|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |
java.lang.Objectjava.io.Reader
com.sun.syndication.io.XmlReader
public class XmlReader
Character stream that handles (or at least attemtps to) all the necessary Voodo to figure out the charset encoding of the XML document within the stream.
IMPORTANT: This class is not related in any way to the org.xml.sax.XMLReader. This one IS a character stream.
All this has to be done without consuming characters from the stream, if not the XML parser will not recognized the document as a valid XML. This is not 100% true, but it's close enough (UTF-8 BOM is not handled by all parsers right now, XmlReader handles it and things work in all parsers).
The XmlReader class handles the charset encoding of XML documents in Files, raw streams and HTTP streams by offering a wide set of constructors.
By default the charset encoding detection is lenient, the constructor with the lenient flag can be used for an script (following HTTP MIME and XML specifications). All this is nicely explained by Mark Pilgrim in his blog, Determining the character encoding of a feed.
Field Summary | |
---|---|
private java.lang.String |
_encoding
|
private java.io.Reader |
_reader
|
private static java.util.regex.Pattern |
CHARSET_PATTERN
|
private static java.util.regex.Pattern |
ENCODING_PATTERN
|
private static java.text.MessageFormat |
HTTP_EX_1
|
private static java.text.MessageFormat |
HTTP_EX_2
|
private static java.text.MessageFormat |
HTTP_EX_3
|
private static int |
PUSHBACK_MAX_SIZE
|
private static java.text.MessageFormat |
RAW_EX_1
|
private static java.text.MessageFormat |
RAW_EX_2
|
private static java.lang.String |
US_ASCII
|
private static java.lang.String |
UTF_16
|
private static java.lang.String |
UTF_16BE
|
private static java.lang.String |
UTF_16LE
|
private static java.lang.String |
UTF_8
|
Fields inherited from class java.io.Reader |
---|
lock |
Constructor Summary | |
---|---|
XmlReader(java.io.File file)
Creates a Reader for a File. |
|
XmlReader(java.io.InputStream is)
Creates a Reader for a raw InputStream. |
|
XmlReader(java.io.InputStream is,
boolean lenient)
Creates a Reader for a raw InputStream. |
|
XmlReader(java.io.InputStream is,
java.lang.String httpContentType)
Creates a Reader using an InputStream an the associated content-type header. |
|
XmlReader(java.io.InputStream is,
java.lang.String httpContentType,
boolean lenient)
Creates a Reader using an InputStream an the associated content-type header. |
|
XmlReader(java.net.URL url)
Creates a Reader using the InputStream of a URL. |
|
XmlReader(java.net.URLConnection conn)
Creates a Reader using the InputStream of a URLConnection. |
Method Summary | |
---|---|
private static java.lang.String |
calculateHttpEncoding(java.lang.String cTMime,
java.lang.String cTEnc,
java.lang.String bomEnc,
java.lang.String xmlGuessEnc,
java.lang.String xmlEnc,
java.io.InputStream is,
boolean lenient)
|
private static java.lang.String |
calculateRawEncoding(java.lang.String bomEnc,
java.lang.String xmlGuessEnc,
java.lang.String xmlEnc,
java.io.InputStream is)
|
void |
close()
Closes the XmlReader stream. |
private void |
doHttpStream(java.io.InputStream is,
java.lang.String httpContentType,
boolean lenient)
|
private void |
doLenientDetection(java.lang.String httpContentType,
XmlReaderException ex)
|
private void |
doRawStream(java.io.InputStream is,
boolean lenient)
|
private static java.lang.String |
getBOMEncoding(java.io.PushbackInputStream is)
|
private static java.lang.String |
getContentTypeEncoding(java.lang.String httpContentType)
|
private static java.lang.String |
getContentTypeMime(java.lang.String httpContentType)
|
java.lang.String |
getEncoding()
Returns the charset encoding of the XmlReader. |
private static java.lang.String |
getXMLGuessEncoding(java.io.PushbackInputStream is)
|
private static java.lang.String |
getXmlProlog(java.io.PushbackInputStream is,
java.lang.String guessedEnc)
|
private static boolean |
isAppXml(java.lang.String mime)
|
private static boolean |
isTextXml(java.lang.String mime)
|
private void |
prepareReader(java.io.InputStream is,
java.lang.String encoding)
|
int |
read(char[] buf,
int offset,
int len)
|
Methods inherited from class java.io.Reader |
---|
mark, markSupported, read, read, read, ready, reset, skip |
Methods inherited from class java.lang.Object |
---|
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait |
Field Detail |
---|
private static final int PUSHBACK_MAX_SIZE
private static final java.lang.String UTF_8
private static final java.lang.String US_ASCII
private static final java.lang.String UTF_16BE
private static final java.lang.String UTF_16LE
private static final java.lang.String UTF_16
private java.io.Reader _reader
private java.lang.String _encoding
private static final java.util.regex.Pattern CHARSET_PATTERN
private static final java.util.regex.Pattern ENCODING_PATTERN
private static final java.text.MessageFormat RAW_EX_1
private static final java.text.MessageFormat RAW_EX_2
private static final java.text.MessageFormat HTTP_EX_1
private static final java.text.MessageFormat HTTP_EX_2
private static final java.text.MessageFormat HTTP_EX_3
Constructor Detail |
---|
public XmlReader(java.io.File file) throws java.io.IOException
It looks for the UTF-8 BOM first, if none sniffs the XML prolog charset, if this is also missing defaults to UTF-8.
It does a lenient charset encoding detection, check the constructor with the lenient parameter for details.
file
- File to create a Reader from.
java.io.IOException
- thrown if there is a problem reading the file.public XmlReader(java.io.InputStream is) throws java.io.IOException
It follows the same logic used for files.
It does a lenient charset encoding detection, check the constructor with the lenient parameter for details.
is
- InputStream to create a Reader from.
java.io.IOException
- thrown if there is a problem reading the stream.public XmlReader(java.io.InputStream is, boolean lenient) throws java.io.IOException, XmlReaderException
It follows the same logic used for files.
If lenient detection is indicated and the detection above fails as per specifications it then attempts the following:
If the content type was 'text/html' it replaces it with 'text/xml' and tries the detection again.
Else if the XML prolog had a charset encoding that encoding is used.
Else if the content type had a charset encoding that encoding is used.
Else 'UTF-8' is used.
If lenient detection is indicated an XmlReaderException is never thrown.
is
- InputStream to create a Reader from.lenient
- indicates if the charset encoding detection should be relaxed.
java.io.IOException
- thrown if there is a problem reading the stream.
XmlReaderException
- thrown if the charset encoding could not be determined according to the specs.public XmlReader(java.net.URL url) throws java.io.IOException
If the URL is not of type HTTP and there is not 'content-type' header in the fetched data it uses the same logic used for Files.
If the URL is a HTTP Url or there is a 'content-type' header in the fetched data it uses the same logic used for an InputStream with content-type.
It does a lenient charset encoding detection, check the constructor with the lenient parameter for details.
url
- URL to create a Reader from.
java.io.IOException
- thrown if there is a problem reading the stream of the URL.public XmlReader(java.net.URLConnection conn) throws java.io.IOException
If the URLConnection is not of type HttpURLConnection and there is not 'content-type' header in the fetched data it uses the same logic used for files.
If the URLConnection is a HTTP Url or there is a 'content-type' header in the fetched data it uses the same logic used for an InputStream with content-type.
It does a lenient charset encoding detection, check the constructor with the lenient parameter for details.
conn
- URLConnection to create a Reader from.
java.io.IOException
- thrown if there is a problem reading the stream of the URLConnection.public XmlReader(java.io.InputStream is, java.lang.String httpContentType) throws java.io.IOException
First it checks if the stream has BOM. If there is not BOM checks the content-type encoding. If there is not content-type encoding checks the XML prolog encoding. If there is not XML prolog encoding uses the default encoding mandated by the content-type MIME type.
It does a lenient charset encoding detection, check the constructor with the lenient parameter for details.
is
- InputStream to create the reader from.httpContentType
- content-type header to use for the resolution of the charset encoding.
java.io.IOException
- thrown if there is a problem reading the file.public XmlReader(java.io.InputStream is, java.lang.String httpContentType, boolean lenient) throws java.io.IOException, XmlReaderException
First it checks if the stream has BOM. If there is not BOM checks the content-type encoding. If there is not content-type encoding checks the XML prolog encoding. If there is not XML prolog encoding uses the default encoding mandated by the content-type MIME type.
If lenient detection is indicated and the detection above fails as per specifications it then attempts the following:
If the content type was 'text/html' it replaces it with 'text/xml' and tries the detection again.
Else if the XML prolog had a charset encoding that encoding is used.
Else if the content type had a charset encoding that encoding is used.
Else 'UTF-8' is used.
If lenient detection is indicated an XmlReaderException is never thrown.
is
- InputStream to create the reader from.httpContentType
- content-type header to use for the resolution of the charset encoding.lenient
- indicates if the charset encoding detection should be relaxed.
java.io.IOException
- thrown if there is a problem reading the file.
XmlReaderException
- thrown if the charset encoding could not be determined according to the specs.Method Detail |
---|
private void doLenientDetection(java.lang.String httpContentType, XmlReaderException ex) throws java.io.IOException
java.io.IOException
public java.lang.String getEncoding()
public int read(char[] buf, int offset, int len) throws java.io.IOException
read
in class java.io.Reader
java.io.IOException
public void close() throws java.io.IOException
close
in interface java.io.Closeable
close
in class java.io.Reader
java.io.IOException
- thrown if there was a problem closing the stream.private void doRawStream(java.io.InputStream is, boolean lenient) throws java.io.IOException
java.io.IOException
private void doHttpStream(java.io.InputStream is, java.lang.String httpContentType, boolean lenient) throws java.io.IOException
java.io.IOException
private void prepareReader(java.io.InputStream is, java.lang.String encoding) throws java.io.IOException
java.io.IOException
private static java.lang.String calculateRawEncoding(java.lang.String bomEnc, java.lang.String xmlGuessEnc, java.lang.String xmlEnc, java.io.InputStream is) throws java.io.IOException
java.io.IOException
private static java.lang.String calculateHttpEncoding(java.lang.String cTMime, java.lang.String cTEnc, java.lang.String bomEnc, java.lang.String xmlGuessEnc, java.lang.String xmlEnc, java.io.InputStream is, boolean lenient) throws java.io.IOException
java.io.IOException
private static java.lang.String getContentTypeMime(java.lang.String httpContentType)
private static java.lang.String getContentTypeEncoding(java.lang.String httpContentType)
private static java.lang.String getBOMEncoding(java.io.PushbackInputStream is) throws java.io.IOException
java.io.IOException
private static java.lang.String getXMLGuessEncoding(java.io.PushbackInputStream is) throws java.io.IOException
java.io.IOException
private static java.lang.String getXmlProlog(java.io.PushbackInputStream is, java.lang.String guessedEnc) throws java.io.IOException
java.io.IOException
private static boolean isAppXml(java.lang.String mime)
private static boolean isTextXml(java.lang.String mime)
|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |