什么';在文本/xml值中编码CR-LF换行符的正确方法是什么?
与可以做任何事情的application/xml文件,或将所有空白序列转换为单个空格字符的normalizedString值不同,我在这里专门针对具有字符串值的text/xml文件进行提问。为了简单起见,假设我只对UTF8编码的文件使用ASCII字符 给定我希望用XML表示的以下两行文本字符串:什么';在文本/xml值中编码CR-LF换行符的正确方法是什么?,xml,xml-serialization,Xml,Xml Serialization,与可以做任何事情的application/xml文件,或将所有空白序列转换为单个空格字符的normalizedString值不同,我在这里专门针对具有字符串值的text/xml文件进行提问。为了简单起见,假设我只对UTF8编码的文件使用ASCII字符 给定我希望用XML表示的以下两行文本字符串: Hello World! 这是内存中的以下字节: 0000: 48 65 6c 6c 6f 0d 0a 57 6f 72 6c 64 21 Hello..World! 根据RFC 2046,任何te
Hello
World!
这是内存中的以下字节:
0000: 48 65 6c 6c 6f 0d 0a 57 6f 72 6c 64 21 Hello..World!
根据RFC 2046,任何text/*MIME类型都必须(不应该)使用回车符后跟换行字符序列来表示换行符。因此,以下XML片段应该是正确的:
<tag>Hello
World!</tag>
你好
世界!
或
0000:3c 74 61 67 3c 48 65 6c 6c 6f 0d 0a 57 6f 72 6c你好..世界
0010:64 21 3c 2f 74 61 67 3c d!
但我经常看到如下文件:
<tag><![CDATA[Hello
World!]]></tag>
更奇怪的是:
<tag>Hello&xD;
World!</tag>
Hello&xD;
世界!
其中&0xD;序列后面跟着一个换行字符:
0000: 3c 74 61 67 3c 48 65 6c 6c 6f 26 78 44 3b 0a 57 <tag>Hello&xD;.W
0010: 6f 72 6c 64 21 3c 2f 74 61 67 3c orld!</tag>
0000:3c 74 61 67 3c 48 65 6c 6c 6f 26 78 44 3b 0a 57 Hello&xD;。W
0010:6f 72 6c 64 21 3c 2f 74 61 67 3c世界!
我错过了什么?在XML字符串值中表示多行文本的正确方法是什么,以便它可以在另一端不受干扰地显示出来?CR(&x0D;)、LF(&x0A;)、CRLF或其他一些组合都是有效的。如中所述,所有这些都转换为单个&x0A;字符。在用Mono编写NUnit测试和用Java编写JUnit测试之后,答案似乎是使用Hello \世界!或者你好 \世界!如下 Foo.cs:
using System.IO;
using System.Text;
using System.Xml.Serialization;
namespace XmlStringTests
{
public class Foo
{
public string greeting;
public static Foo DeserializeFromXmlString (string xml)
{
Foo result;
using (MemoryStream memoryStream = new MemoryStream()) {
byte[] buffer = Encoding.UTF8.GetBytes (xml);
memoryStream.Write (buffer, 0, buffer.Length);
memoryStream.Seek (0, SeekOrigin.Begin);
XmlSerializer xs = new XmlSerializer (typeof(Foo));
result = (Foo)xs.Deserialize (memoryStream);
}
return result;
}
}
}
XmlStringTests.cs:
using NUnit.Framework;
namespace XmlStringTests
{
[TestFixture]
public class XmlStringTests
{
const string expected = "Hello\u000d\u000aWorld!";
[Test(Description="Fails")]
public void Cdata ()
{
const string test = "<Foo><greeting><![CDATA[Hello\u000d\u000aWorld!]]></greeting></Foo>";
Foo bar = Foo.DeserializeFromXmlString (test);
Assert.AreEqual (expected, bar.greeting);
}
[Test(Description="Fails")]
public void CdataWithHash13 ()
{
const string test = "<Foo><greeting><![CDATA[Hello \u000aWorld!]]></greeting></Foo>";
Foo bar = Foo.DeserializeFromXmlString (test);
Assert.AreEqual (expected, bar.greeting);
}
[Test(Description="Fails")]
public void CdataWithHashxD ()
{
const string test = "<Foo><greeting><![CDATA[Hello
\u000aWorld!]]></greeting></Foo>";
Foo bar = Foo.DeserializeFromXmlString (test);
Assert.AreEqual (expected, bar.greeting);
}
[Test(Description="Fails")]
public void Simple ()
{
const string test = "<Foo><greeting>Hello\u000d\u000aWorld!</greeting></Foo>";
Foo bar = Foo.DeserializeFromXmlString (test);
Assert.AreEqual (expected, bar.greeting);
}
[Test(Description="Passes")]
public void SimpleWithHash13 ()
{
const string test = "<Foo><greeting>Hello \u000aWorld!</greeting></Foo>";
Foo bar = Foo.DeserializeFromXmlString (test);
Assert.AreEqual (expected, bar.greeting);
}
[Test(Description="Passes")]
public void SimpleWithHashxD ()
{
const string test = "<Foo><greeting>Hello
\u000aWorld!</greeting></Foo>";
Foo bar = Foo.DeserializeFromXmlString (test);
Assert.AreEqual (expected, bar.greeting);
}
}
}
XmlStringTests.java:
import static org.junit.Assert.*;
import org.junit.Test;
public class XmlStringTests {
String expected = "Hello\r\nWorld!";
@Test //Fails
public void testCdata ()
{
String test = "<Foo><greeting><![CDATA[Hello\r\nWorld!]]></greeting></Foo>";
Foo bar = Foo.DeserializeFromXmlString (test);
assertEquals (expected, bar.greeting);
}
@Test //Fails
public void testCdataWithHash13 ()
{
String test = "<Foo><greeting><![CDATA[Hello \nWorld!]]></greeting></Foo>";
Foo bar = Foo.DeserializeFromXmlString (test);
assertEquals (expected, bar.greeting);
}
@Test //Fails
public void testCdataWithHashxD ()
{
String test = "<Foo><greeting><![CDATA[Hello
\nWorld!]]></greeting></Foo>";
Foo bar = Foo.DeserializeFromXmlString (test);
assertEquals (expected, bar.greeting);
}
@Test //Fails
public void testSimple ()
{
String test = "<Foo><greeting>Hello\r\nWorld!</greeting></Foo>";
Foo bar = Foo.DeserializeFromXmlString (test);
assertEquals (expected, bar.greeting);
}
@Test //Passes
public void testSimpleWithHash13 ()
{
String test = "<Foo><greeting>Hello \nWorld!</greeting></Foo>";
Foo bar = Foo.DeserializeFromXmlString (test);
assertEquals (expected, bar.greeting);
}
@Test //Passes
public void testSimpleWithHashxD ()
{
String test = "<Foo><greeting>Hello
\nWorld!</greeting></Foo>";
Foo bar = Foo.DeserializeFromXmlString (test);
assertEquals (expected, bar.greeting);
}
}
import static org.junit.Assert.*;
导入org.junit.Test;
公共类XmlStringTests{
字符串应为=“Hello\r\nWorld!”;
@测试//失败
公共void testCdata()
{
字符串测试=”;
Foo bar=Foo.DeserializeFromXmlString(测试);
assertEquals(预期,酒吧问候语);
}
@测试//失败
public void testCdataWithHash13()
{
字符串测试=”;
Foo bar=Foo.DeserializeFromXmlString(测试);
assertEquals(预期,酒吧问候语);
}
@测试//失败
公共void TestCDATA WithHashXD()
{
字符串测试=”;
Foo bar=Foo.DeserializeFromXmlString(测试);
assertEquals(预期,酒吧问候语);
}
@测试//失败
公共void testSimple()
{
字符串测试=“你好\r\nWorld!”;
Foo bar=Foo.DeserializeFromXmlString(测试);
assertEquals(预期,酒吧问候语);
}
@测试//通过
public void testSimpleWithHash13()
{
String test=“你好
;\nWorld!”;
Foo bar=Foo.DeserializeFromXmlString(测试);
assertEquals(预期,酒吧问候语);
}
@测试//通过
public void testSimpleWithHashxD()
{
String test=“你好
;\nWorld!”;
Foo bar=Foo.DeserializeFromXmlString(测试);
assertEquals(预期,酒吧问候语);
}
}
我希望这能节省一些人的时间。根据相同的规范,CR(#d)是CDATA块中的有效字符,因此不应进行转换。我将从CR LF输入中获取LF定义为被骚扰。有没有一种方法可以正确地对XML进行编码,以使CR LF在接收端返回,或者XML只是被破坏了,不适合文本/XML MIME类型?在阅读规范时,我将其解释为:如果在输入中发现以下任何原始代码点序列,请将其替换为
0xd 0xa
:0xd 0x85
,0x85
,0x2028
,0xd«除0xa或0x85以外的任何内容
。由于此替换发生在“解析之前”(请参阅参考资料),因此应保留任何文字字符实体(即和#xd
)。因此,对于该示例,解析的内容应该是字节序列0xd
,而不是0xa
。我读的规范正确吗?您的答案似乎表明此替换可能发生在解析之后,而不是之前…
import java.io.StringReader;
import javax.xml.bind.JAXBContext;
import javax.xml.bind.JAXBException;
import javax.xml.bind.Unmarshaller;
import javax.xml.bind.annotation.XmlRootElement;
import javax.xml.bind.annotation.XmlType;
@XmlRootElement(name = "Foo")
@XmlType(propOrder = { "greeting" })
public class Foo {
public String greeting;
public static Foo DeserializeFromXmlString(String xml) {
try {
JAXBContext context = JAXBContext.newInstance(Foo.class);
Unmarshaller unmarshaller = context.createUnmarshaller();
Foo foo = (Foo) unmarshaller.unmarshal(new StringReader(xml));
return foo;
} catch (JAXBException e) {
e.printStackTrace();
return null;
}
}
}
import static org.junit.Assert.*;
import org.junit.Test;
public class XmlStringTests {
String expected = "Hello\r\nWorld!";
@Test //Fails
public void testCdata ()
{
String test = "<Foo><greeting><![CDATA[Hello\r\nWorld!]]></greeting></Foo>";
Foo bar = Foo.DeserializeFromXmlString (test);
assertEquals (expected, bar.greeting);
}
@Test //Fails
public void testCdataWithHash13 ()
{
String test = "<Foo><greeting><![CDATA[Hello \nWorld!]]></greeting></Foo>";
Foo bar = Foo.DeserializeFromXmlString (test);
assertEquals (expected, bar.greeting);
}
@Test //Fails
public void testCdataWithHashxD ()
{
String test = "<Foo><greeting><![CDATA[Hello
\nWorld!]]></greeting></Foo>";
Foo bar = Foo.DeserializeFromXmlString (test);
assertEquals (expected, bar.greeting);
}
@Test //Fails
public void testSimple ()
{
String test = "<Foo><greeting>Hello\r\nWorld!</greeting></Foo>";
Foo bar = Foo.DeserializeFromXmlString (test);
assertEquals (expected, bar.greeting);
}
@Test //Passes
public void testSimpleWithHash13 ()
{
String test = "<Foo><greeting>Hello \nWorld!</greeting></Foo>";
Foo bar = Foo.DeserializeFromXmlString (test);
assertEquals (expected, bar.greeting);
}
@Test //Passes
public void testSimpleWithHashxD ()
{
String test = "<Foo><greeting>Hello
\nWorld!</greeting></Foo>";
Foo bar = Foo.DeserializeFromXmlString (test);
assertEquals (expected, bar.greeting);
}
}