public void RemoveExtraBookTitles()
{
//NB: here we're just keeping it simple, not even making sure, for example, that
//"Nupela Book" is in a Tok Pisin div. If it was in English, we'd zap it as well.
//This xpath will collect up both divs in the data-div, and also copies of this
//that may be in a bloom-translationGroup in the cover and title pages.
var genericBookNames = new[] {"Basic Book", "Nupela Buk", "Buku Dasar"};
foreach(XmlElement n in _dom.SafeSelectNodes("//*[@data-book='bookTitle']"))
{
if(genericBookNames.Contains(n.InnerText.Trim()))
{
n.ParentNode.RemoveChild(n);
}
}
}
public void RemoveExtraBookTitles_BookTitlesThatAreJustGeneric_Removed()
{
var bookDom = new HtmlDom(@"<html ><head></head><body>
<div id='bloomDataDiv'>
<div data-book='bookTitle' lang='en'>something unique</div>
<div data-book='bookTitle' lang='id'>Buku Dasar</div>
<div data-book='bookTitle' lang='tpi'>Nupela Buk</div>
</div>
<div id='somePage'>
<div class='bloom-translationGroup bookTitle'>
<div class='bloom-editable' data-book='bookTitle' lang='tpi'>
<p>Nupela Buk<br/></p>
</div>
<div class='bloom-editable' data-book='bookTitle' lang='id'>
<p>Buku Dasar</p>
</div>
<div class='bloom-editable' data-book='bookTitle'>
<p>something unique<br/></p>
</div>
</div>
</div>
</body></html>");
bookDom.RemoveExtraBookTitles();
AssertThatXmlIn.Dom(bookDom.RawDom).HasSpecifiedNumberOfMatchesForXpath("//div[@data-book='bookTitle' and @lang='en' and text()='something unique']", 1);
AssertThatXmlIn.Dom(bookDom.RawDom).HasSpecifiedNumberOfMatchesForXpath("//div[@data-book='bookTitle' and @lang='id']", 0);
AssertThatXmlIn.Dom(bookDom.RawDom).HasSpecifiedNumberOfMatchesForXpath("//div[@data-book='bookTitle' and @lang='tpi']", 0);
}
