Improve handling of certain html tags

Foorack · Foorack · commit 5d6d2a76c2ea · 2020-04-18T00:26:57.000+02:00
diff --git a/UdonXML.cs b/UdonXML.cs
@@ -381,7 +381,21 @@ private object[] Parse(char[] input)
                         }
                         else
                         {
-                            tagName += c + "";
+                            // i.e. bordered in <table>, or html in <doctype>, sometimes they don't have values
+                            if (c == ' ')
+                            {
+                                // Add tag
+                                if (tagName.Trim().Length != 0)
+                                {
+                                    tagNames = AddLastToStringArray(tagNames, tagName.Trim());
+                                    tagValues = AddLastToStringArray(tagValues, null);
+                                    tagName = "";
+                                }
+                            }
+                            else
+                            {
+                                tagName += c + "";
+                            }
                         }
                     }
                     else
@@ -444,7 +458,19 @@ private string Serialize(object[] data, string padding)
             var tagList = "";
             for (var i = 0; i != tagNames.Length; i++)
             {
-                tagList += " " + tagNames[i] + "=\"" + tagValues[i] + "\"";
+                var tagValue = (string) tagValues[i];
+                Debug.Log(tagValue);
+                Debug.Log((tagValue == null) + " " + (null == tagValue));
+                Debug.Log("");
+                if (null == tagValue)
+                {
+                    // Tags without value, such as bordered in table, or html in doctype
+                    tagList += " " + tagNames[i];
+                }
+                else
+                {
+                    tagList += " " + tagNames[i] + "=\"" + tagValues[i] + "\"";
+                }
             }
 
             if (nodeChildren.Length == 0)
@@ -455,7 +481,7 @@ private string Serialize(object[] data, string padding)
                     {
                         output += $"<{nodeName}{tagList}?>"; // ?xml has an extra ? at the end
                     }
-                    else if (nodeName == "!DOCTYPE")
+                    else if (nodeName.ToUpper() == "!DOCTYPE")
                     {
                         output += $"<{nodeName}{tagList}>"; // doc types are self closing without the usual slash
                     }
diff --git a/UdonXMLTest.cs b/UdonXMLTest.cs
@@ -595,9 +595,57 @@ public class UdonXMLTest : UdonSharpBehaviour
    </w:body>
 </w:document>";
 
+    private string EXAMPLE_DATA_6 = @"<!doctype html >
+<html>
+<head>
+    <title>Example Domain</title>
+
+    <meta charset=""utf-8"" />
+    <meta http-equiv=""Content-type"" content=""text/html; charset=utf-8"" />
+    <meta name=""viewport"" content=""width=device-width, initial-scale=1"" />
+    <style type=""text/css"">
+    body {
+        background-color: #f0f0f2;
+        margin: 0;
+        padding: 0;
+        font-family: -apple-system, system-ui, BlinkMacSystemFont, ""Segoe UI"", ""Open Sans"", ""Helvetica Neue"", Helvetica, Arial, sans-serif;
+        
+    }
+    div {
+        width: 600px;
+        margin: 5em auto;
+        padding: 2em;
+        background-color: #fdfdff;
+        border-radius: 0.5em;
+        box-shadow: 2px 3px 7px 2px rgba(0,0,0,0.02);
+    }
+    a:link, a:visited {
+        color: #38488f;
+        text-decoration: none;
+    }
+    @media (max-width: 700px) {
+        div {
+            margin: 0 auto;
+            width: auto;
+        }
+    }
+    </style>    
+</head>
+
+<body>
+<div>
+    <h1>Example Domain</h1>
+    <p>This domain is for use in illustrative examples in documents. You may use this
+    domain in literature without prior coordination or asking for permission.</p>
+    <p><a href=""https://www.iana.org/domains/example"">More information...</a></p>
+</div>
+</body>
+</html>
+";
+
     public void Start()
     {
-        var root = udonXml.LoadXml(EXAMPLE_DATA_5);
+        var root = udonXml.LoadXml(EXAMPLE_DATA_6);
 
         if (root == null)
         {

Original file line number	Diff line number	Diff line change
`@@ -381,7 +381,21 @@ private object[] Parse(char[] input)`
`381`	`381`	`}`
`382`	`382`	`else`
`383`	`383`	`{`
`384`		`- tagName += c + "";`
	`384`	`+ // i.e. bordered in <table>, or html in <doctype>, sometimes they don't have values`
	`385`	`+ if (c == ' ')`
	`386`	`+ {`
	`387`	`+ // Add tag`
	`388`	`+ if (tagName.Trim().Length != 0)`
	`389`	`+ {`
	`390`	`+ tagNames = AddLastToStringArray(tagNames, tagName.Trim());`
	`391`	`+ tagValues = AddLastToStringArray(tagValues, null);`
	`392`	`+ tagName = "";`
	`393`	`+ }`
	`394`	`+ }`
	`395`	`+ else`
	`396`	`+ {`
	`397`	`+ tagName += c + "";`
	`398`	`+ }`
`385`	`399`	`}`
`386`	`400`	`}`
`387`	`401`	`else`
`@@ -444,7 +458,19 @@ private string Serialize(object[] data, string padding)`
`444`	`458`	`var tagList = "";`
`445`	`459`	`for (var i = 0; i != tagNames.Length; i++)`
`446`	`460`	`{`
`447`		`- tagList += " " + tagNames[i] + "=\"" + tagValues[i] + "\"";`
	`461`	`+ var tagValue = (string) tagValues[i];`
	`462`	`+ Debug.Log(tagValue);`
	`463`	`+ Debug.Log((tagValue == null) + " " + (null == tagValue));`
	`464`	`+ Debug.Log("");`
	`465`	`+ if (null == tagValue)`
	`466`	`+ {`
	`467`	`+ // Tags without value, such as bordered in table, or html in doctype`
	`468`	`+ tagList += " " + tagNames[i];`
	`469`	`+ }`
	`470`	`+ else`
	`471`	`+ {`
	`472`	`+ tagList += " " + tagNames[i] + "=\"" + tagValues[i] + "\"";`
	`473`	`+ }`
`448`	`474`	`}`
`449`	`475`
`450`	`476`	`if (nodeChildren.Length == 0)`
`@@ -455,7 +481,7 @@ private string Serialize(object[] data, string padding)`
`455`	`481`	`{`
`456`	`482`	`output += $"<{nodeName}{tagList}?>"; // ?xml has an extra ? at the end`
`457`	`483`	`}`
`458`		`- else if (nodeName == "!DOCTYPE")`
	`484`	`+ else if (nodeName.ToUpper() == "!DOCTYPE")`
`459`	`485`	`{`
`460`	`486`	`output += $"<{nodeName}{tagList}>"; // doc types are self closing without the usual slash`
`461`	`487`	`}`