fix(xml): clean xml out of standard

Author: AntonelloDN

deploy/morpho/Morpho Decompose XML.ghuser

@@ -28,32 +28,26 @@
 except: pass
 
 import System
-import xml.etree.ElementTree as ET
 from Grasshopper.Kernel.Data import GH_Path
 from Grasshopper import DataTree
 import re
+import clr
+clr.AddReference("System.Linq")
+clr.AddReference("System.XML.Linq")
+from System.Xml.Linq import XDocument
 
 ghenv.Component.Message = "1.1.0"
 
-
-
-def get_clean_xml(text):
-    
-    characters = '[^\s()_<>/,\.A-Za-z0-9=""]+'
-    text = re.sub(characters, '', text)
-    return text
-
-
 def main():
 
     if _XML and _keyword:
 
-        roots = [ET.fromstring(get_clean_xml(el)) for el in _XML]
+        xdocs = [XDocument.Parse(el) for el in _XML]
         results = DataTree[System.Object]()
 
         for i, key in enumerate(_keyword):
             path = GH_Path(0, i)
-            results.AddRange( [root.find(key).text for root in roots if root.find(key) != None] ,path )
+            results.AddRange( [element.Value for xdoc in xdocs for element in xdoc.Descendants(key) ] ,path )
 
         return results
     else:

deploy/src/Morpho Decompose XML.py

@@ -75,17 +75,14 @@ public Library(string file,
 
         private string GetCompatibleText(string file)
         {
-            string characters = @"[^\s()_<>/,\.A-Za-z0-9=""]+";
-            Encoding encoding = Encoding.UTF8;
+            string characters = @"[^\s()_<>/,\.A-Za-z0-9=""\P{IsBasicLatin}]+";
 
             if (!System.IO.File.Exists(file))
                 throw new Exception($"{file} not found.");
-            string text = System.IO.File.ReadAllText(file, encoding);
+            string text = System.IO.File.ReadAllText(file);
+            string res = Regex.Replace(text, characters, "");
 
-            text = System.Net.WebUtility.HtmlDecode(text);
-            Regex.Replace(characters, "", text);
-
-            return text.Replace("&", "");
+            return res;
         }
 
         private void SetLibrary(string file, string type, string keyword)

project/Morpho/Morpho25/IO/Library.cs

@@ -27,14 +27,14 @@ public Read(string path)
 
         private string ReadEdxFile(string path)
         {
-            string characters = @"[^\s()_<>/,\.A-Za-z0-9=""]+";
-            Encoding isoLatin1 = Encoding.GetEncoding(28591); ;
-            string text = System.IO.File.ReadAllText(path, isoLatin1);
+            string characters = @"[^\s()_<>/,\.A-Za-z0-9=""\P{IsBasicLatin}\p{IsLatin-1Supplement}]+";
 
-            Regex.Replace(characters, "", text);
+            if (!System.IO.File.Exists(path))
+                throw new Exception($"{path} not found.");
+            string text = System.IO.File.ReadAllText(path);
+            string res = Regex.Replace(text, characters, "");
 
-            return text.Replace("&", "")
-                .Replace("<Remark for this Source Type>", "");
+            return res.Replace("<Remark for this Source Type>", "");
         }
 
         private static string GetValueFromXml(XmlNodeList nodeList,