Author: rdonkin
Date: Sun Jul 6 03:23:15 2008
New Revision: 674281
URL: http://svn.apache.org/viewvc?rev=674281&view=rev
Log:
This change breaks backwards compatibility but I think is justified. I agree
that defaulting is appropriate for TEXT types but is very unreliable for other
types. For many types conversion to characters is not appropriate (for example,
image/png). For other types, the type itself contains charset meta-data (for
example application/xhtml+xml). By defaulting in these cases information is
lost: it is not possible to destinguish between the case when the charset
parameters is explicitly set to us-ascii and when the charset is unset. Non
TEXT types cannot be assumed to default to us-ascii and so this behaviour is
potentially dangerous.
Modified:
james/mime4j/trunk/src/main/java/org/apache/james/mime4j/ContentDescriptor.java
james/mime4j/trunk/src/main/java/org/apache/james/mime4j/DefaultBodyDescriptor.java
james/mime4j/trunk/src/test/java/org/apache/james/mime4j/BaseTestForBodyDescriptors.java
Modified:
james/mime4j/trunk/src/main/java/org/apache/james/mime4j/ContentDescriptor.java
URL:
http://svn.apache.org/viewvc/james/mime4j/trunk/src/main/java/org/apache/james/mime4j/ContentDescriptor.java?rev=674281&r1=674280&r2=674281&view=diff
==============================================================================
---
james/mime4j/trunk/src/main/java/org/apache/james/mime4j/ContentDescriptor.java
(original)
+++
james/mime4j/trunk/src/main/java/org/apache/james/mime4j/ContentDescriptor.java
Sun Jul 6 03:23:15 2008
@@ -56,10 +56,15 @@
String getSubType();
/**
- * The body descriptors character set.
+ * <p>The body descriptors character set, defaulted appropriately for the
MIME type.</p>
+ * <p>
+ * For <code>TEXT</code> types, this will be defaulted to
<code>us-ascii</code>.
+ * For other types, when the charset parameter is missing this property
will be null.
+ * </p>
* @return Character set, which has been parsed from the
- * content-type definition. Must not be null, but "US-ASCII",
- * if no content-type was specified.
+ * content-type definition. Not null for <code>TEXT</code> types, when
unset will
+ * be set to default <code>us-ascii</code>. For other types, when unset,
+ * null will be returnedsvn s
*/
String getCharset();
Modified:
james/mime4j/trunk/src/main/java/org/apache/james/mime4j/DefaultBodyDescriptor.java
URL:
http://svn.apache.org/viewvc/james/mime4j/trunk/src/main/java/org/apache/james/mime4j/DefaultBodyDescriptor.java?rev=674281&r1=674280&r2=674281&view=diff
==============================================================================
---
james/mime4j/trunk/src/main/java/org/apache/james/mime4j/DefaultBodyDescriptor.java
(original)
+++
james/mime4j/trunk/src/main/java/org/apache/james/mime4j/DefaultBodyDescriptor.java
Sun Jul 6 03:23:15 2008
@@ -33,6 +33,8 @@
* @version $Id: BodyDescriptor.java,v 1.4 2005/02/11 10:08:37 ntherning Exp $
*/
public class DefaultBodyDescriptor implements MutableBodyDescriptor {
+ private static final String US_ASCII = "us-ascii";
+
private static final String SUB_TYPE_EMAIL = "rfc822";
private static final String MEDIA_TYPE_TEXT = "text";
@@ -53,7 +55,7 @@
private String subType = DEFAULT_SUB_TYPE;
private String mimeType = DEFAULT_MIME_TYPE;
private String boundary = null;
- private String charset = "us-ascii";
+ private String charset = US_ASCII;
private String transferEncoding = "7bit";
private Map parameters = new HashMap();
private boolean contentTypeSet;
@@ -158,12 +160,16 @@
}
String c = (String) params.get("charset");
+ charset = null;
if (c != null) {
c = c.trim();
if (c.length() > 0) {
charset = c.toLowerCase();
}
}
+ if (charset == null && MEDIA_TYPE_TEXT.equals(mediaType)) {
+ charset = US_ASCII;
+ }
/*
* Add all other parameters to parameters.
Modified:
james/mime4j/trunk/src/test/java/org/apache/james/mime4j/BaseTestForBodyDescriptors.java
URL:
http://svn.apache.org/viewvc/james/mime4j/trunk/src/test/java/org/apache/james/mime4j/BaseTestForBodyDescriptors.java?rev=674281&r1=674280&r2=674281&view=diff
==============================================================================
---
james/mime4j/trunk/src/test/java/org/apache/james/mime4j/BaseTestForBodyDescriptors.java
(original)
+++
james/mime4j/trunk/src/test/java/org/apache/james/mime4j/BaseTestForBodyDescriptors.java
Sun Jul 6 03:23:15 2008
@@ -146,12 +146,12 @@
*/
bd = newBodyDescriptor();
assertEquals("us-ascii", bd.getCharset());
- bd.addField("Content-Type ", "some/type; charset=ISO-8859-1");
+ bd.addField("Content-Type ", "text/type; charset=ISO-8859-1");
assertEquals("iso-8859-1", bd.getCharset());
bd = newBodyDescriptor();
assertEquals("us-ascii", bd.getCharset());
- bd.addField("Content-Type ", "some/type");
+ bd.addField("Content-Type ", "text/type");
assertEquals("us-ascii", bd.getCharset());
/*
@@ -184,5 +184,16 @@
assertEquals("\"hepp\" =us\t-ascii", bd.getCharset());
}
+
+ public void testDoDefaultToUsAsciiWhenUntyped() throws Exception {
+ MutableBodyDescriptor descriptor = newBodyDescriptor();
+ descriptor.addField("To", "[EMAIL PROTECTED]");
+ assertEquals("us-ascii", descriptor.getCharset());
+ }
+ public void testDoNotDefaultToUsAsciiForNonTextTypes() throws Exception {
+ MutableBodyDescriptor descriptor = newBodyDescriptor();
+ descriptor.addField("Content-Type", "image/png; name=blob.png");
+ assertNull(descriptor.getCharset());
+ }
}
---------------------------------------------------------------------
To unsubscribe, e-mail: [EMAIL PROTECTED]
For additional commands, e-mail: [EMAIL PROTECTED]
