Map the weird numeric escapes to textual ones

2025-03-26 02:34:21 +01:00
parent 2bfd9f951e
commit 1a4b4f76f2
2 changed files with 141 additions and 21 deletions
--- a/processor/xml.go
+++ b/processor/xml.go
@@ -84,10 +84,11 @@ func (p *XMLProcessor) ProcessContent(content string, path string, luaExpr strin
 		declaration := doc.FirstChild.OutputXML(true)
 		// Remove the firstChild (declaration) before serializing the rest of the document
 		doc.FirstChild = doc.FirstChild.NextSibling
-		return declaration + doc.OutputXML(true), modCount, matchCount, nil
+		return ConvertToNamedEntities(declaration + doc.OutputXML(true)), modCount, matchCount, nil
 	}

-	return doc.OutputXML(true), modCount, matchCount, nil
+	// Convert numeric entities to named entities for better readability
+	return ConvertToNamedEntities(doc.OutputXML(true)), modCount, matchCount, nil
 }

 // ToLua converts XML node values to Lua variables
@@ -268,3 +269,127 @@ func nodeTypeName(nodeType xmlquery.NodeType) string {
 		return "unknown"
 	}
 }
+
+// ConvertToNamedEntities replaces numeric XML entities with their named counterparts
+func ConvertToNamedEntities(xml string) string {
+	// Basic XML entities
+	replacements := map[string]string{
+		// Basic XML entities
+		"&#34;": "&quot;", // double quote
+		"&#39;": "&apos;", // single quote
+		"&#60;": "&lt;",   // less than
+		"&#62;": "&gt;",   // greater than
+		"&#38;": "&amp;",  // ampersand
+
+		// Common symbols
+		"&#160;":  "&nbsp;",   // non-breaking space
+		"&#169;":  "&copy;",   // copyright
+		"&#174;":  "&reg;",    // registered trademark
+		"&#8364;": "&euro;",   // euro
+		"&#163;":  "&pound;",  // pound
+		"&#165;":  "&yen;",    // yen
+		"&#162;":  "&cent;",   // cent
+		"&#167;":  "&sect;",   // section
+		"&#8482;": "&trade;",  // trademark
+		"&#9824;": "&spades;", // spade
+		"&#9827;": "&clubs;",  // club
+		"&#9829;": "&hearts;", // heart
+		"&#9830;": "&diams;",  // diamond
+
+		// Special characters
+		"&#161;":  "&iexcl;",  // inverted exclamation
+		"&#191;":  "&iquest;", // inverted question
+		"&#171;":  "&laquo;",  // left angle quotes
+		"&#187;":  "&raquo;",  // right angle quotes
+		"&#183;":  "&middot;", // middle dot
+		"&#8226;": "&bull;",   // bullet
+		"&#8230;": "&hellip;", // horizontal ellipsis
+		"&#8242;": "&prime;",  // prime
+		"&#8243;": "&Prime;",  // double prime
+		"&#8254;": "&oline;",  // overline
+		"&#8260;": "&frasl;",  // fraction slash
+
+		// Math symbols
+		"&#177;":  "&plusmn;", // plus-minus
+		"&#215;":  "&times;",  // multiplication
+		"&#247;":  "&divide;", // division
+		"&#8734;": "&infin;",  // infinity
+		"&#8776;": "&asymp;",  // almost equal
+		"&#8800;": "&ne;",     // not equal
+		"&#8804;": "&le;",     // less than or equal
+		"&#8805;": "&ge;",     // greater than or equal
+		"&#8721;": "&sum;",    // summation
+		"&#8730;": "&radic;",  // square root
+		"&#8747;": "&int;",    // integral
+
+		// Accented characters
+		"&#192;": "&Agrave;", // A grave
+		"&#193;": "&Aacute;", // A acute
+		"&#194;": "&Acirc;",  // A circumflex
+		"&#195;": "&Atilde;", // A tilde
+		"&#196;": "&Auml;",   // A umlaut
+		"&#197;": "&Aring;",  // A ring
+		"&#198;": "&AElig;",  // AE ligature
+		"&#199;": "&Ccedil;", // C cedilla
+		"&#200;": "&Egrave;", // E grave
+		"&#201;": "&Eacute;", // E acute
+		"&#202;": "&Ecirc;",  // E circumflex
+		"&#203;": "&Euml;",   // E umlaut
+		"&#204;": "&Igrave;", // I grave
+		"&#205;": "&Iacute;", // I acute
+		"&#206;": "&Icirc;",  // I circumflex
+		"&#207;": "&Iuml;",   // I umlaut
+		"&#208;": "&ETH;",    // Eth
+		"&#209;": "&Ntilde;", // N tilde
+		"&#210;": "&Ograve;", // O grave
+		"&#211;": "&Oacute;", // O acute
+		"&#212;": "&Ocirc;",  // O circumflex
+		"&#213;": "&Otilde;", // O tilde
+		"&#214;": "&Ouml;",   // O umlaut
+		"&#216;": "&Oslash;", // O slash
+		"&#217;": "&Ugrave;", // U grave
+		"&#218;": "&Uacute;", // U acute
+		"&#219;": "&Ucirc;",  // U circumflex
+		"&#220;": "&Uuml;",   // U umlaut
+		"&#221;": "&Yacute;", // Y acute
+		"&#222;": "&THORN;",  // Thorn
+		"&#223;": "&szlig;",  // Sharp s
+		"&#224;": "&agrave;", // a grave
+		"&#225;": "&aacute;", // a acute
+		"&#226;": "&acirc;",  // a circumflex
+		"&#227;": "&atilde;", // a tilde
+		"&#228;": "&auml;",   // a umlaut
+		"&#229;": "&aring;",  // a ring
+		"&#230;": "&aelig;",  // ae ligature
+		"&#231;": "&ccedil;", // c cedilla
+		"&#232;": "&egrave;", // e grave
+		"&#233;": "&eacute;", // e acute
+		"&#234;": "&ecirc;",  // e circumflex
+		"&#235;": "&euml;",   // e umlaut
+		"&#236;": "&igrave;", // i grave
+		"&#237;": "&iacute;", // i acute
+		"&#238;": "&icirc;",  // i circumflex
+		"&#239;": "&iuml;",   // i umlaut
+		"&#240;": "&eth;",    // eth
+		"&#241;": "&ntilde;", // n tilde
+		"&#242;": "&ograve;", // o grave
+		"&#243;": "&oacute;", // o acute
+		"&#244;": "&ocirc;",  // o circumflex
+		"&#245;": "&otilde;", // o tilde
+		"&#246;": "&ouml;",   // o umlaut
+		"&#248;": "&oslash;", // o slash
+		"&#249;": "&ugrave;", // u grave
+		"&#250;": "&uacute;", // u acute
+		"&#251;": "&ucirc;",  // u circumflex
+		"&#252;": "&uuml;",   // u umlaut
+		"&#253;": "&yacute;", // y acute
+		"&#254;": "&thorn;",  // thorn
+		"&#255;": "&yuml;",   // y umlaut
+	}
+
+	result := xml
+	for numeric, named := range replacements {
+		result = strings.ReplaceAll(result, numeric, named)
+	}
+	return result
+}