From 3959d43a5c3412704f21b4c69aa723e71e2134e8 Mon Sep 17 00:00:00 2001
From: Michael Peter Christen
Date: Tue, 3 Aug 2021 16:57:24 +0200
Subject: fixed doku link
---
.../yacy/document/parser/GenericXMLParserTest.java | 100 ++++++++++-----------
1 file changed, 50 insertions(+), 50 deletions(-)
(limited to 'test/java')
diff --git a/test/java/net/yacy/document/parser/GenericXMLParserTest.java b/test/java/net/yacy/document/parser/GenericXMLParserTest.java
index d18ed22bc..3d2ae67a3 100644
--- a/test/java/net/yacy/document/parser/GenericXMLParserTest.java
+++ b/test/java/net/yacy/document/parser/GenericXMLParserTest.java
@@ -23,9 +23,9 @@
package net.yacy.document.parser;
import static org.junit.Assert.assertEquals;
+import static org.junit.Assert.assertFalse;
import static org.junit.Assert.assertNotNull;
import static org.junit.Assert.assertTrue;
-import static org.junit.Assert.assertFalse;
import java.io.ByteArrayInputStream;
import java.io.File;
@@ -45,7 +45,7 @@ import net.yacy.document.VocabularyScraper;
/**
* Unit tests for the {@link GenericXMLParser} class
- *
+ *
* @author luccioman
*
*/
@@ -58,13 +58,13 @@ public class GenericXMLParserTest {
@Before
public void setUp() {
- this.parser = new GenericXMLParser();
+ parser = new GenericXMLParser();
}
/**
* Unit test for the GenericXMLParser.parse() function with some small XML
* test files.
- *
+ *
* @throws Exception
* when an unexpected error occurred
*/
@@ -77,7 +77,7 @@ public class GenericXMLParserTest {
FileInputStream inStream = new FileInputStream(new File(folder, fileName));
DigestURL location = new DigestURL("http://localhost/" + fileName);
try {
- Document[] documents = this.parser.parse(location, "text/xml", null, new VocabularyScraper(), 0,
+ Document[] documents = parser.parse(location, "text/xml", null, new VocabularyScraper(), 0,
inStream);
assertNotNull("Parser result must not be null for file " + fileName, documents);
assertNotNull("Parsed text must not be empty for file " + fileName, documents[0].getTextString());
@@ -90,7 +90,7 @@ public class GenericXMLParserTest {
}
/**
- *
+ *
* @param parser
* generic xml parser instance. Must not be null.
* @param encodedXML
@@ -123,10 +123,10 @@ public class GenericXMLParserTest {
/**
* Test UTF-8 charset detection
- *
+ *
* @see RFC 7303 "UTF-8 Charset" example
* (https://tools.ietf.org/html/rfc7303#section-8.1)
- *
+ *
* @throws Exception
* when an unexpected error occurred
*/
@@ -138,7 +138,7 @@ public class GenericXMLParserTest {
*/
byte[] encodedXML = ("" + UMLAUT_TEXT_TAG)
.getBytes(StandardCharsets.UTF_8);
- testCharsetDetection(this.parser, encodedXML, "application/xml; charset=utf-8", StandardCharsets.UTF_8.name(),
+ testCharsetDetection(parser, encodedXML, "application/xml; charset=utf-8", StandardCharsets.UTF_8.name(),
"Maßkrügen");
/*
@@ -146,18 +146,18 @@ public class GenericXMLParserTest {
* declaration
*/
encodedXML = ("" + UMLAUT_TEXT_TAG).getBytes(StandardCharsets.UTF_8);
- testCharsetDetection(this.parser, encodedXML, "application/xml; charset=utf-8", StandardCharsets.UTF_8.name(),
+ testCharsetDetection(parser, encodedXML, "application/xml; charset=utf-8", StandardCharsets.UTF_8.name(),
"Maßkrügen");
}
/**
* Test UTF-16 charset detection
- *
+ *
* @see RFC 7303 "UTF-16 Charset" and
* "Omitted Charset and 16-Bit MIME Entity" examples
* (https://tools.ietf.org/html/rfc7303#section-8.2 and
* https://tools.ietf.org/html/rfc7303#section-8.4)
- *
+ *
* @throws Exception
* when an unexpected error occurred
*/
@@ -169,7 +169,7 @@ public class GenericXMLParserTest {
*/
byte[] encodedXML = ("" + UMLAUT_TEXT_TAG)
.getBytes(StandardCharsets.UTF_16);
- testCharsetDetection(this.parser, encodedXML, "application/xml; charset=utf-16", StandardCharsets.UTF_16.name(),
+ testCharsetDetection(parser, encodedXML, "application/xml; charset=utf-16", StandardCharsets.UTF_16.name(),
"Maßkrügen");
/*
@@ -177,7 +177,7 @@ public class GenericXMLParserTest {
* XML declaration having only BOM (Byte Order Mark)
*/
encodedXML = ("" + UMLAUT_TEXT_TAG).getBytes(StandardCharsets.UTF_16);
- testCharsetDetection(this.parser, encodedXML, "application/xml; charset=utf-16",
+ testCharsetDetection(parser, encodedXML, "application/xml; charset=utf-16",
StandardCharsets.UTF_16BE.name(), "Maßkrügen");
/*
@@ -186,22 +186,22 @@ public class GenericXMLParserTest {
*/
encodedXML = ("" + UMLAUT_TEXT_TAG)
.getBytes(StandardCharsets.UTF_16);
- testCharsetDetection(this.parser, encodedXML, "application/xml", StandardCharsets.UTF_16.name(), "Maßkrügen");
+ testCharsetDetection(parser, encodedXML, "application/xml", StandardCharsets.UTF_16.name(), "Maßkrügen");
/*
* Charset is omitted in both Content-Type HTTP header and XML
* declaration with BOM (Byte Order Mark)
*/
encodedXML = ("" + UMLAUT_TEXT_TAG).getBytes(StandardCharsets.UTF_16);
- testCharsetDetection(this.parser, encodedXML, "application/xml", StandardCharsets.UTF_16BE.name(), "Maßkrügen");
+ testCharsetDetection(parser, encodedXML, "application/xml", StandardCharsets.UTF_16BE.name(), "Maßkrügen");
}
/**
* Test ISO-8859-1 charset detection
- *
+ *
* @see RFC 7303 "Omitted Charset and 8-Bit MIME Entity" example
* (https://tools.ietf.org/html/rfc7303#section-8.3)
- *
+ *
* @throws Exception
* when an unexpected error occurred
*/
@@ -213,7 +213,7 @@ public class GenericXMLParserTest {
*/
byte[] encodedXML = ("" + UMLAUT_TEXT_TAG)
.getBytes(StandardCharsets.ISO_8859_1);
- testCharsetDetection(this.parser, encodedXML, "application/xml", StandardCharsets.ISO_8859_1.name(),
+ testCharsetDetection(parser, encodedXML, "application/xml", StandardCharsets.ISO_8859_1.name(),
"Maßkrügen");
}
@@ -221,10 +221,10 @@ public class GenericXMLParserTest {
* Test charset detection when the character encoding is omitted in
* Content-Type header, and content has a XML declaration with no encoding
* declaration
- *
+ *
* @see RFC 7303 "Omitted Charset, No Internal Encoding Declaration" example
* (https://tools.ietf.org/html/rfc7303#section-8.5)
- *
+ *
* @throws Exception
* when an unexpected error occurred
*/
@@ -242,15 +242,15 @@ public class GenericXMLParserTest {
encodedXML = (""
+ "In München steht ein Hofbräuhaus, dort gibt es Bier in Maßkrügen")
.getBytes(StandardCharsets.US_ASCII);
- testCharsetDetection(this.parser, encodedXML, "application/xml", StandardCharsets.UTF_8.name(), "Maßkrügen");
+ testCharsetDetection(parser, encodedXML, "application/xml", StandardCharsets.UTF_8.name(), "Maßkrügen");
}
/**
* Test UTF-16BE charset detection
- *
+ *
* @see RFC 7303 "UTF-16BE Charset" example
* (https://tools.ietf.org/html/rfc7303#section-8.6)
- *
+ *
* @throws Exception
* when an unexpected error occurred
*/
@@ -262,13 +262,13 @@ public class GenericXMLParserTest {
*/
byte[] encodedXML = ("" + UMLAUT_TEXT_TAG)
.getBytes(StandardCharsets.UTF_16BE);
- testCharsetDetection(this.parser, encodedXML, "application/xml; charset=utf-16be",
+ testCharsetDetection(parser, encodedXML, "application/xml; charset=utf-16be",
StandardCharsets.UTF_16BE.name(), "Maßkrügen");
}
/**
* Test absolute URLs detection in XML elements attributes.
- *
+ *
* @throws Exception
* when an unexpected error occurred
*/
@@ -288,7 +288,7 @@ public class GenericXMLParserTest {
String charsetFromHttpHeader = HeaderFramework.getCharacterEncoding(contentTypeHeader);
DigestURL location = new DigestURL("http://localhost/testfile.xml");
try {
- Document[] documents = this.parser.parse(location, contentTypeHeader, charsetFromHttpHeader,
+ Document[] documents = parser.parse(location, contentTypeHeader, charsetFromHttpHeader,
new VocabularyScraper(), 0, inStream);
assertEquals(1, documents.length);
Collection detectedAnchors = documents[0].getAnchors();
@@ -304,7 +304,7 @@ public class GenericXMLParserTest {
/**
* Test absolute URLs detection in XML elements text.
- *
+ *
* @throws Exception
* when an unexpected error occurred
*/
@@ -324,7 +324,7 @@ public class GenericXMLParserTest {
String charsetFromHttpHeader = HeaderFramework.getCharacterEncoding(contentTypeHeader);
DigestURL location = new DigestURL("http://localhost/testfile.xml");
try {
- Document[] documents = this.parser.parse(location, contentTypeHeader, charsetFromHttpHeader,
+ Document[] documents = parser.parse(location, contentTypeHeader, charsetFromHttpHeader,
new VocabularyScraper(), 0, inStream);
assertEquals(1, documents.length);
Collection detectedAnchors = documents[0].getAnchors();
@@ -337,7 +337,7 @@ public class GenericXMLParserTest {
inStream.close();
}
}
-
+
/**
* Test parsing well-formed XML fragment (no XML declaration, no DTD or schema)
* @throws Exception when an unexpected error occurred
@@ -351,18 +351,18 @@ public class GenericXMLParserTest {
String charsetFromHttpHeader = HeaderFramework.getCharacterEncoding(contentTypeHeader);
DigestURL location = new DigestURL("http://localhost/testfile.xml");
try {
- Document[] documents = this.parser.parse(location, contentTypeHeader, charsetFromHttpHeader,
+ Document[] documents = parser.parse(location, contentTypeHeader, charsetFromHttpHeader,
new VocabularyScraper(), 0, inStream);
assertEquals(1, documents.length);
assertEquals("Node content1 Node content2", documents[0].getTextString());
} finally {
inStream.close();
- }
+ }
}
-
+
/**
* Test URLs detection when applying limits.
- *
+ *
* @throws Exception
* when an unexpected error occurred
*/
@@ -376,7 +376,7 @@ public class GenericXMLParserTest {
+ "Home page : http://yacy.net - International Forum : "
+ "https://searchlab.eu "
+ "and this is a mention to a relative URL : /document.html
"
- + "Here are YaCybug tracker and Wiki."
+ + "
Here are YaCybug tracker and Wiki."
+ "And this is a relative link to another sub document
"
+ "