Implemented HTML Tools (#240)

Co-authored-by: widlam <mikolaj.widla@gmail.com>
Reviewed-on: #240
Reviewed-by: Adam Bem <bema@noreply.example.com>
Co-authored-by: Mikolaj Widla <widlam@noreply.example.com>
Co-committed-by: Mikolaj Widla <widlam@noreply.example.com>

Backend-libXML/Parser.py

@@ -1,7 +1,28 @@
-from lxml import etree
+from lxml import etree, html
 from io import BytesIO
 
 
+def convertHTML(source: str, sourceFrom: str):
+    htmlParser = html.HTMLParser(remove_comments=True, remove_blank_text=True)
+    xmlParser = etree.XMLParser(remove_comments=True, remove_blank_text=True)
+
+    if sourceFrom == "xml":
+        xmldoc = etree.parse(BytesIO(source.encode("utf-8")), xmlParser)
+        return html.tostring(xmldoc, method="html", pretty_print=True).decode()
+    elif sourceFrom == "html":
+        htmldoc = html.parse(BytesIO(source.encode("utf-8")), htmlParser)
+        return etree.tostring(htmldoc, method="xml", pretty_print=True, doctype="", xml_declaration=True, encoding="utf-8").decode()
+    else:
+        return
+
+
+def formatHTML(source: str, prettify: bool) -> str:
+    parser = html.HTMLParser(remove_blank_text=True, remove_comments=True, remove_pis=True)
+    htmlDoc = html.parse(BytesIO(source.encode("utf-8")),parser=parser)
+    if not prettify:
+        return html.tostring(htmlDoc).decode().replace("\n", "").replace(">    ", ">")
+    return etree.tostring(htmlDoc, encoding='unicode', pretty_print=True)
+
 def formatXML(source: str, prettify: bool) -> str:
     """Method used to format XML