>
|
||
<choose>
|
||
<editor/>
|
||
<translator/>
|
||
<titles/>
|
||
</choose>
|
||
</substitute>
|
||
</author>
|
||
<locator>
|
||
<number/>
|
||
</locator>
|
||
<identifier>
|
||
<number/>
|
||
</identifier>
|
||
<titles>
|
||
<title/>
|
||
</titles>
|
||
<date>
|
||
<year/>
|
||
<month prefix=", "/>
|
||
<day prefix=" "/>
|
||
</date>
|
||
<publisher>
|
||
<place suffix=": "/>
|
||
<name/>
|
||
</publisher>
|
||
<access>
|
||
<text term-name="retrieved" text-transform="capitalize"/>
|
||
<date suffix=", ">
|
||
<month/>
|
||
<day suffix=", "/>
|
||
<year/>
|
||
</date>
|
||
<text term-name="from"/>
|
||
<url/>
|
||
<date prefix=", "/>
|
||
</access>
|
||
</defaults>
|
||
<citation prefix="(" suffix=")" delimiter="; ">
|
||
<et-al min-authors="6" use-first="6" position="first"/>
|
||
<et-al min-authors="6" use-first="1" position="subsequent"/>
|
||
<layout>
|
||
<item>
|
||
<author form="short" suffix=", "/>
|
||
<date>
|
||
<year/>
|
||
</date>
|
||
<locator prefix=": "/>
|
||
</item>
|
||
</layout>
|
||
</citation>
|
||
<bibliography hanging-indent="true">
|
||
<sort algorithm="author-date"/>
|
||
<et-al min-authors="4" use-first="3"/>
|
||
<layout>
|
||
<list>
|
||
<heading>
|
||
<text term-name="references"/>
|
||
</heading>
|
||
</list>
|
||
<item suffix=".">
|
||
<choose>
|
||
<type name="book">
|
||
<author/>
|
||
<date prefix=" (" suffix=").">
|
||
<year/>
|
||
</date>
|
||
<group suffix=".">
|
||
<titles font-style="italic" prefix=" "/>
|
||
<group prefix=" (" suffix=")" delimiter=", ">
|
||
<editor/>
|
||
<translator/>
|
||
</group>
|
||
</group>
|
||
<publisher prefix=" "/>
|
||
<access prefix=" "/>
|
||
</type>
|
||
<type name="chapter">
|
||
<author/>
|
||
<date prefix=" (" suffix=").">
|
||
<year/>
|
||
</date>
|
||
<titles font-style="italic" prefix=" "/>
|
||
<group class="container" prefix=" ">
|
||
<text term-name="in" text-transform="capitalize"/>
|
||
<editor prefix=" " suffix=",">
|
||
<name and="symbol" sort-separator=", " initialize-with="."/>
|
||
<label prefix=" (" suffix=")" text-transform="capitalize"/>
|
||
</editor>
|
||
<translator prefix=" " suffix=",">
|
||
<name and="symbol" sort-separator=", " initialize-with="."/>
|
||
<label prefix=" (" suffix=")" text-transform="capitalize"/>
|
||
</translator>
|
||
<titles relation="container" font-style="italic" prefix=" " suffix="."/>
|
||
<titles relation="collection" prefix=" " suffix="."/>
|
||
<publisher prefix=" "/>
|
||
<pages prefix=" (" suffix=")">
|
||
<label text-transform="capitalize" suffix=". "/>
|
||
<number/>
|
||
</pages>
|
||
</group>
|
||
<access prefix=" "/>
|
||
</type>
|
||
<type name="article">
|
||
<author/>
|
||
<date prefix=" (" suffix=").">
|
||
<year/>
|
||
</date>
|
||
<group suffix=".">
|
||
<titles prefix=" "/>
|
||
<group prefix=" (" suffix=")" delimiter=", ">
|
||
<editor/>
|
||
<translator/>
|
||
</group>
|
||
</group>
|
||
<group class="container" prefix=" " suffix=".">
|
||
<titles relation="container" font-style="italic"/>
|
||
<volume prefix=", " font-style="italic"/>
|
||
<issue prefix="(" suffix=")"/>
|
||
<pages prefix=", "/>
|
||
</group>
|
||
<access prefix=" "/>
|
||
</type>
|
||
</choose>
|
||
</item>
|
||
</layout>
|
||
</bibliography>
|
||
</style>');
|
||
|
||
REPLACE INTO "csl" VALUES('http://purl.org/net/xbiblio/csl/styles/chicago-note.csl', '2006-08-12 19:22:00', 'Chicago (Footnote)',
|
||
'<?xml version="1.0" encoding="UTF-8"?>
|
||
<?oxygen RNGSchema="../schema/trunk/csl.rnc" type="compact"?>
|
||
<style xmlns="http://purl.org/net/xbiblio/csl" class="note" xml:lang="en">
|
||
<info>
|
||
<title>Chicago Note Sans Reference List</title>
|
||
<id>http://purl.org/net/xbiblio/csl/styles/chicago-note.csl</id>
|
||
<author>
|
||
<name>Bruce D’Arcus</name>
|
||
<email>bdarcus@sourceforge.net</email>
|
||
</author>
|
||
<updated>2006-08-03T04:35:20-07:00</updated>
|
||
<summary>The note-without-bibliography variant of the Chicago style.</summary>
|
||
</info>
|
||
<defaults>
|
||
<contributor>
|
||
<label suffix=". " text-transform="lowercase"/>
|
||
<name and="text"/>
|
||
</contributor>
|
||
<author>
|
||
<name and="text"/>
|
||
<label prefix = ", " suffix="." text-transform="lowercase"/>
|
||
<substitute>
|
||
<choose>
|
||
<editor/>
|
||
<translator/>
|
||
</choose>
|
||
</substitute>
|
||
</author>
|
||
<locator>
|
||
<number/>
|
||
</locator>
|
||
<titles>
|
||
<title/>
|
||
</titles>
|
||
<date>
|
||
<year/>
|
||
</date>
|
||
<publisher>
|
||
<place suffix=": "/>
|
||
<name/>
|
||
</publisher>
|
||
<access>
|
||
<url/>
|
||
<date prefix=" "/>
|
||
</access>
|
||
</defaults>
|
||
<citation suffix=".">
|
||
<et-al min-authors="4" use-first="1"/>
|
||
<layout>
|
||
<item>
|
||
<choose>
|
||
<type name="book">
|
||
<author suffix=", "/>
|
||
<titles font-style="italic"/>
|
||
<editor prefix=", "/>
|
||
<translator prefix=", "/>
|
||
<group prefix=" (" suffix=")" delimiter=", ">
|
||
<publisher/>
|
||
<date/>
|
||
</group>
|
||
<pages prefix=", "/>
|
||
</type>
|
||
<type name="chapter">
|
||
<author suffix=", "/>
|
||
<titles prefix="“" suffix=",” "/>
|
||
<group class="container">
|
||
<text term-name="in" text-transform="lowercase"/>
|
||
<titles relation="container" prefix=" " font-style="italic"/>
|
||
<editor prefix=", "/>
|
||
<translator prefix=", "/>
|
||
<pages prefix=", "/>
|
||
<group prefix=" (" suffix=")" delimiter=", ">
|
||
<publisher/>
|
||
<date/>
|
||
</group>
|
||
</group>
|
||
</type>
|
||
<type name="journal-article">
|
||
<author suffix=", "/>
|
||
<titles prefix="“" suffix=",” "/>
|
||
<titles relation="container" font-style="italic"/>
|
||
<volume prefix=" "/>
|
||
<issue prefix=" (" suffix=")"/>
|
||
<pages prefix=": "/>
|
||
</type>
|
||
<type name="article">
|
||
<author suffix=", "/>
|
||
<titles prefix="“" suffix=",” "/>
|
||
<titles relation="container" font-style="italic"/>
|
||
<date prefix=", ">
|
||
<day suffix=" "/>
|
||
<month suffix=" " text-transform="capitalize"/>
|
||
<year/>
|
||
</date>
|
||
</type>
|
||
</choose>
|
||
</item>
|
||
<item position="subsequent" ibid="true">
|
||
<author/>
|
||
<title prefix=", "/>
|
||
</item>
|
||
</layout>
|
||
</citation>
|
||
</style>'); |