Formatted and cleaned up sources
This commit is contained in:
Patrick Gotthard
parent
6eca421a93
commit
ed8691df13
93 changed files with 1089 additions and 1055 deletions
|
|
@ -34,18 +34,25 @@ import java.util.regex.Matcher;
|
|||
import java.util.regex.Pattern;
|
||||
|
||||
/**
|
||||
* 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.
|
||||
* 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.
|
||||
* <p>
|
||||
* IMPORTANT: This class is not related in any way to the org.xml.sax.XMLReader. This one IS a character stream.
|
||||
* IMPORTANT: This class is not related in any way to the org.xml.sax.XMLReader. This one IS a
|
||||
* character stream.
|
||||
* <p>
|
||||
* 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).
|
||||
* 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).
|
||||
* <p>
|
||||
* The XmlReader class handles the charset encoding of XML documents in Files, raw streams and HTTP streams by offering a wide set of constructors.
|
||||
* The XmlReader class handles the charset encoding of XML documents in Files, raw streams and HTTP
|
||||
* streams by offering a wide set of constructors.
|
||||
* <P>
|
||||
* 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, <a href="http://diveintomark.org/archives/2004/02/13/xml-media-types"> Determining
|
||||
* the character encoding of a feed</a>.
|
||||
* 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, <a
|
||||
* href="http://diveintomark.org/archives/2004/02/13/xml-media-types"> Determining the character
|
||||
* encoding of a feed</a>.
|
||||
* <p>
|
||||
*
|
||||
* @author Alejandro Abdelnur
|
||||
|
|
@ -80,9 +87,11 @@ public class XmlReader extends Reader {
|
|||
/**
|
||||
* Creates a Reader for a File.
|
||||
* <p>
|
||||
* 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 looks for the UTF-8 BOM first, if none sniffs the XML prolog charset, if this is also
|
||||
* missing defaults to UTF-8.
|
||||
* <p>
|
||||
* It does a lenient charset encoding detection, check the constructor with the lenient parameter for details.
|
||||
* It does a lenient charset encoding detection, check the constructor with the lenient
|
||||
* parameter for details.
|
||||
* <p>
|
||||
*
|
||||
* @param file File to create a Reader from.
|
||||
|
|
@ -98,7 +107,8 @@ public class XmlReader extends Reader {
|
|||
* <p>
|
||||
* It follows the same logic used for files.
|
||||
* <p>
|
||||
* It does a lenient charset encoding detection, check the constructor with the lenient parameter for details.
|
||||
* It does a lenient charset encoding detection, check the constructor with the lenient
|
||||
* parameter for details.
|
||||
* <p>
|
||||
*
|
||||
* @param is InputStream to create a Reader from.
|
||||
|
|
@ -110,13 +120,16 @@ public class XmlReader extends Reader {
|
|||
}
|
||||
|
||||
/**
|
||||
* Creates a Reader for a raw InputStream and uses the provided default encoding if none is determined.
|
||||
* Creates a Reader for a raw InputStream and uses the provided default encoding if none is
|
||||
* determined.
|
||||
* <p>
|
||||
* It follows the same logic used for files.
|
||||
* <p>
|
||||
* If lenient detection is indicated and the detection above fails as per specifications it then attempts the following:
|
||||
* If lenient detection is indicated and the detection above fails as per specifications it then
|
||||
* attempts the following:
|
||||
* <p>
|
||||
* If the content type was 'text/html' it replaces it with 'text/xml' and tries the detection again.
|
||||
* If the content type was 'text/html' it replaces it with 'text/xml' and tries the detection
|
||||
* again.
|
||||
* <p>
|
||||
* Else if the XML prolog had a charset encoding that encoding is used.
|
||||
* <p>
|
||||
|
|
@ -131,7 +144,8 @@ public class XmlReader extends Reader {
|
|||
* @param lenient indicates if the charset encoding detection should be relaxed.
|
||||
* @param defaultEncoding default encoding to use if one cannot be detected.
|
||||
* @throws IOException thrown if there is a problem reading the stream.
|
||||
* @throws XmlReaderException thrown if the charset encoding could not be determined according to the specs.
|
||||
* @throws XmlReaderException thrown if the charset encoding could not be determined according
|
||||
* to the specs.
|
||||
*
|
||||
*/
|
||||
public XmlReader(final InputStream is, final boolean lenient, final String defaultEncoding) throws IOException, XmlReaderException {
|
||||
|
|
@ -156,9 +170,11 @@ public class XmlReader extends Reader {
|
|||
* <p>
|
||||
* It follows the same logic used for files.
|
||||
* <p>
|
||||
* If lenient detection is indicated and the detection above fails as per specifications it then attempts the following:
|
||||
* If lenient detection is indicated and the detection above fails as per specifications it then
|
||||
* attempts the following:
|
||||
* <p>
|
||||
* If the content type was 'text/html' it replaces it with 'text/xml' and tries the detection again.
|
||||
* If the content type was 'text/html' it replaces it with 'text/xml' and tries the detection
|
||||
* again.
|
||||
* <p>
|
||||
* Else if the XML prolog had a charset encoding that encoding is used.
|
||||
* <p>
|
||||
|
|
@ -172,7 +188,8 @@ public class XmlReader extends Reader {
|
|||
* @param is InputStream to create a Reader from.
|
||||
* @param lenient indicates if the charset encoding detection should be relaxed.
|
||||
* @throws IOException thrown if there is a problem reading the stream.
|
||||
* @throws XmlReaderException thrown if the charset encoding could not be determined according to the specs.
|
||||
* @throws XmlReaderException thrown if the charset encoding could not be determined according
|
||||
* to the specs.
|
||||
*
|
||||
*/
|
||||
public XmlReader(final InputStream is, final boolean lenient) throws IOException, XmlReaderException {
|
||||
|
|
@ -182,11 +199,14 @@ public class XmlReader extends Reader {
|
|||
/**
|
||||
* Creates a Reader using the InputStream of a URL.
|
||||
* <p>
|
||||
* 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 not of type HTTP and there is not 'content-type' header in the fetched data it
|
||||
* uses the same logic used for Files.
|
||||
* <p>
|
||||
* 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.
|
||||
* 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.
|
||||
* <p>
|
||||
* It does a lenient charset encoding detection, check the constructor with the lenient parameter for details.
|
||||
* It does a lenient charset encoding detection, check the constructor with the lenient
|
||||
* parameter for details.
|
||||
* <p>
|
||||
*
|
||||
* @param url URL to create a Reader from.
|
||||
|
|
@ -200,12 +220,14 @@ public class XmlReader extends Reader {
|
|||
/**
|
||||
* Creates a Reader using the InputStream of a URLConnection.
|
||||
* <p>
|
||||
* 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 not of type HttpURLConnection and there is not 'content-type' header
|
||||
* in the fetched data it uses the same logic used for files.
|
||||
* <p>
|
||||
* 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.
|
||||
* 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.
|
||||
* <p>
|
||||
* It does a lenient charset encoding detection, check the constructor with the lenient parameter for details.
|
||||
* It does a lenient charset encoding detection, check the constructor with the lenient
|
||||
* parameter for details.
|
||||
* <p>
|
||||
*
|
||||
* @param conn URLConnection to create a Reader from.
|
||||
|
|
@ -245,10 +267,12 @@ public class XmlReader extends Reader {
|
|||
/**
|
||||
* Creates a Reader using an InputStream and the associated content-type header.
|
||||
* <p>
|
||||
* 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.
|
||||
* 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.
|
||||
* <p>
|
||||
* It does a lenient charset encoding detection, check the constructor with the lenient parameter for details.
|
||||
* It does a lenient charset encoding detection, check the constructor with the lenient
|
||||
* parameter for details.
|
||||
* <p>
|
||||
*
|
||||
* @param is InputStream to create the reader from.
|
||||
|
|
@ -263,12 +287,15 @@ public class XmlReader extends Reader {
|
|||
/**
|
||||
* Creates a Reader using an InputStream and the associated content-type header.
|
||||
* <p>
|
||||
* 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.
|
||||
* 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.
|
||||
* <p>
|
||||
* If lenient detection is indicated and the detection above fails as per specifications it then attempts the following:
|
||||
* If lenient detection is indicated and the detection above fails as per specifications it then
|
||||
* attempts the following:
|
||||
* <p>
|
||||
* If the content type was 'text/html' it replaces it with 'text/xml' and tries the detection again.
|
||||
* If the content type was 'text/html' it replaces it with 'text/xml' and tries the detection
|
||||
* again.
|
||||
* <p>
|
||||
* Else if the XML prolog had a charset encoding that encoding is used.
|
||||
* <p>
|
||||
|
|
@ -284,7 +311,8 @@ public class XmlReader extends Reader {
|
|||
* @param lenient indicates if the charset encoding detection should be relaxed.
|
||||
* @param defaultEncoding default encoding to use if one cannot be detected.
|
||||
* @throws IOException thrown if there is a problem reading the file.
|
||||
* @throws XmlReaderException thrown if the charset encoding could not be determined according to the specs.
|
||||
* @throws XmlReaderException thrown if the charset encoding could not be determined according
|
||||
* to the specs.
|
||||
*
|
||||
*/
|
||||
public XmlReader(final InputStream is, final String httpContentType, final boolean lenient, final String defaultEncoding) throws IOException,
|
||||
|
|
@ -308,12 +336,15 @@ public class XmlReader extends Reader {
|
|||
/**
|
||||
* Creates a Reader using an InputStream and the associated content-type header.
|
||||
* <p>
|
||||
* 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.
|
||||
* 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.
|
||||
* <p>
|
||||
* If lenient detection is indicated and the detection above fails as per specifications it then attempts the following:
|
||||
* If lenient detection is indicated and the detection above fails as per specifications it then
|
||||
* attempts the following:
|
||||
* <p>
|
||||
* If the content type was 'text/html' it replaces it with 'text/xml' and tries the detection again.
|
||||
* If the content type was 'text/html' it replaces it with 'text/xml' and tries the detection
|
||||
* again.
|
||||
* <p>
|
||||
* Else if the XML prolog had a charset encoding that encoding is used.
|
||||
* <p>
|
||||
|
|
@ -328,7 +359,8 @@ public class XmlReader extends Reader {
|
|||
* @param httpContentType content-type header to use for the resolution of the charset encoding.
|
||||
* @param lenient indicates if the charset encoding detection should be relaxed.
|
||||
* @throws IOException thrown if there is a problem reading the file.
|
||||
* @throws XmlReaderException thrown if the charset encoding could not be determined according to the specs.
|
||||
* @throws XmlReaderException thrown if the charset encoding could not be determined according
|
||||
* to the specs.
|
||||
*
|
||||
*/
|
||||
public XmlReader(final InputStream is, final String httpContentType, final boolean lenient) throws IOException, XmlReaderException {
|
||||
|
|
@ -336,7 +368,8 @@ public class XmlReader extends Reader {
|
|||
}
|
||||
|
||||
/**
|
||||
* Returns the default encoding to use if none is set in HTTP content-type, XML prolog and the rules based on content-type are not adequate.
|
||||
* Returns the default encoding to use if none is set in HTTP content-type, XML prolog and the
|
||||
* rules based on content-type are not adequate.
|
||||
* <p/>
|
||||
* If it is NULL the content-type based rules are used.
|
||||
* <p/>
|
||||
|
|
@ -348,7 +381,8 @@ public class XmlReader extends Reader {
|
|||
}
|
||||
|
||||
/**
|
||||
* Sets the default encoding to use if none is set in HTTP content-type, XML prolog and the rules based on content-type are not adequate.
|
||||
* Sets the default encoding to use if none is set in HTTP content-type, XML prolog and the
|
||||
* rules based on content-type are not adequate.
|
||||
* <p/>
|
||||
* If it is set to NULL the content-type based rules are used.
|
||||
* <p/>
|
||||
|
|
|
|||
|
|
@ -689,7 +689,7 @@ public class Atom10Parser extends BaseWireFeedParser {
|
|||
* Parse entry from reader.
|
||||
*/
|
||||
public static Entry parseEntry(final Reader rd, final String baseURI, final Locale locale) throws JDOMException, IOException, IllegalArgumentException,
|
||||
FeedException {
|
||||
FeedException {
|
||||
|
||||
// Parse entry into JDOM tree
|
||||
final SAXBuilder builder = new SAXBuilder();
|
||||
|
|
|
|||
|
|
@ -48,17 +48,17 @@ public class DateParser {
|
|||
// parse a valid date out of a substring of the full string given the mask so we have to check
|
||||
// the most complete format first, then it fails with exception
|
||||
private static final String[] W3CDATETIME_MASKS = { "yyyy-MM-dd'T'HH:mm:ss.SSSz", "yyyy-MM-dd't'HH:mm:ss.SSSz", "yyyy-MM-dd'T'HH:mm:ss.SSS'Z'",
|
||||
"yyyy-MM-dd't'HH:mm:ss.SSS'z'", "yyyy-MM-dd'T'HH:mm:ssz", "yyyy-MM-dd't'HH:mm:ssz", "yyyy-MM-dd'T'HH:mm:ssZ", "yyyy-MM-dd't'HH:mm:ssZ",
|
||||
"yyyy-MM-dd'T'HH:mm:ss'Z'", "yyyy-MM-dd't'HH:mm:ss'z'", "yyyy-MM-dd'T'HH:mmz", // together
|
||||
// with
|
||||
// logic
|
||||
// in
|
||||
// the
|
||||
// parseW3CDateTime
|
||||
// they
|
||||
"yyyy-MM'T'HH:mmz", // handle W3C dates without time forcing them to
|
||||
// be GMT
|
||||
"yyyy'T'HH:mmz", "yyyy-MM-dd't'HH:mmz", "yyyy-MM-dd'T'HH:mm'Z'", "yyyy-MM-dd't'HH:mm'z'", "yyyy-MM-dd", "yyyy-MM", "yyyy" };
|
||||
"yyyy-MM-dd't'HH:mm:ss.SSS'z'", "yyyy-MM-dd'T'HH:mm:ssz", "yyyy-MM-dd't'HH:mm:ssz", "yyyy-MM-dd'T'HH:mm:ssZ", "yyyy-MM-dd't'HH:mm:ssZ",
|
||||
"yyyy-MM-dd'T'HH:mm:ss'Z'", "yyyy-MM-dd't'HH:mm:ss'z'", "yyyy-MM-dd'T'HH:mmz", // together
|
||||
// with
|
||||
// logic
|
||||
// in
|
||||
// the
|
||||
// parseW3CDateTime
|
||||
// they
|
||||
"yyyy-MM'T'HH:mmz", // handle W3C dates without time forcing them to
|
||||
// be GMT
|
||||
"yyyy'T'HH:mmz", "yyyy-MM-dd't'HH:mmz", "yyyy-MM-dd'T'HH:mm'Z'", "yyyy-MM-dd't'HH:mm'z'", "yyyy-MM-dd", "yyyy-MM", "yyyy" };
|
||||
|
||||
/**
|
||||
* The masks used to validate and parse the input to this Atom date. These are a lot more
|
||||
|
|
@ -67,14 +67,14 @@ public class DateParser {
|
|||
*/
|
||||
@SuppressWarnings("unused")
|
||||
private static final String[] masks = { "yyyy-MM-dd'T'HH:mm:ss.SSSz", "yyyy-MM-dd't'HH:mm:ss.SSSz", // invalid
|
||||
"yyyy-MM-dd'T'HH:mm:ss.SSS'Z'", "yyyy-MM-dd't'HH:mm:ss.SSS'z'", // invalid
|
||||
"yyyy-MM-dd'T'HH:mm:ssz", "yyyy-MM-dd't'HH:mm:ssz", // invalid
|
||||
"yyyy-MM-dd'T'HH:mm:ss'Z'", "yyyy-MM-dd't'HH:mm:ss'z'", // invalid
|
||||
"yyyy-MM-dd'T'HH:mmz", // invalid
|
||||
"yyyy-MM-dd't'HH:mmz", // invalid
|
||||
"yyyy-MM-dd'T'HH:mm'Z'", // invalid
|
||||
"yyyy-MM-dd't'HH:mm'z'", // invalid
|
||||
"yyyy-MM-dd", "yyyy-MM", "yyyy" };
|
||||
"yyyy-MM-dd'T'HH:mm:ss.SSS'Z'", "yyyy-MM-dd't'HH:mm:ss.SSS'z'", // invalid
|
||||
"yyyy-MM-dd'T'HH:mm:ssz", "yyyy-MM-dd't'HH:mm:ssz", // invalid
|
||||
"yyyy-MM-dd'T'HH:mm:ss'Z'", "yyyy-MM-dd't'HH:mm:ss'z'", // invalid
|
||||
"yyyy-MM-dd'T'HH:mmz", // invalid
|
||||
"yyyy-MM-dd't'HH:mmz", // invalid
|
||||
"yyyy-MM-dd'T'HH:mm'Z'", // invalid
|
||||
"yyyy-MM-dd't'HH:mm'z'", // invalid
|
||||
"yyyy-MM-dd", "yyyy-MM", "yyyy" };
|
||||
|
||||
static {
|
||||
ADDITIONAL_MASKS = PropertiesLoader.getPropertiesLoader().getTokenizedProperty("datetime.extra.masks", "|");
|
||||
|
|
|
|||
|
|
@ -73,7 +73,7 @@ public class TestSyndFeedAtom03DCSyModules extends TestSyndFeedAtom03 {
|
|||
assertProperty(dc.getRights(), prefix + "dc:rights");
|
||||
} else {
|
||||
assertProperty(dc.getRights(), prefix + "copyright"); // in
|
||||
// header
|
||||
// header
|
||||
// is
|
||||
// convenience
|
||||
// method
|
||||
|
|
|
|||
Loading…
Reference in a new issue