Groovy scripts to parse Blogger export xml

01. get file name from loaded editor.groovy

def editor = eclipse.editors.get("blog-02-28-2014 (1).xml").getEditor(true);
def xmlFile = editor.getEditorInput().fileStore.toString();
return xmlFile;

02.open xml file in Groovy and get list of items

xmlFile = "/Users/plugin/Downloads/blog-02-28-2014 (1).xml";
def xml = new XmlParser().parse(xmlFile)
return xml.children().size();

03. getting values and sizes.groovy

xmlFile = "/Users/plugin/Downloads/blog-02-28-2014 (1).xml";
def xml = new XmlParser().parse(xmlFile)

return xml.title.first()

return xml.entry.size() // = 1338
return xml.title.size() // = 1
return xml.link.size() // = 4

04. view entry.groovy

xmlFile = "/Users/plugin/Downloads/blog-02-28-2014 (1).xml";
def xml = new XmlParser().parse(xmlFile)

def entry =  xml.entry[10];//.first();
show(entry)
return entry;

05. resolve titles and show them on a treeView.groovy

xmlFile = "/Users/plugin/Downloads/blog-02-28-2014 (1).xml";
def xml = new XmlParser().parse(xmlFile)

def titles = xml.entry.collect { it.title[0].value()[0] } . take (20);

def view = eclipse.views.create("Blogger data viewer").clear();
view.add.treeViewer().add_Nodes(titles);

return titles;

06. show titles in a table.groovy

xmlFile = "/Users/plugin/Downloads/blog-02-28-2014 (1).xml";
def xml = new XmlParser().parse(xmlFile)

def view = eclipse.views.create("Blogger data viewer").clear();
def table = view.add.table();
table.columns("title");

for(def entry in xml.entry.take(20))
{
	table.add_Row(entry.title[0].value()[0]);
}
return "done";

07. list category and title on a table.groovy

def xmlFile = "/Users/plugin/Downloads/blog-02-28-2014 (1).xml";
def xml = new XmlParser().parse(xmlFile)

def view = eclipse.views.create("Blogger data viewer").clear();
def table = view.add.table();
table.columns("category", "title");

for(def entry in xml.entry.drop(20).take(20))
{
	def title    = entry.title[0].value()[0];
	def category = entry.category[0].attributes().term;

	table.add_Row(category,title);
}
return "done";

08. unique list of categories.groovy

def xmlFile = "/Users/plugin/Downloads/blog-02-28-2014 (1).xml";
def xml = new XmlParser().parse(xmlFile)

def categories =  xml.entry.collect { it.category[0] .attributes().term }.unique();

return categories;

09. finding all posts.groovy

def xmlFile = "/Users/plugin/Downloads/blog-02-28-2014 (1).xml";
def xml = new XmlParser().parse(xmlFile)

def categoryToFind = "http://schemas.google.com/blogger/2008/kind#post";
def allPosts =  xml.entry.findAll { it.category[0] .attributes().term == categoryToFind };

return allPosts.size();

10. create table with title, publishDate and categories

def xmlFile = "/Users/plugin/Downloads/blog-02-28-2014 (1).xml";

def xml = new XmlParser().parse(xmlFile)

def categoryToFind = "http://schemas.google.com/blogger/2008/kind#post";
def allPosts =  xml.entry.findAll { it.category[0] .attributes().term == categoryToFind };

def view = eclipse.views.create("Blogger data viewer").clear();
def table = view.add.table();
table.columns("title", "publish date", "categories");

for(def entry in allPosts.take(20))
{
	def title             = entry.title[0].value()[0];
	def publishDate = entry.published[0].value();
    def categories   =  entry.category.collect { it.attributes().term}.drop(1).sort()
	
	table.add_Row(title, publishDate, categories);
}
return "done";

11. get all posts that are marked as draft.groovy

def xmlFile = "/Users/plugin/Downloads/blog-03-09-2014.xml";

def xmlParser = new XmlParser();
def xml = xmlParser.parse(xmlFile)

def categoryToFind = "http://schemas.google.com/blogger/2008/kind#post";
def allPosts =  xml.entry.findAll { it.category[0] .attributes().term == categoryToFind && 
				    it["app:control"].size() > 0};  
				    
// the app:control will contain this entry (when a draf)
/*
  <app:control xmlns:app="http://purl.org/atom/app#">
    <app:draft>
      yes
    </app:draft>
  </app:control>
 */ 

return allPosts.size()

//this is one way to create an XML file
def _entry =allPosts.find { it.title[0].value()[0] == 'Using Firebase Token Generator' } 
def writer = new StringWriter()
new XmlNodePrinter(new PrintWriter(writer)).print(_entry.first())
def result = writer.toString()
return result;

12. first working script to create UI to view blogger posts.groovy

def xmlFile = "/Users/plugin/Downloads/blog-03-09-2014.xml";

def xmlParser = new XmlParser();
def xml = xmlParser.parse(xmlFile)

def categoryToFind = "http://schemas.google.com/blogger/2008/kind#post";
def allPosts =  xml.entry.findAll { it.category[0] .attributes().term == categoryToFind && 
													it["app:control"].size() == 0};


def view = eclipse.views.create("Blogger data viewer").clear();
def table = view.add.table();
def browser = view.add.browser();

def _eclipse = eclipse;

table.set.event.onSelection(new Runnable() { public void run() 
	{
		try
		{
			def selected = table.getSelection().first().text.toInteger();
			def entry = allPosts[selected]
			def html = entry.content[0].value()[0];
			browser.setText(html);
		}
		catch(Exception ex)
		{
			_eclipse.log("ERROR: " + ex.getMessage());
		}
	}});

table.columns("#", "title", "publish date", "categories","content");
def count = 1;
for(def entry in allPosts)//.take(20))
{
	def title             = entry.title[0].value()[0];
	def publishDate = entry.published[0].value();
    def categories   =  entry.category.collect { it.attributes().term}.drop(1).sort()
	def content       = entry.content[0].value()[0];
	table.add_Row(count++, title, publishDate, categories, content);
}
return "done";

//Config:UIThread_False

13. how to find all AngularJS posts.groovy

def xmlFile = "/Users/plugin/Downloads/blog-03-09-2014.xml";

def xmlParser = new XmlParser();
def xml = xmlParser.parse(xmlFile)

def postCategory = "http://schemas.google.com/blogger/2008/kind#post";
def categoryFilter = "AngularJS";
def allPosts =  xml.entry.findAll { it.category[0] .attributes().term == postCategory && 
				    it.category.collect().toString().contains(categoryFilter) &&
				    it["app:control"].size() == 0};

14. CREATE IMPORTable xml based on tag filter (with viewer).groovy

def categoryFilter = "Git";
def exportXmlFile = "/Users/plugin/_Books/Posts_with_Only_${categoryFilter}.xml";


//*** Step 1) load the original blogger export

def xmlFile = "/Users/plugin/Downloads/blog-03-09-2014.xml";

def xmlParser = new XmlParser();
def xml = xmlParser.parse(xmlFile)

def postCategory = "http://schemas.google.com/blogger/2008/kind#post";
def pageCategory = "http://schemas.google.com/blogger/2008/kind#page";

// get all posts
def allPosts  =  xml.entry.findAll { it.category[0] .attributes().term == postCategory && it["app:control"].size() == 0};
def allDrafts =  xml.entry.findAll { it.category[0] .attributes().term == postCategory && it["app:control"].size() > 0}
def allPages  =  xml.entry.findAll { it.category[0] .attributes().term == pageCategory }


//*** Step 3) remove all posts that dont match the categoryFilter value

def allPostsToRemove =	allPosts.findAll { it.category.collect().toString().contains(categoryFilter)==false }

for(def postToRemove in allPostsToRemove)
	xml.remove(postToRemove);

for(def postToRemove in allDrafts)
	xml.remove(postToRemove);

for(def postToRemove in allPages)
	xml.remove(postToRemove);

//*** Step 4) write file (making sure it is in utf-8 format
def outputStreamWritter = new OutputStreamWriter(new FileOutputStream(exportXmlFile),"UTF-8");
def bufferedWriter          = new BufferedWriter (outputStreamWritter);
def printWriter                = new PrintWriter(bufferedWriter)
def xmlNodePrinter = new XmlNodePrinter(printWriter);

xmlNodePrinter.print(xml);

//*** Step5)  load the exportXmlFile (to that we can show it on the Eclipse view
xml = xmlParser.parse(exportXmlFile)


allPosts =  xml.entry.findAll { it.category[0] .attributes().term == postCategory };

//create view

def view = eclipse.views.create("Blogger data viewer").clear();
def table = view.add.table();
def browser = view.add.browser();

def _eclipse = eclipse;

//set event to show selected row on browser
table.set.event.onSelection(new Runnable() { public void run() 
	{
		try
		{
			def selected = table.getSelection().first().text.toInteger() -1;
			def entry = allPosts[selected]
			def html = entry.content[0].value()[0];
			browser.setText(html);
		}
		catch(Exception ex)
		{
			_eclipse.log("ERROR: " + ex.getMessage());
		}
	}});

//set table columns and add rows

table.columns("#", "title", "publish date", "categories","content");
def count = 1;
for(def entry in allPosts) //.take(20))
{
	def title             = entry.title[0].value()[0];
	def publishDate = entry.published[0].value();
    def categories   =  entry.category.collect { it.attributes().term}.drop(1).sort()
	def content       = entry.content[0].value()[0];
	table.add_Row(count++, title, publishDate, categories, content);
}
return "done";

//Config:UIThread_False