EncodingSniffer: change meta tag parsing to case insensitive

duonglaiquang · rbri · commit 38ee3c6ba71a · 2024-04-01T13:40:54.000+02:00
diff --git a/src/main/java/org/htmlunit/util/EncodingSniffer.java b/src/main/java/org/htmlunit/util/EncodingSniffer.java
@@ -455,8 +455,8 @@ else if (matches(bytes, i, META_START)) {
                 i += META_START.length;
                 for (Attribute att = getAttribute(bytes, i); att != null; att = getAttribute(bytes, i)) {
                     i = att.getUpdatedIndex();
-                    final String name = att.getName();
-                    final String value = att.getValue();
+                    final String name = att.getName().toLowerCase(Locale.ROOT);
+                    final String value = att.getValue().toLowerCase(Locale.ROOT);
                     if ("charset".equals(name) || "content".equals(name)) {
                         Charset charset = null;
                         if ("charset".equals(name)) {
diff --git a/src/test/java/org/htmlunit/util/EncodingSnifferTest.java b/src/test/java/org/htmlunit/util/EncodingSnifferTest.java
@@ -80,6 +80,7 @@ public void fromMetaTag() throws Exception {
         meta(UTF_8, "abc <meta http-equiv='Content-Type' content='text/html; charset=utf-8'/>");
         meta(UTF_8, "abc <meta http-equiv='Content-Type' content='text/html; CHARSET=UTF-8'/>");
         meta(UTF_8, "abc <meta http-equiv='Content-Type' content='text/html; chArsEt=UtF-8'/>");
+        meta(UTF_8, "<meta a='b' c=d e=\"f\" CONTENT='text/html; CHARSET=utf-8' />");
     }
 
     private static void meta(final Charset expectedEncoding, final String content) throws Exception {

Original file line number	Diff line number	Diff line change
`@@ -80,6 +80,7 @@ public void fromMetaTag() throws Exception {`
`80`	`80`	`meta(UTF_8, "abc <meta http-equiv='Content-Type' content='text/html; charset=utf-8'/>");`
`81`	`81`	`meta(UTF_8, "abc <meta http-equiv='Content-Type' content='text/html; CHARSET=UTF-8'/>");`
`82`	`82`	`meta(UTF_8, "abc <meta http-equiv='Content-Type' content='text/html; chArsEt=UtF-8'/>");`
	`83`	`+ meta(UTF_8, "<meta a='b' c=d e=\"f\" CONTENT='text/html; CHARSET=utf-8' />");`
`83`	`84`	`}`
`84`	`85`
`85`	`86`	`private static void meta(final Charset expectedEncoding, final String content) throws Exception {`