PatchesAndForks/rome
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

enhancement for #181 - sets user-agent header on UrlConnection

Browse source
This commit is contained in:
Martin Kurz 2014-04-18 20:32:46 +02:00
parent fee63dd5b1
commit 95629798ba
2 changed files with 59 additions and 74 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

13
pom.xml
View file

@ -78,6 +78,19 @@
<build> <build>
<plugins> <plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-jar-plugin</artifactId>
<version>2.4</version>
<configuration>
<archive>
<manifest>
<addDefaultImplementationEntries>true</addDefaultImplementationEntries>
<addDefaultSpecificationEntries>true</addDefaultSpecificationEntries>
</manifest>
</archive>
</configuration>
</plugin>
<plugin> <plugin>
<groupId>org.apache.maven.plugins</groupId> <groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-site-plugin</artifactId> <artifactId>maven-site-plugin</artifactId>

120
src/main/java/com/sun/syndication/io/XmlReader.java
View file

@ -34,25 +34,18 @@ import java.util.regex.Matcher;
import java.util.regex.Pattern; import java.util.regex.Pattern;
/** /**
* Character stream that handles (or at least attemtps to) all the necessary Voodo to figure out the * 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.
* charset encoding of the XML document within the stream.
* <p> * <p>
* IMPORTANT: This class is not related in any way to the org.xml.sax.XMLReader. This one IS a * IMPORTANT: This class is not related in any way to the org.xml.sax.XMLReader. This one IS a character stream.
* character stream.
* <p> * <p>
* All this has to be done without consuming characters from the stream, if not the XML parser will * 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%
* not recognized the document as a valid XML. This is not 100% true, but it's close enough (UTF-8 * 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).
* BOM is not handled by all parsers right now, XmlReader handles it and things work in all
* parsers).
* <p> * <p>
* The XmlReader class handles the charset encoding of XML documents in Files, raw streams and HTTP * The XmlReader class handles the charset encoding of XML documents in Files, raw streams and HTTP streams by offering a wide set of constructors.
* streams by offering a wide set of constructors.
* <P> * <P>
* By default the charset encoding detection is lenient, the constructor with the lenient flag can * 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
* be used for an script (following HTTP MIME and XML specifications). All this is nicely explained * 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
* by Mark Pilgrim in his blog, <a * the character encoding of a feed</a>.
* href="http://diveintomark.org/archives/2004/02/13/xml-media-types"> Determining the character
* encoding of a feed</a>.
* <p> * <p>
* *
* @author Alejandro Abdelnur * @author Alejandro Abdelnur
@ -87,11 +80,9 @@ public class XmlReader extends Reader {
/** /**
* Creates a Reader for a File. * Creates a Reader for a File.
* <p> * <p>
* It looks for the UTF-8 BOM first, if none sniffs the XML prolog charset, if this is also * It looks for the UTF-8 BOM first, if none sniffs the XML prolog charset, if this is also missing defaults to UTF-8.
* missing defaults to UTF-8.
* <p> * <p>
* It does a lenient charset encoding detection, check the constructor with the lenient * It does a lenient charset encoding detection, check the constructor with the lenient parameter for details.
* parameter for details.
* <p> * <p>
* *
* @param file File to create a Reader from. * @param file File to create a Reader from.
@ -107,8 +98,7 @@ public class XmlReader extends Reader {
* <p> * <p>
* It follows the same logic used for files. * It follows the same logic used for files.
* <p> * <p>
* It does a lenient charset encoding detection, check the constructor with the lenient * It does a lenient charset encoding detection, check the constructor with the lenient parameter for details.
* parameter for details.
* <p> * <p>
* *
* @param is InputStream to create a Reader from. * @param is InputStream to create a Reader from.
@ -120,16 +110,13 @@ public class XmlReader extends Reader {
} }
/** /**
* Creates a Reader for a raw InputStream and uses the provided default encoding if none is * Creates a Reader for a raw InputStream and uses the provided default encoding if none is determined.
* determined.
* <p> * <p>
* It follows the same logic used for files. * It follows the same logic used for files.
* <p> * <p>
* If lenient detection is indicated and the detection above fails as per specifications it then * If lenient detection is indicated and the detection above fails as per specifications it then attempts the following:
* attempts the following:
* <p> * <p>
* If the content type was 'text/html' it replaces it with 'text/xml' and tries the detection * If the content type was 'text/html' it replaces it with 'text/xml' and tries the detection again.
* again.
* <p> * <p>
* Else if the XML prolog had a charset encoding that encoding is used. * Else if the XML prolog had a charset encoding that encoding is used.
* <p> * <p>
@ -144,8 +131,7 @@ public class XmlReader extends Reader {
* @param lenient indicates if the charset encoding detection should be relaxed. * @param lenient indicates if the charset encoding detection should be relaxed.
* @param defaultEncoding default encoding to use if one cannot be detected. * @param defaultEncoding default encoding to use if one cannot be detected.
* @throws IOException thrown if there is a problem reading the stream. * @throws IOException thrown if there is a problem reading the stream.
* @throws XmlReaderException thrown if the charset encoding could not be determined according * @throws XmlReaderException thrown if the charset encoding could not be determined according to the specs.
* to the specs.
* *
*/ */
public XmlReader(final InputStream is, final boolean lenient, final String defaultEncoding) throws IOException, XmlReaderException { public XmlReader(final InputStream is, final boolean lenient, final String defaultEncoding) throws IOException, XmlReaderException {
@ -170,11 +156,9 @@ public class XmlReader extends Reader {
* <p> * <p>
* It follows the same logic used for files. * It follows the same logic used for files.
* <p> * <p>
* If lenient detection is indicated and the detection above fails as per specifications it then * If lenient detection is indicated and the detection above fails as per specifications it then attempts the following:
* attempts the following:
* <p> * <p>
* If the content type was 'text/html' it replaces it with 'text/xml' and tries the detection * If the content type was 'text/html' it replaces it with 'text/xml' and tries the detection again.
* again.
* <p> * <p>
* Else if the XML prolog had a charset encoding that encoding is used. * Else if the XML prolog had a charset encoding that encoding is used.
* <p> * <p>
@ -188,8 +172,7 @@ public class XmlReader extends Reader {
* @param is InputStream to create a Reader from. * @param is InputStream to create a Reader from.
* @param lenient indicates if the charset encoding detection should be relaxed. * @param lenient indicates if the charset encoding detection should be relaxed.
* @throws IOException thrown if there is a problem reading the stream. * @throws IOException thrown if there is a problem reading the stream.
* @throws XmlReaderException thrown if the charset encoding could not be determined according * @throws XmlReaderException thrown if the charset encoding could not be determined according to the specs.
* to the specs.
* *
*/ */
public XmlReader(final InputStream is, final boolean lenient) throws IOException, XmlReaderException { public XmlReader(final InputStream is, final boolean lenient) throws IOException, XmlReaderException {
@ -199,14 +182,11 @@ public class XmlReader extends Reader {
/** /**
* Creates a Reader using the InputStream of a URL. * Creates a Reader using the InputStream of a URL.
* <p> * <p>
* If the URL is not of type HTTP and there is not 'content-type' header in the fetched data it * 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.
* uses the same logic used for Files.
* <p> * <p>
* If the URL is a HTTP Url or there is a 'content-type' header in the fetched data it uses the * 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.
* same logic used for an InputStream with content-type.
* <p> * <p>
* It does a lenient charset encoding detection, check the constructor with the lenient * It does a lenient charset encoding detection, check the constructor with the lenient parameter for details.
* parameter for details.
* <p> * <p>
* *
* @param url URL to create a Reader from. * @param url URL to create a Reader from.
@ -220,14 +200,12 @@ public class XmlReader extends Reader {
/** /**
* Creates a Reader using the InputStream of a URLConnection. * Creates a Reader using the InputStream of a URLConnection.
* <p> * <p>
* If the URLConnection is not of type HttpURLConnection and there is not 'content-type' header * 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.
* in the fetched data it uses the same logic used for files.
* <p> * <p>
* If the URLConnection is a HTTP Url or there is a 'content-type' header in the fetched data it * 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
* uses the same logic used for an InputStream with content-type. * content-type.
* <p> * <p>
* It does a lenient charset encoding detection, check the constructor with the lenient * It does a lenient charset encoding detection, check the constructor with the lenient parameter for details.
* parameter for details.
* <p> * <p>
* *
* @param conn URLConnection to create a Reader from. * @param conn URLConnection to create a Reader from.
@ -238,6 +216,12 @@ public class XmlReader extends Reader {
defaultEncoding = staticDefaultEncoding; defaultEncoding = staticDefaultEncoding;
final boolean lenient = true; final boolean lenient = true;
if (conn instanceof HttpURLConnection) { if (conn instanceof HttpURLConnection) {
final Package pckg = this.getClass().getPackage();
if (pckg.getImplementationTitle() != null && pckg.getImplementationVersion() != null) {
conn.setRequestProperty("User-Agent", pckg.getImplementationTitle() + "/" + pckg.getImplementationVersion());
} else {
conn.setRequestProperty("User-Agent", "ROME");
}
try { try {
doHttpStream(conn.getInputStream(), conn.getContentType(), lenient); doHttpStream(conn.getInputStream(), conn.getContentType(), lenient);
} catch (final XmlReaderException ex) { } catch (final XmlReaderException ex) {
@ -261,12 +245,10 @@ public class XmlReader extends Reader {
/** /**
* Creates a Reader using an InputStream and the associated content-type header. * Creates a Reader using an InputStream and the associated content-type header.
* <p> * <p>
* First it checks if the stream has BOM. If there is not BOM checks the content-type encoding. * 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
* If there is not content-type encoding checks the XML prolog encoding. If there is not XML * encoding. If there is not XML prolog encoding uses the default encoding mandated by the content-type MIME type.
* prolog encoding uses the default encoding mandated by the content-type MIME type.
* <p> * <p>
* It does a lenient charset encoding detection, check the constructor with the lenient * It does a lenient charset encoding detection, check the constructor with the lenient parameter for details.
* parameter for details.
* <p> * <p>
* *
* @param is InputStream to create the reader from. * @param is InputStream to create the reader from.
@ -281,15 +263,12 @@ public class XmlReader extends Reader {
/** /**
* Creates a Reader using an InputStream and the associated content-type header. * Creates a Reader using an InputStream and the associated content-type header.
* <p> * <p>
* First it checks if the stream has BOM. If there is not BOM checks the content-type encoding. * 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
* If there is not content-type encoding checks the XML prolog encoding. If there is not XML * encoding. If there is not XML prolog encoding uses the default encoding mandated by the content-type MIME type.
* prolog encoding uses the default encoding mandated by the content-type MIME type.
* <p> * <p>
* If lenient detection is indicated and the detection above fails as per specifications it then * If lenient detection is indicated and the detection above fails as per specifications it then attempts the following:
* attempts the following:
* <p> * <p>
* If the content type was 'text/html' it replaces it with 'text/xml' and tries the detection * If the content type was 'text/html' it replaces it with 'text/xml' and tries the detection again.
* again.
* <p> * <p>
* Else if the XML prolog had a charset encoding that encoding is used. * Else if the XML prolog had a charset encoding that encoding is used.
* <p> * <p>
@ -305,8 +284,7 @@ public class XmlReader extends Reader {
* @param lenient indicates if the charset encoding detection should be relaxed. * @param lenient indicates if the charset encoding detection should be relaxed.
* @param defaultEncoding default encoding to use if one cannot be detected. * @param defaultEncoding default encoding to use if one cannot be detected.
* @throws IOException thrown if there is a problem reading the file. * @throws IOException thrown if there is a problem reading the file.
* @throws XmlReaderException thrown if the charset encoding could not be determined according * @throws XmlReaderException thrown if the charset encoding could not be determined according to the specs.
* to the specs.
* *
*/ */
public XmlReader(final InputStream is, final String httpContentType, final boolean lenient, final String defaultEncoding) throws IOException, public XmlReader(final InputStream is, final String httpContentType, final boolean lenient, final String defaultEncoding) throws IOException,
@ -330,15 +308,12 @@ public class XmlReader extends Reader {
/** /**
* Creates a Reader using an InputStream and the associated content-type header. * Creates a Reader using an InputStream and the associated content-type header.
* <p> * <p>
* First it checks if the stream has BOM. If there is not BOM checks the content-type encoding. * 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
* If there is not content-type encoding checks the XML prolog encoding. If there is not XML * encoding. If there is not XML prolog encoding uses the default encoding mandated by the content-type MIME type.
* prolog encoding uses the default encoding mandated by the content-type MIME type.
* <p> * <p>
* If lenient detection is indicated and the detection above fails as per specifications it then * If lenient detection is indicated and the detection above fails as per specifications it then attempts the following:
* attempts the following:
* <p> * <p>
* If the content type was 'text/html' it replaces it with 'text/xml' and tries the detection * If the content type was 'text/html' it replaces it with 'text/xml' and tries the detection again.
* again.
* <p> * <p>
* Else if the XML prolog had a charset encoding that encoding is used. * Else if the XML prolog had a charset encoding that encoding is used.
* <p> * <p>
@ -353,8 +328,7 @@ public class XmlReader extends Reader {
* @param httpContentType content-type header to use for the resolution of the charset encoding. * @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. * @param lenient indicates if the charset encoding detection should be relaxed.
* @throws IOException thrown if there is a problem reading the file. * @throws IOException thrown if there is a problem reading the file.
* @throws XmlReaderException thrown if the charset encoding could not be determined according * @throws XmlReaderException thrown if the charset encoding could not be determined according to the specs.
* to the specs.
* *
*/ */
public XmlReader(final InputStream is, final String httpContentType, final boolean lenient) throws IOException, XmlReaderException { public XmlReader(final InputStream is, final String httpContentType, final boolean lenient) throws IOException, XmlReaderException {
@ -362,8 +336,7 @@ public class XmlReader extends Reader {
} }
/** /**
* Returns the default encoding to use if none is set in HTTP content-type, XML prolog and the * 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.
* rules based on content-type are not adequate.
* <p/> * <p/>
* If it is NULL the content-type based rules are used. * If it is NULL the content-type based rules are used.
* <p/> * <p/>
@ -375,8 +348,7 @@ public class XmlReader extends Reader {
} }
/** /**
* Sets the default encoding to use if none is set in HTTP content-type, XML prolog and the * 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.
* rules based on content-type are not adequate.
* <p/> * <p/>
* If it is set to NULL the content-type based rules are used. * If it is set to NULL the content-type based rules are used.
* <p/> * <p/>