diff --git a/chrome/chromeFiles/content/scholar/xpcom/cite.js b/chrome/chromeFiles/content/scholar/xpcom/cite.js index 65f6607159..c378720cdc 100644 --- a/chrome/chromeFiles/content/scholar/xpcom/cite.js +++ b/chrome/chromeFiles/content/scholar/xpcom/cite.js @@ -104,7 +104,6 @@ CSL.prototype.preprocessItems = function(items) { if(!item._csl || item._csl.dateModified != dateModified) { // namespace everything in item._csl so there's no chance of overlap item._csl = new Object(); - item._csl.ignore = new Array(); item._csl.dateModified = dateModified; // separate item into authors, editors, translators @@ -115,11 +114,10 @@ CSL.prototype.preprocessItems = function(items) { // parse date item._csl.date = CSL.prototype._processDate(item.getField("date")); - } else { - // clear disambiguation and subsequent author substitute - if(item._csl.disambiguation) item._csl.date.disambiguation = undefined; - if(item._csl.subsequentAuthorSubstitute) item._csl.subsequentAuthorSubstitute = undefined; } + // clear disambiguation and subsequent author substitute + if(item._csl.disambiguation) item._csl.date.disambiguation = undefined; + if(item._csl.subsequentAuthorSubstitute) item._csl.subsequentAuthorSubstitute = undefined; } // sort by sort order @@ -179,7 +177,7 @@ CSL.prototype.preprocessItems = function(items) { item._csl.number = i; // handle subsequent author substitutes - if(this._bib.subsequentAuthorSubstitute && lastAuthor == author) { + if(lastAuthor == author) { item._csl.subsequentAuthorSubstitute = true; } lastAuthor = author; diff --git a/chrome/chromeFiles/content/scholar/xpcom/utilities.js b/chrome/chromeFiles/content/scholar/xpcom/utilities.js index 22f369a714..57c41bcace 100644 --- a/chrome/chromeFiles/content/scholar/xpcom/utilities.js +++ b/chrome/chromeFiles/content/scholar/xpcom/utilities.js @@ -26,6 +26,10 @@ Scholar.Utilities.prototype.strToDate = function(date) { * Cleans extraneous punctuation off an author name */ Scholar.Utilities.prototype.cleanAuthor = function(author, type, useComma) { + if(typeof(author) != "string") { + throw "cleanAuthor: author must be a string"; + } + author = author.replace(/^[\s\.\,\/\[\]\:]+/, ''); author = author.replace(/[\s\,\/\[\]\:\.]+$/, ''); author = author.replace(/ +/, ' '); @@ -54,6 +58,10 @@ Scholar.Utilities.prototype.cleanAuthor = function(author, type, useComma) { * Cleans whitespace off a string and replaces multiple spaces with one */ Scholar.Utilities.prototype.cleanString = function(s) { + if(typeof(s) != "string") { + throw "cleanString: argument must be a string"; + } + s = s.replace(/[ \xA0\r\n]+/g, " "); s = s.replace(/^\s+/, ""); return s.replace(/\s+$/, ""); @@ -63,6 +71,10 @@ Scholar.Utilities.prototype.cleanString = function(s) { * Cleans any non-word non-parenthesis characters off the ends of a string */ Scholar.Utilities.prototype.superCleanString = function(x) { + if(typeof(s) != "string") { + throw "superCleanString: argument must be a string"; + } + var x = x.replace(/^[^\w(]+/, ""); return x.replace(/[^\w)]+$/, ""); } @@ -71,6 +83,10 @@ Scholar.Utilities.prototype.superCleanString = function(x) { * Eliminates HTML tags, replacing
s with /ns */ Scholar.Utilities.prototype.cleanTags = function(x) { + if(typeof(s) != "string") { + throw "cleanTags: argument must be a string"; + } + x = x.replace(/]*>/gi, "\n"); return x.replace(/<[^>]+>/g, ""); } @@ -118,6 +134,10 @@ Scholar.Utilities.prototype.inArray = Scholar.inArray; * pads a number or other string with a given string on the left */ Scholar.Utilities.prototype.lpad = function(string, pad, length) { + if(typeof(s) != "string") { + throw "lpad: argument must be a string"; + } + while(string.length < length) { string = pad + string; } diff --git a/scrapers.sql b/scrapers.sql index abb20024eb..1e217a91fd 100644 --- a/scrapers.sql +++ b/scrapers.sql @@ -1,4 +1,4 @@ --- 81 +-- 82 -- Set the following timestamp to the most recent scraper update date REPLACE INTO "version" VALUES ('repository', STRFTIME('%s', '2006-08-31 22:44:00')); @@ -3458,7 +3458,7 @@ function scrape(doc, url) { return; } - newItem.attachments.push({url:url, title:"New York Times Article", + newItem.attachments.push({url:url, title:"Article (HTML)", mimeType:"text/html", downloadable:true}); } else { newItem.url = doc.location.href; @@ -3471,7 +3471,7 @@ function scrape(doc, url) { } } - newItem.attachments.push({document:doc, title:"New York Times Article", + newItem.attachments.push({document:doc, title:"Article (HTML)", downloadable:true}); } @@ -3543,6 +3543,220 @@ function doWeb(doc, url) { } }'); +REPLACE INTO "translators" VALUES ('1e6d1529-246f-4429-84e2-1f1b180b250d', '2006-09-06 17:54:00', 4, 'Chronicle of Higher Education', 'Simon Kornblith', '^http://chronicle\.com/', +'function detectWeb(doc, url) { + var articleRegexp = /^http:\/\/chronicle\.com\/(?:daily|weekly)\/[^/]+\// + if(articleRegexp.test(url)) { + if(doc.location.href.indexOf("weekly") != -1) { + return "magazineArticle"; + } else { + return "website"; + } + } else { + var aTags = doc.getElementsByTagName("a"); + for(var i=0; i